{ "openapi": "3.1.0", "info": { "title": "deAPI REST API", "description": "Decentralized AI inference API for image generation, video processing, audio transcription, and more.\n\n## Rate limits\n\nTwo windows can apply to a request: a per-minute one (RPM) and a per-day one (RPD). Every\nthrottled response — success or 429 — carries the `X-RateLimit-*` headers, so you can pace\ntraffic without waiting to be rejected. Each header documents itself: see `components/headers`,\nor the headers listed on any response. What follows is only what a header cannot say about\nitself.\n\nWindows open on your first request into a bucket and run their full length from that second —\nnever to a calendar boundary, in any timezone. That is deliberate: a boundary every account\nshares is a boundary every account can double up on.\n\n**The headers describe the pool *this* request landed in, and `X-RateLimit-Source` is what\nidentifies it — not `X-RateLimit-Limit` alone.** A per-model limit is keyed to the model you\nnamed, so a request that carried no recognised `model` — rejected at validation, an unknown\nslug, an empty body — was counted against your tier pool, and it is the tier pool the headers\nthen describe. The two pools are fully independent: separate minute window, separate day,\nseparate `X-RateLimit-Daily-Reset`. This is a consequence of rate limiting running *before*\nvalidation, which is what keeps malformed traffic from reaching the rest of the API\nuncounted. Compare headers only across responses carrying the same `X-RateLimit-Source`.\n\n**Buckets are shared in ways worth knowing.** API **v1 and v2 count against the same bucket**,\nso migrating grants no fresh allowance and mixed traffic behaves as one stream. All `*/price`\nand `*/price-calculation` endpoints share a single quote bucket, separate from generation.\nPrompt enhancement (`/v2/prompts/enhancements`) has its own bucket as well, so heavy prompt\nwork no longer eats into your image throughput.\n\n**Counting is exact in sequence, best-effort in parallel.** Sent one after another, your\nrequests are counted precisely: the one that crosses the limit is the one that gets 429. Sent\nin parallel, a few beyond the limit can slip through, because the counter is read and then\nincremented as two steps and requests already in flight are not yet visible to one another.\nThe excess is bounded by how many of your own requests are in flight at once, and it only\never runs in your favour — you are never rejected while below your limit. So do not treat\n`X-RateLimit-Remaining` as a reservation: it is a snapshot, and a request you sent a\nmillisecond ago may already have spent what it shows.\n\n**Not every 429 comes from the request rate.** Creating API keys has its own hourly bucket,\nand a key with an IP whitelist has one for calls from addresses it refuses. A 429 always\ndescribes the bucket that actually refused it — `X-RateLimit-Type` names that bucket, and\nevery other `X-RateLimit-*` header on the response belongs to it. So back off on the headers\nyou were sent, and do not carry figures from one 429 over to the next.\n\n**A call refused by a key's IP whitelist does not spend the account's request allowance.**\nIt is counted against the address it came from instead, on a much tighter window — so a\nwhitelist cannot be turned against the owner it protects, and being refused still does not\ncome free.\n\nRequests rejected before authentication (HTTP 401) never reach the limiter and carry no\nrate-limit headers at all.", "contact": { "name": "deAPI Support", "url": "https://deapi.ai", "email": "support@deapi.ai" }, "version": "0.0.1" }, "servers": [ { "url": "https://api.deapi.ai", "description": "Production API Server base URL" } ], "paths": { "/api/v2/account": { "get": { "tags": [ "Client API v2" ], "summary": "Get the account's billing", "description": "Balance and automatic top-up settings. Needs an ADMIN key.", "operationId": "getAccount", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "responses": { "200": { "description": "The account's billing.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/AccountBilling" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/account/payments": { "get": { "tags": [ "Client API v2" ], "summary": "List the account's payments", "description": "Top-ups of the balance, newest first, in every status. Needs an ADMIN key.", "operationId": "listAccountPayments", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "$ref": "#/components/parameters/ListLimit" }, { "$ref": "#/components/parameters/ListPerPage" }, { "$ref": "#/components/parameters/ListPage" } ], "responses": { "200": { "description": "A page of payments.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/PaymentCollection" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/key": { "get": { "tags": [ "Client API v2" ], "summary": "Get the calling API key", "description": "The key sending the request: name, preview, role, status, dates, spend limit and IP whitelist. Never the secret. Works with any key role.", "operationId": "getCurrentApiKey", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "responses": { "200": { "description": "The calling key.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/ApiKeyResource" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/keys": { "get": { "tags": [ "Client API v2" ], "summary": "List the account's API keys", "description": "Every key of the account, newest first. Needs an ADMIN key. Never secrets.", "operationId": "listApiKeys", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "$ref": "#/components/parameters/ListLimit" }, { "$ref": "#/components/parameters/ListPerPage" }, { "$ref": "#/components/parameters/ListPage" } ], "responses": { "200": { "description": "A page of keys.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ApiKeyCollection" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] }, "post": { "tags": [ "Client API v2" ], "summary": "Create an API key", "description": "Creates a key with the API role. Needs an ADMIN key; ADMIN keys can only be created in the Dashboard. **The secret is returned once, in this response.** Counts toward the account's limit of active keys and the hourly limit of keys created over the API (shared by all ADMIN keys of the account). An `ip_whitelist` given here applies from the key's first call.", "operationId": "createApiKey", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "required": [ "name" ], "properties": { "name": { "type": "string", "example": "Customer 1234", "maxLength": 255 }, "expires_at": { "description": "Optional. Leave it out for a key that never expires. A date must be in the future and no later than 2038-01-19 03:14:07 UTC, the latest instant this platform can store — a 422, not a silently shortened key.", "type": [ "string", "null" ], "format": "date-time", "example": "2026-12-31T23:59:59Z" }, "role": { "description": "Only `api`. `admin` is refused with 403.", "type": "string", "example": "api", "enum": [ "api", "admin" ] }, "ip_whitelist": { "$ref": "#/components/schemas/ApiKeyIpWhitelist", "description": "Optional. The only addresses the new key may be used from; omitted or `[]` means any. Duplicates and surrounding whitespace are removed, an explicit `null` is refused." }, "limit": { "$ref": "#/components/schemas/ApiKeySpendLimit", "description": "Optional. What this key may spend per window, in USD; omitted or `null` means no limit. Work that would take the key past it is refused with 402 `key_limit_exceeded`." }, "reset_interval": { "description": "How often that limit starts over; `none` means it never does. Only accepted together with a non-null `limit`. Windows are anchored on the key's creation instant, not the calendar.", "type": "string", "example": "monthly", "default": "none", "enum": [ "none", "daily", "weekly", "monthly" ] } }, "type": "object" } } } }, "responses": { "201": { "description": "The new key, with its secret.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/CreatedApiKeyResource" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "422": { "$ref": "#/components/responses/ApiKeyLimitReached" }, "429": { "$ref": "#/components/responses/ApiKeyCreationRateLimited" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/keys/{id}": { "get": { "tags": [ "Client API v2" ], "summary": "Get an API key", "description": "Any key of the account. Needs an ADMIN key.", "operationId": "getApiKey", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "name": "id", "in": "path", "required": true, "schema": { "type": "integer" } } ], "responses": { "200": { "description": "The key.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/ApiKeyResource" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "404": { "description": "No such key on this account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] }, "delete": { "tags": [ "Client API v2" ], "summary": "Delete an API key", "description": "Permanently deletes an API-role key. Needs an ADMIN key; ADMIN keys are deleted in the Dashboard only. The key's past usage stays in usage reports.", "operationId": "deleteApiKey", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "name": "id", "in": "path", "required": true, "schema": { "type": "integer" } } ], "responses": { "204": { "description": "Deleted." }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "404": { "description": "No such key on this account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] }, "patch": { "tags": [ "Client API v2" ], "summary": "Change an API key", "description": "Switches an API-role key on or off, changes its expiry date, spend limit and reset window, and sets the addresses it may be used from. Needs an ADMIN key. The role cannot be changed; ADMIN keys are changed in the Dashboard only. Making a key active again counts toward the limit of active keys.", "operationId": "updateApiKey", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "name": "id", "in": "path", "required": true, "schema": { "type": "integer" } } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "properties": { "active": { "description": "`false` disables the key, `true` enables it again.", "type": "boolean", "example": false }, "expires_at": { "description": "`null` removes the expiry date. A date must be in the future and no later than 2038-01-19 03:14:07 UTC, the latest instant this platform can store — a 422, not a silently shortened key.", "type": [ "string", "null" ], "format": "date-time", "example": "2027-01-31T23:59:59Z" }, "ip_whitelist": { "$ref": "#/components/schemas/ApiKeyIpWhitelist", "description": "Replaces the whole list — entries are not merged with the ones already there. `[]` clears it and the key works from any address again; omitting the field leaves the list untouched, and an explicit `null` is refused." }, "limit": { "$ref": "#/components/schemas/ApiKeySpendLimit", "description": "The new spend limit per window, in USD. `null` removes the limit; omitting the field leaves both the limit and what has been spent against it untouched. Changing the amount never resets the counter: raising it from 50 to 100 on a key that has already spent 50 leaves 50 of room, and lowering it below what has been spent accepts nothing more until the window resets." }, "reset_interval": { "description": "The new window. Changing it restarts the counter. Can be sent on its own, but only for a key that already has a limit; alongside `\"limit\": null` it is refused.", "type": "string", "example": "daily", "enum": [ "none", "daily", "weekly", "monthly" ] } }, "type": "object" } } } }, "responses": { "200": { "description": "The key after the change.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/ApiKeyResource" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "404": { "description": "No such key on this account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ApiKeyLimitReached" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/account/balance": { "get": { "tags": [ "Client API v2" ], "summary": "Get account balance", "description": "Retrieve the current account balance for the authenticated client. Needs an ADMIN key.", "operationId": "getAccountBalance", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "responses": { "200": { "description": "Current client balance.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ClientInfoResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "404": { "description": "Request not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/jobs/{job_request}": { "get": { "tags": [ "Client API v2" ], "summary": "Get job status and result", "description": "Retrieve the current status and result of a submitted inference job.", "operationId": "getJob", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "name": "job_request", "in": "path", "required": true, "schema": { "type": "string", "example": "c08a339c-73e5-4d67-a4d5-231302fbff9a" } } ], "responses": { "200": { "description": "Current status of requested inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestStatusResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Request not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/models": { "get": { "tags": [ "Client API v2" ], "summary": "List available models", "description": "Lists the inference models available to your account. The list is scoped to you: it contains only enabled models that are either public or explicitly granted to your account, and it omits models that require a higher plan tier than your account has (those return 422 on generation and pricing). A model explicitly granted to your account is always listed, whatever tier it requires.", "operationId": "listModels", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "$ref": "#/components/parameters/ListLimit" }, { "$ref": "#/components/parameters/ListPerPage" }, { "$ref": "#/components/parameters/ListPage" }, { "$ref": "#/components/parameters/ClientModelsSort" }, { "name": "filter[inference_types]", "in": "query", "description": "Comma-separated inference types to filter by. Values are the type slugs returned in each model's `inference_types`. Example: txt2img,vid-upscale", "required": false, "style": "form", "explode": false, "schema": { "type": "array", "items": { "type": "string", "enum": [ "txt2img", "txt2audio", "txt2music", "txt2video", "txt2embedding", "img2img", "img2txt", "img2video", "img-upscale", "img-rmbg", "audio2text", "audio2video", "audio_file2text", "video2text", "video_file2text", "vid-upscale", "vid-rmbg", "video2desc", "video_file2desc" ] } } }, { "name": "filter[tags]", "in": "query", "description": "Comma-separated tags to filter by. Tags are controlled labels set per model; read the `tags` field of any model in this response to see which are in use. Example: new,experimental", "required": false, "style": "form", "explode": false, "schema": { "type": "array", "items": { "type": "string" } } } ], "responses": { "200": { "description": "List of available models.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ClientDiffusionModelCollection" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Request not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/prompts/enhancements": { "post": { "tags": [ "Client API v2" ], "summary": "Enhance a prompt", "description": "Rewrites a prompt for a specific model using a guide configured for that model and inference type. Requires a guide for your `model_slug` + `type` pair — call the `/price` sibling first, which runs the same check for free and quotes the fee.", "operationId": "clientBoostPromptV2", "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "properties": { "prompt": { "type": "string", "example": "A beautiful landscape with mountains", "minLength": 3 }, "negative_prompt": { "type": [ "string", "null" ], "example": "blurry, low quality", "minLength": 3 }, "type": { "description": "Inference type, v2 dot notation. Only prompt-driven types are boostable.", "type": "string", "example": "images.generations", "enum": [ "images.generations", "images.edits", "videos.generations", "videos.animations", "audio.speech", "audio.music" ] }, "model_slug": { "type": "string", "example": "Flux1schnell" }, "image": { "description": "Reference image. Required for images.edits/videos.animations. Supported formats: JPEG, PNG, BMP, GIF, WebP.", "type": [ "string", "null" ], "format": "binary" } }, "type": "object" } } } }, "responses": { "200": { "description": "Enhanced prompts returned successfully", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "prompt": { "type": "string" }, "negative_prompt": { "type": [ "string", "null" ] } }, "type": "object" } } } }, "422": { "$ref": "#/components/responses/ValidationError", "description": "Validation failed, insufficient balance, no guide available, or the model is not available on your plan. In the last case the error is reported on the \"model_slug\" field (not \"model\") with the message \"This model is not available on your plan. Please upgrade to access it.\" — you cannot boost a prompt for a model you are not able to generate with. Such a model is also omitted from GET /models." }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/prompts/enhancements/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate prompt enhancement price", "description": "Price of a prompt boost, and a free check that one is possible: it runs the same guide lookup as the boost itself, so a 422 here means the boost would also be rejected. Charges nothing either way. NOTE the response shape differs from every other price endpoint: this one returns `{\"price\": …}` at the top level, not wrapped in `data`.", "operationId": "clientCalculateBoostPriceV2", "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "properties": { "prompt": { "type": "string", "example": "A beautiful landscape", "minLength": 3 }, "negative_prompt": { "type": [ "string", "null" ], "example": "blurry, low quality", "minLength": 3 }, "type": { "description": "Inference type, v2 dot notation. Only prompt-driven types are boostable.", "type": "string", "example": "images.generations", "enum": [ "images.generations", "images.edits", "videos.generations", "videos.animations", "audio.speech", "audio.music" ] }, "model_slug": { "type": "string", "example": "Flux1schnell" }, "image": { "description": "Reference image (for price estimation of image-based types).", "type": [ "string", "null" ], "format": "binary" } }, "type": "object" } } } }, "responses": { "200": { "description": "Price calculation returned successfully", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "price": { "type": "number", "format": "float", "example": 0.00012345 } }, "type": "object" } } } }, "422": { "$ref": "#/components/responses/ValidationError", "description": "Validation failed, or the model is not available on your plan. In the last case the error is reported on the \"model_slug\" field (not \"model\") with the message \"This model is not available on your plan. Please upgrade to access it.\"" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/key/usage": { "get": { "tags": [ "Client API v2" ], "summary": "Usage of the calling API key", "description": "Cost, requests and errors of the key sending the request. Works with any key role.", "operationId": "getCurrentApiKeyUsage", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "$ref": "#/components/parameters/UsageFrom" }, { "$ref": "#/components/parameters/UsageTo" }, { "name": "group_by", "in": "query", "required": false, "schema": { "type": "string", "default": "day", "enum": [ "day", "hour", "type", "model" ] } } ], "responses": { "200": { "description": "The report.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/UsageReport" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "422": { "description": "Invalid range or group_by.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/keys/{id}/usage": { "get": { "tags": [ "Client API v2" ], "summary": "Usage of an API key", "description": "Like `GET /api/v2/key/usage`, for any key of the account. Needs an ADMIN key.", "operationId": "getApiKeyUsage", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "name": "id", "in": "path", "required": true, "schema": { "type": "integer" } }, { "$ref": "#/components/parameters/UsageFrom" }, { "$ref": "#/components/parameters/UsageTo" }, { "name": "group_by", "in": "query", "required": false, "schema": { "type": "string", "default": "day", "enum": [ "day", "hour", "type", "model" ] } } ], "responses": { "200": { "description": "The report.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/UsageReport" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "404": { "description": "No such key on this account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "description": "Invalid range or group_by.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/account/usage": { "get": { "tags": [ "Client API v2" ], "summary": "Usage of the whole account", "description": "Cost, requests and errors of every key of the account, optionally per key. The same data as the Usage screen in the Dashboard. Needs an ADMIN key.", "operationId": "getAccountUsage", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" }, { "$ref": "#/components/parameters/UsageFrom" }, { "$ref": "#/components/parameters/UsageTo" }, { "name": "group_by", "in": "query", "required": false, "schema": { "type": "string", "default": "day", "enum": [ "day", "hour", "type", "model", "key" ] } } ], "responses": { "200": { "description": "The report.", "content": { "application/json": { "schema": { "properties": { "data": { "$ref": "#/components/schemas/UsageReport" } }, "type": "object" } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "403": { "$ref": "#/components/responses/InsufficientPermissions" }, "422": { "description": "Invalid range or group_by.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/audio-syncs": { "post": { "tags": [ "Client API v2" ], "summary": "Generate a video conditioned on an audio track", "description": "Generate a video conditioned on an audio track.", "operationId": "syncVideoAudio", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Audio to video generation parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Aud2VideoRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/audio-syncs/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of an audio-to-video sync request", "description": "Estimate the price of an audio-to-video sync request.", "operationId": "estimateVideoAudioSyncPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Audio to video price calculation parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Aud2VideoPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for audio2video inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.15 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/edits/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of an image edit request", "description": "Estimate the price of an image edit request.", "operationId": "estimateImageEditPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image generation parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Img2ImgPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for img2img inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.25 }, "is_estimated": { "description": "True when the price is an ESTIMATE rather than an exact quote. Partner (external-provider) models are billed by the provider after the inference, so the final charge is not knowable up front.", "type": "boolean", "example": false }, "estimate_basis": { "description": "What the estimate is derived from. `request_params` - observed costs of requests with these exact parameters; `price_matrix` - the model's price table for these parameters (resolution, duration, …); `model_history` - observed costs of recent requests to this model; `model_default` - the model's configured fallback, used while it has no history; `unavailable` - no cost data at all, so `price` is 0.0 and must not be relied on. Null when the price is exact rather than estimated, which is the case for every native (non-partner) model.", "type": [ "string", "null" ], "example": "request_params", "enum": [ "request_params", "price_matrix", "model_history", "model_default", "unavailable", null ] } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/ocr/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of an image OCR request", "description": "Estimate the price of an image OCR request.", "operationId": "estimateImageOcrPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image to text conversion parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Img2TxtPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for img2txt inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.15 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/animations/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of an image-to-video animation request", "description": "Estimate the price of an image-to-video animation request.", "operationId": "estimateVideoAnimationPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image to video price calculation parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Img2VideoPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for img2video inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.15 }, "is_estimated": { "description": "True when the price is an ESTIMATE rather than an exact quote. Partner (external-provider) models are billed by the provider after the inference, so the final charge is not knowable up front.", "type": "boolean", "example": false }, "estimate_basis": { "description": "What the estimate is derived from. `request_params` - observed costs of requests with these exact parameters; `price_matrix` - the model's price table for these parameters (resolution, duration, …); `model_history` - observed costs of recent requests to this model; `model_default` - the model's configured fallback, used while it has no history; `unavailable` - no cost data at all, so `price` is 0.0 and must not be relied on. Null when the price is exact rather than estimated, which is the case for every native (non-partner) model.", "type": [ "string", "null" ], "example": "request_params", "enum": [ "request_params", "price_matrix", "model_history", "model_default", "unavailable", null ] } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/background-removals/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of an image background removal request", "description": "Estimate the price of an image background removal request.", "operationId": "estimateImageBackgroundRemovalPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image background removal parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/ImageRemoveBgPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for image background removal inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.15 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/upscales/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of an image upscale request", "description": "Estimate the price of an image upscale request.", "operationId": "estimateImageUpscalePrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image upscaling parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/ImageUpscalePriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for image upscaling inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.15 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/generations/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a text-to-image generation request", "description": "Estimate the price of a text-to-image generation request.", "operationId": "estimateImagePrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image generation parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2ImgPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for text2img inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.25 }, "is_estimated": { "description": "True when the price is an ESTIMATE rather than an exact quote. Partner (external-provider) models are billed by the provider after the inference, so the final charge is not knowable up front.", "type": "boolean", "example": false }, "estimate_basis": { "description": "What the estimate is derived from. `request_params` - observed costs of requests with these exact parameters; `price_matrix` - the model's price table for these parameters (resolution, duration, …); `model_history` - observed costs of recent requests to this model; `model_default` - the model's configured fallback, used while it has no history; `unavailable` - no cost data at all, so `price` is 0.0 and must not be relied on. Null when the price is exact rather than estimated, which is the case for every native (non-partner) model.", "type": [ "string", "null" ], "example": "request_params", "enum": [ "request_params", "price_matrix", "model_history", "model_default", "unavailable", null ] } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/audio/speech/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a text-to-speech generation request", "description": "Estimate the price of a text-to-speech generation request. Either text or count_text must be provided.", "operationId": "estimateSpeechPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Audio generation parameters. Either text or count_text must be provided. Voice is optional (not needed for voice_clone or voice_design modes).", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2AudioPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for text2audio inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.25 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/embeddings/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of an embedding request", "description": "Estimate the price of an embedding request.", "operationId": "estimateEmbeddingPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Text to embedding conversion parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2EmbeddingPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for txt2embedding inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.0003 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/web/search": { "post": { "tags": [ "Client API v2" ], "summary": "Search the web", "description": "Search the live web and get ranked results — optionally with each page's text, the most relevant excerpts and an AI-written summary — in a single synchronous call. The response is returned directly: there is no `request_id` to poll, no webhook and no job status. The amount charged is returned in `cost`.", "operationId": "webSearch", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebSearchRequestBody" } } } }, "responses": { "200": { "description": "Search results.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebSearchResponse" }, "examples": { "quick": { "summary": "Quick search", "value": { "request_id": "ba1e1b58-a12c-4f83-9ec7-572e301fa1c2", "cost": 0.0048, "results": [ { "url": "https://huggingface.co/models?pipeline_tag=text-to-image", "title": "Text-to-Image Models – Hugging Face" }, { "url": "https://fluence.ai/blog/best-open-source-text-to-image-models/", "title": "12 Best Open Source Image Generation Models (in 2026)", "published_at": "2026-10-20T08:48:00+00:00", "author": "Fluence" } ] } }, "with_content": { "summary": "Balanced search with text, excerpts and summary", "value": { "request_id": "dc260284-883c-44be-b61b-ef82a3486a50", "cost": 0.012, "results": [ { "url": "https://bfl.ai/blog/flux-2", "title": "FLUX.2: Frontier Visual Intelligence | Black Forest Labs", "published_at": "2025-11-25T15:11:07+00:00", "image": "https://bfl.ai/api/og/blog/flux-2", "text": "FLUX.2: Frontier Visual Intelligence | Black Forest Labs\n\n# FLUX.2: Frontier Visual Intelligence\n\nNovember 25, 2025 5 min read ...", "excerpts": [ "# FLUX.2: Frontier Visual Intelligence\n\nFLUX.2 is designed for real-world creative workflows ..." ], "summary": "FLUX.2 introduces several major enhancements for real-world creative workflows: multi-reference support ..." } ] } } } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/web/search/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a web search", "description": "Estimate what a web search would cost. Accepts the same body as `POST /api/v2/web/search` and validates it the same way. Nothing is charged.", "operationId": "estimateWebSearchPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebSearchRequestBody" } } } }, "responses": { "200": { "description": "Calculated price.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebPriceResponse" }, "examples": { "quick": { "summary": "Quick search, up to 10 results", "value": { "price": 0.0048 } } } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/web/contents": { "post": { "tags": [ "Client API v2" ], "summary": "Read web pages", "description": "Fetch up to 20 URLs and get clean page text, the most relevant excerpts and/or an AI-written summary of each — in a single synchronous call. Request at least one of `text`, `excerpts` or `summary`. Each page reports its own `status`; pages that could not be read are not charged. The response is returned directly — there is no job to poll.", "operationId": "webContents", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebContentsRequestBody" } } } }, "responses": { "200": { "description": "Page contents, one entry per requested URL.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebContentsResponse" }, "examples": { "mixed": { "summary": "One page read, one not found, one unreachable", "value": { "request_id": "72e1b519-fefb-4fc0-8f43-126d73f776cb", "cost": 0.0012, "results": [ { "url": "https://example.com", "status": "ok", "title": "Example Domain", "text": "Example Domain\n\nThis domain is for use in documentation examples ..." }, { "url": "https://deapi.ai/nonexistent-page", "status": "not_found" }, { "url": "https://unreachable.example/page", "status": "unknown" } ] } } } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/web/contents/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of reading web pages", "description": "Estimate what a web contents request would cost, assuming every URL can be read. Accepts the same body as `POST /api/v2/web/contents` and validates it the same way. Nothing is charged.", "operationId": "estimateWebContentsPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebContentsRequestBody" } } } }, "responses": { "200": { "description": "Calculated price.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/WebPriceResponse" }, "examples": { "text": { "summary": "One URL, text only", "value": { "price": 0.0012 } } } } } }, "401": { "description": "Missing, unknown, expired or deactivated key — `code` says which: `missing_key`, `invalid_key`, `key_expired` or `key_revoked`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/generations/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a text-to-video generation request", "description": "Estimate the price of a text-to-video generation request.", "operationId": "estimateVideoPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Text to video conversion parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2VideoPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for txt2video inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.15 }, "is_estimated": { "description": "True when the price is an ESTIMATE rather than an exact quote. Partner (external-provider) models are billed by the provider after the inference, so the final charge is not knowable up front.", "type": "boolean", "example": false }, "estimate_basis": { "description": "What the estimate is derived from. `request_params` - observed costs of requests with these exact parameters; `price_matrix` - the model's price table for these parameters (resolution, duration, …); `model_history` - observed costs of recent requests to this model; `model_default` - the model's configured fallback, used while it has no history; `unavailable` - no cost data at all, so `price` is 0.0 and must not be relied on. Null when the price is exact rather than estimated, which is the case for every native (non-partner) model.", "type": [ "string", "null" ], "example": "request_params", "enum": [ "request_params", "price_matrix", "model_history", "model_default", "unavailable", null ] } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/audio/transcriptions/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a transcription request", "description": "Estimate the price of a transcription request. Provide one of: source_url, source_file, or duration_seconds.", "operationId": "estimateTranscriptionPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Transcription price calculation parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/TranscribePriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for transcription.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "Calculated price for the transcription", "type": "number", "format": "float", "example": 0.25 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/audio/music/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a text-to-music generation request", "description": "Estimate the price of a text-to-music generation request. Requires duration and inference_steps parameters.", "operationId": "estimateMusicPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Music generation parameters for price calculation.", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2MusicPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for text2music inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.25 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Model not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/descriptions/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a video description", "description": "Quote a video description before submitting it. Priced on the machine time the description takes — which grows with the length of the video and with the `preset` — at the model's hourly rate, except on TikTok, where the price is a fixed card by length (up to 1, 2, 3, 5 or 10 minutes; 10 minutes is the maximum) scaled ×0.75 / ×1 / ×1.5 by the `preset`. `include_metadata` adds the same flat surcharge as on transcription, on URL sources only. Provide the source as a URL, an upload, or a known `duration_seconds`.", "operationId": "estimateVideoDescriptionPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Provide exactly one of video_url, video_file or duration_seconds.", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/VideoDescriptionPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for the video description.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "Calculated price", "type": "number", "format": "float", "example": 0.25 }, "duration_seconds": { "description": "Length of the video the price was calculated for, in seconds: read from the video_url or the video_file, or the duration_seconds sent.", "type": "number", "format": "float", "example": 100 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/background-removals/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a video background removal request", "description": "Estimate the price of a video background removal request.", "operationId": "estimateVideoBackgroundRemovalPrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Video background removal parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/VideoRemoveBgPriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for video background removal inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.25 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/upscales/price": { "post": { "tags": [ "Client API v2" ], "summary": "Estimate the price of a video upscale request", "description": "Estimate the price of a video upscale request.", "operationId": "estimateVideoUpscalePrice", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Video upscaling parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/VideoUpscalePriceRequestBody" } } } }, "responses": { "200": { "description": "Calculated price for video upscaling inference.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "properties": { "data": { "properties": { "price": { "description": "What this request would cost, in the same credit unit as the account balance. A quote only — nothing is charged by this endpoint.", "type": "number", "format": "float", "example": 0.25 } }, "type": "object" } }, "type": "object" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/edits": { "post": { "tags": [ "Client API v2" ], "summary": "Edit an image guided by a text prompt", "description": "Edit an image guided by a text prompt. Accepts either a single image via \"image\" or multiple images via \"images[]\" (mutually exclusive).", "operationId": "editImage", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image generation parameters. Either \"image\" or \"images[]\" must be provided (not both).", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Img2ImgRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/ocr": { "post": { "tags": [ "Client API v2" ], "summary": "Extract text from an image via OCR", "description": "Extract text from an image via OCR.", "operationId": "extractImageText", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image to text conversion parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Img2TxtRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/animations": { "post": { "tags": [ "Client API v2" ], "summary": "Animate a still image into a video", "description": "Animate a still image into a video.", "operationId": "animateImage", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image to video generation parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Img2VideoRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/background-removals": { "post": { "tags": [ "Client API v2" ], "summary": "Remove the background from an image", "description": "Remove the background from an image.", "operationId": "removeImageBackground", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image background removal parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/ImageRemoveBgRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/upscales": { "post": { "tags": [ "Client API v2" ], "summary": "Upscale an image to a higher resolution", "description": "Upscale an image to a higher resolution.", "operationId": "upscaleImage", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image upscaling parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/ImageUpscaleRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/audio/speech": { "post": { "tags": [ "Client API v2" ], "summary": "Generate speech audio from text", "description": "Generate speech audio from text. Supports three TTS modes: custom_voice (default, preset speakers), voice_clone (clone from reference audio), voice_design (create voice from description).", "operationId": "generateSpeech", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Audio generation parameters. Supports three TTS modes: custom_voice (default, preset speakers), voice_clone (clone from reference audio), voice_design (create voice from description).", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Txt2AudioRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/embeddings": { "post": { "tags": [ "Client API v2" ], "summary": "Generate embeddings for one or more input texts", "description": "Generate embeddings for one or more input texts.", "operationId": "createEmbedding", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Text to embedding conversion parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2EmbeddingRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/images/generations": { "post": { "tags": [ "Client API v2" ], "summary": "Generate an image from a text prompt", "description": "Generate an image from a text prompt.", "operationId": "generateImage", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Image generation parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2ImgRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/audio/music": { "post": { "tags": [ "Client API v2" ], "summary": "Generate music from a text prompt", "description": "Generate music from a text prompt.", "operationId": "generateMusic", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Music generation parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Txt2MusicRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Model not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/generations": { "post": { "tags": [ "Client API v2" ], "summary": "Generate a video from a text prompt", "description": "Generate a video from a text prompt.", "operationId": "generateVideo", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Text to video conversion parameters", "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Txt2VideoRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/audio/transcriptions": { "post": { "tags": [ "Client API v2" ], "summary": "Transcribe audio or video to text", "description": "Transcribe audio or video to text. Accepts either a source URL (YouTube, Twitter, Twitch, Kick, TikTok, Twitter Spaces) or a file upload (audio/video). The job type is auto-detected from the input.", "operationId": "createTranscription", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Transcription parameters. Provide exactly one of source_url or source_file.", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/TranscribeRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/descriptions": { "post": { "tags": [ "Client API v2" ], "summary": "Describe what happens in a video", "description": "Produce a timestamped index of what happens on screen — a list of events, each with `start`, `end` (seconds) and a `description` — plus scene boundaries and source metadata. Reads the picture, not the audio track; for speech use POST /api/v2/audio/transcriptions. Accepts either a video URL (YouTube, Twitter/X, Twitch, Kick, TikTok) or a file upload. The result is a JSON document: `{\"events\": [{\"start\", \"end\", \"description\", \"merged?\", \"edge_distance\"}], \"scenes\": [...], \"meta\": {\"duration\", \"preset\", ...}}`, delivered as `result_url` on the job (and as a serialized JSON string in `result` when `return_result_in_response` is set). Priced on machine time at the model's hourly rate — longer videos and higher presets cost more — or, for TikTok, on a fixed card by length capped at 10 minutes; see POST /api/v2/videos/descriptions/price.", "operationId": "createVideoDescription", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Video description parameters. Provide exactly one of video_url or video_file.", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/VideoDescriptionRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/background-removals": { "post": { "tags": [ "Client API v2" ], "summary": "Remove the background from a video", "description": "Remove the background from a video.", "operationId": "removeVideoBackground", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Video background removal parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/VideoRemoveBgRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } }, "/api/v2/videos/upscales": { "post": { "tags": [ "Client API v2" ], "summary": "Upscale a video to a higher resolution", "description": "Upscale a video to a higher resolution.", "operationId": "upscaleVideo", "parameters": [ { "$ref": "#/components/parameters/AcceptHeader" } ], "requestBody": { "description": "Video upscaling parameters", "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/VideoUpscaleRequestBody" } } } }, "responses": { "200": { "description": "ID of the inference request.", "headers": { "X-RateLimit-Policy": { "$ref": "#/components/headers/X-RateLimit-Policy" }, "X-RateLimit-Source": { "$ref": "#/components/headers/X-RateLimit-Source" }, "X-RateLimit-Limit": { "$ref": "#/components/headers/X-RateLimit-Limit" }, "X-RateLimit-Remaining": { "$ref": "#/components/headers/X-RateLimit-Remaining" }, "X-RateLimit-Reset": { "$ref": "#/components/headers/X-RateLimit-Reset" }, "X-RateLimit-Daily-Limit": { "$ref": "#/components/headers/X-RateLimit-Daily-Limit" }, "X-RateLimit-Daily-Remaining": { "$ref": "#/components/headers/X-RateLimit-Daily-Remaining" }, "X-RateLimit-Daily-Reset": { "$ref": "#/components/headers/X-RateLimit-Daily-Reset" } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/JobRequestResponseResource" } } } }, "401": { "description": "Unauthorized user.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "404": { "description": "Not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/response_error_default" } } } }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimitExceeded" }, "403": { "$ref": "#/components/responses/AccountSuspended" }, "402": { "$ref": "#/components/responses/KeyLimitExceeded" } }, "security": [ { "bearerAuth": [] } ] } } }, "components": { "schemas": { "UsageReport": { "required": [ "from", "to", "group_by", "currency", "totals", "groups" ], "properties": { "from": { "description": "Start of the range, UTC, inclusive.", "type": "string", "format": "date-time", "example": "2026-09-15T00:00:00+00:00" }, "to": { "description": "End of the range, UTC, exclusive.", "type": "string", "format": "date-time", "example": "2026-09-22T00:00:00+00:00" }, "group_by": { "type": "string", "example": "day", "enum": [ "day", "hour", "type", "model", "key" ] }, "currency": { "type": "string", "example": "USD" }, "totals": { "$ref": "#/components/schemas/UsageFigures" }, "groups": { "description": "Only groups with usage. `key` is: day — `YYYY-MM-DD`; hour — the hour's start (UTC); type — a v2 inference type such as `images.generations`; model — the model slug; key — the API key id, `panel` for what the Dashboard itself ran on the account, `deleted` for keys that no longer exist, null when the request has no recorded origin.", "type": "array", "items": { "allOf": [ { "properties": { "key": { "example": "2026-09-21", "oneOf": [ { "type": "string" }, { "type": "integer" }, { "type": "null" } ] }, "name": { "description": "Only with group_by=key: the key's name, or `Panel` / `Deleted keys` for those two groups.", "type": [ "string", "null" ] } }, "type": "object" }, { "$ref": "#/components/schemas/UsageFigures" } ] } } }, "type": "object" }, "UsageFigures": { "required": [ "cost", "requests", "errors" ], "properties": { "cost": { "description": "Charged, net of refunds.", "type": "number", "format": "float", "example": 12.345678 }, "requests": { "description": "Inference requests accepted in the window.", "type": "integer", "example": 830 }, "errors": { "description": "Of those, requests that ended in an error. Requests refused before a job was created (401, 403, 429) are not counted.", "type": "integer", "example": 4 } }, "type": "object" }, "response_error_default": { "properties": { "data": { "description": "Information from success endpoint", "type": "object" }, "message": { "description": "Error general message", "type": "string" }, "errors": { "description": "Information about errors", "type": "array", "items": {} }, "statusCode": { "description": "Status code", "type": "integer" }, "code": { "description": "A stable, machine-readable reason, on the responses that publish one. Refused credentials (401): `missing_key` — no Bearer credentials arrived at all; `invalid_key` — a key was presented but is unknown, carries the wrong secret, or is malformed; `key_expired` — past its expiry date; `key_revoked` — deactivated. Refused requests: `insufficient_permissions` (403), `ip_not_allowed` (403), `active_key_limit_reached` (422), `insufficient_balance` (422), `key_limit_exceeded` (402), `rate_limited` (429). Absent wherever a response publishes no code, so treat an unknown value as the status code alone — the list grows.", "type": "string", "enum": [ "missing_key", "invalid_key", "key_expired", "key_revoked", "insufficient_permissions", "ip_not_allowed", "active_key_limit_reached", "insufficient_balance", "key_limit_exceeded", "rate_limited" ] } }, "type": "object" }, "ApiKeyIpWhitelist": { "description": "The addresses an API key may be used from. An empty list means any address, which is what a key carries until a list is set. Entries are single IPv4/IPv6 addresses or CIDR ranges of either family, and a key with a non-empty list is refused from anywhere else — including a call whose address cannot be established. Sending the field replaces the whole list; `[]` clears it. A JSON object is refused, as is an entry that could never gate anything: a `/0` range (say \"any address\" with an empty list instead) and an IPv4 address written in IPv6 notation such as `::ffff:192.0.2.1` (write `192.0.2.1`, the form a caller is matched against).", "type": "array", "items": { "type": "string", "example": "203.0.113.7" }, "example": [ "203.0.113.7", "198.51.100.0/24" ], "maxItems": 20 }, "response_error_rate_limit": { "description": "Rate limit exceeded response", "properties": { "message": { "description": "Error message", "type": "string", "example": "Too Many Attempts." } }, "type": "object" }, "WebhookProcessingPayload": { "title": "Webhook Payload - Job Processing", "description": "Payload sent when a job transitions from pending to processing state. Indicates a worker has started processing the job.", "required": [ "event", "delivery_id", "timestamp", "data" ], "properties": { "event": { "description": "The event type", "type": "string", "example": "job.processing" }, "delivery_id": { "description": "Unique identifier for this delivery", "type": "string", "format": "uuid", "example": "550e8400-e29b-41d4-a716-446655440000" }, "timestamp": { "description": "ISO 8601 timestamp when the event occurred", "type": "string", "format": "date-time", "example": "2024-01-15T10:30:00.000Z" }, "data": { "description": "Event-specific data", "required": [ "job_request_id", "status", "previous_status", "job_type", "started_at" ], "properties": { "job_request_id": { "description": "The UUID of the job request", "type": "string", "format": "uuid", "example": "123e4567-e89b-12d3-a456-426614174000" }, "status": { "description": "Current job status", "type": "string", "example": "processing" }, "previous_status": { "description": "Previous job status", "type": "string", "example": "pending" }, "job_type": { "description": "Type of inference job", "type": "string", "example": "txt2img", "enum": [ "txt2img", "img2txt", "txt2audio", "vid2txt", "aud2txt", "txt2video", "img2video", "img2img", "img_upscale", "img_rmbg", "vid_upscale", "vid_rmbg", "txt2embedding", "videofile2txt", "audiofile2txt" ] }, "started_at": { "description": "ISO 8601 timestamp when processing started", "type": "string", "format": "date-time", "example": "2024-01-15T10:30:00.000Z" } }, "type": "object" } }, "type": "object" }, "WebhookCompletedPayload": { "title": "Webhook Payload - Job Completed", "description": "Payload sent when a job completes successfully. Includes the result URL for downloading the output and what the request cost.", "required": [ "event", "delivery_id", "timestamp", "data" ], "properties": { "event": { "description": "The event type", "type": "string", "example": "job.completed" }, "delivery_id": { "description": "Unique identifier for this delivery", "type": "string", "format": "uuid", "example": "550e8400-e29b-41d4-a716-446655440001" }, "timestamp": { "description": "ISO 8601 timestamp when the event occurred", "type": "string", "format": "date-time", "example": "2024-01-15T10:30:45.000Z" }, "data": { "description": "Event-specific data", "required": [ "job_request_id", "status", "previous_status", "job_type", "completed_at", "result_url", "processing_time_ms" ], "properties": { "job_request_id": { "description": "The UUID of the job request", "type": "string", "format": "uuid", "example": "123e4567-e89b-12d3-a456-426614174000" }, "status": { "description": "Current job status", "type": "string", "example": "done" }, "previous_status": { "description": "Previous job status", "type": "string", "example": "processing" }, "job_type": { "description": "Type of inference job", "type": "string", "example": "txt2img", "enum": [ "txt2img", "img2txt", "txt2audio", "vid2txt", "aud2txt", "txt2video", "img2video", "img2img", "img_upscale", "img_rmbg", "vid_upscale", "vid_rmbg", "txt2embedding", "videofile2txt", "audiofile2txt" ] }, "completed_at": { "description": "ISO 8601 timestamp when the job completed", "type": "string", "format": "date-time", "example": "2024-01-15T10:30:45.000Z" }, "result_url": { "description": "URL to download the job result", "type": "string", "format": "uri", "example": "https://storage.deapi.ai/results/123e4567-e89b-12d3-a456-426614174000/output.png" }, "processing_time_ms": { "description": "Total processing time in milliseconds", "type": "integer", "example": 45000 }, "price": { "description": "What this request cost you, in credits — the same figure GET /jobs/{uuid} reports. For models served by an external provider the charge settles after inference, so this may be the estimate quoted at submission, flagged is_estimated; the settled charge can differ from it. Own-fleet models are charged up front and always report the exact figure.", "properties": { "amount": { "description": "Credits charged for this request", "type": "number", "format": "float", "example": 0.0234 }, "is_estimated": { "description": "True when the figure is the submission-time estimate rather than a settled charge. Do not use an estimated value for reconciliation or invoicing.", "type": "boolean", "example": false } }, "type": [ "object", "null" ] } }, "type": "object" } }, "type": "object" }, "WebhookFailedPayload": { "title": "Webhook Payload - Job Failed", "description": "Payload sent when a job fails during processing. Includes error details for debugging.", "required": [ "event", "delivery_id", "timestamp", "data" ], "properties": { "event": { "description": "The event type", "type": "string", "example": "job.failed" }, "delivery_id": { "description": "Unique identifier for this delivery", "type": "string", "format": "uuid", "example": "550e8400-e29b-41d4-a716-446655440002" }, "timestamp": { "description": "ISO 8601 timestamp when the event occurred", "type": "string", "format": "date-time", "example": "2024-01-15T10:30:45.000Z" }, "data": { "description": "Event-specific data", "required": [ "job_request_id", "status", "previous_status", "job_type", "failed_at", "error_code" ], "properties": { "job_request_id": { "description": "The UUID of the job request", "type": "string", "format": "uuid", "example": "123e4567-e89b-12d3-a456-426614174000" }, "status": { "description": "Current job status", "type": "string", "example": "error" }, "previous_status": { "description": "Previous job status", "type": "string", "example": "processing" }, "job_type": { "description": "Type of inference job", "type": "string", "example": "txt2img", "enum": [ "txt2img", "img2txt", "txt2audio", "vid2txt", "aud2txt", "txt2video", "img2video", "img2img", "img_upscale", "img_rmbg", "vid_upscale", "vid_rmbg", "txt2embedding", "videofile2txt", "audiofile2txt", null ] }, "failed_at": { "description": "ISO 8601 timestamp when the job failed", "type": "string", "format": "date-time", "example": "2024-01-15T10:30:45.000Z" }, "error_code": { "description": "Machine-readable error code", "type": "string", "example": "WORKER_TIMEOUT", "enum": [ "WORKER_TIMEOUT", "WORKER_ERROR", "PROCESSING_ERROR" ] }, "error_reason": { "description": "Bounded, actionable failure reason: SOURCE_PRIVATE, SOURCE_RESTRICTED, SOURCE_UNPROCESSABLE, SOURCE_DOWNLOAD_FAILED, INPUT_TOO_LARGE, TIMEOUT, CAPACITY_UNAVAILABLE or PROCESSING_FAILED. THIS LIST IS OPEN — new values may be added without a major version, so treat any unrecognised value as PROCESSING_FAILED. Prefer branching on `retryable`.", "type": "string", "example": "SOURCE_DOWNLOAD_FAILED" }, "retryable": { "description": "Whether resubmitting the identical request could plausibly succeed. Branch on this rather than on error_reason — it stays correct as new reasons are added.", "type": "boolean", "example": true }, "refunded": { "description": "Whether the upfront charge for this job was returned. False covers both a charge deliberately kept and a job that failed before it was ever charged.", "type": "boolean", "example": true }, "price": { "description": "What this request cost you, in credits — the same figure GET /jobs/{uuid} reports. A refunded or never-charged request reports 0. For models served by an external provider the charge settles after inference, so on job.completed this may be the estimate quoted at submission, flagged is_estimated; the settled charge can differ from it. Own-fleet models are charged up front and always report the exact figure.", "properties": { "amount": { "description": "Credits charged for this request", "type": "number", "format": "float", "example": 0.0234 }, "is_estimated": { "description": "True when the figure is the submission-time estimate rather than a settled charge. Do not use an estimated value for reconciliation or invoicing.", "type": "boolean", "example": false } }, "type": [ "object", "null" ] } }, "type": "object" } }, "type": "object" }, "Aud2VideoRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "required": [ "prompt", "audio", "model", "width", "height", "seed", "frames", "fps" ], "properties": { "prompt": { "description": "The main prompt for video generation", "type": "string", "example": "A beautiful sunset over mountains with dramatic music" }, "negative_prompt": { "description": "Elements to avoid in the generated video. Dropped (not forwarded to the worker) when the model declares `info.features.supports_negative_prompt: false`.", "type": [ "string", "null" ], "example": "blur, darkness, noise" }, "audio": { "description": "Audio file to condition the video generation. Supported formats: MP3, WAV, OGG, FLAC. Maximum file size: 20 MB.", "type": "string", "format": "binary" }, "first_frame_image": { "description": "Image for the first frame of video (optional). Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.", "type": [ "string", "null" ], "format": "binary" }, "last_frame_image": { "description": "Image for the last frame of video (optional). Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.", "type": [ "string", "null" ], "format": "binary" }, "width": { "description": "Width of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "height": { "description": "Height of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "guidance": { "description": "Guidance scale. Bounded by `info.limits.min_guidance` / `max_guidance` from `GET /api/v2/models` (0–30 when the model declares none). Required when the model declares `info.features.supports_guidance: true`; optional when the flag is absent. When the model declares `supports_guidance: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "number", "example": 7.5 }, "steps": { "description": "Number of inference steps. Bounded by `info.limits.min_steps` / `max_steps` from `GET /api/v2/models` (1–100 when the model declares none). Required when the model declares `info.features.supports_steps: true`; optional when the flag is absent. When the model declares `supports_steps: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "integer", "example": 20 }, "frames": { "description": "Number of video frames to generate. The accepted range is model-specific — read `info.limits.min_frames`/`max_frames` for your `model` from `GET /api/v2/models`; a value outside it is rejected with 422.", "type": "integer", "example": 97 }, "fps": { "description": "FPS of the generated video. The model dictates the value: read `info.defaults.fps` for your `model` from `GET /api/v2/models`. Where `min_fps` equals `max_fps` that is the only accepted value; anything outside the range is rejected with 422.", "type": "integer", "example": 24 }, "seed": { "description": "Random seed for generation", "type": "integer", "example": 42 }, "model": { "description": "The model to use for video generation. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Ltx2_3_22B_Dist_INT8" }, "webhook_url": { "description": "Optional HTTPS URL to receive webhook notifications for job status changes (processing, completed, failed). Must be HTTPS. Max 2048 characters. A per-request URL is self-contained: it is delivered even when the account has no webhook configuration, or the account webhook is disabled. See the `webhooks` block at the top level of this document for the event payloads and the headers each delivery carries.", "type": [ "string", "null" ], "format": "uri", "example": "https://your-server.com/webhooks/deapi", "maxLength": 2048 }, "webhook_secret": { "description": "Optional per-request HMAC secret (min. 32 chars) used to sign the webhook callback. Overrides the account-default secret for this job only. If omitted, the account-default secret signs the callback; if no secret exists at all, the callback is still delivered but UNSIGNED (empty X-DeAPI-Signature header). Requires `webhook_url` to also be set.", "type": [ "string", "null" ], "example": "a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5", "maxLength": 255, "minLength": 32 } }, "type": "object" }, "Aud2VideoPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "required": [ "model", "width", "height", "frames", "fps" ], "properties": { "width": { "description": "Width of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "height": { "description": "Height of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "steps": { "description": "Number of inference steps. Bounded by `info.limits.min_steps` / `max_steps` from `GET /api/v2/models` (1–100 when the model declares none). Required when the model declares `info.features.supports_steps: true`; optional when the flag is absent. When the model declares `supports_steps: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "integer", "example": 20 }, "frames": { "description": "Number of video frames to generate. The accepted range is model-specific — read `info.limits.min_frames`/`max_frames` for your `model` from `GET /api/v2/models`; a value outside it is rejected with 422.", "type": "integer", "example": 97 }, "fps": { "description": "FPS of the generated video. The model dictates the value: read `info.defaults.fps` for your `model` from `GET /api/v2/models`. Where `min_fps` equals `max_fps` that is the only accepted value; anything outside the range is rejected with 422.", "type": "integer", "example": 24 }, "model": { "description": "The model to use for video generation. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Ltx2_3_22B_Dist_INT8" } }, "type": "object" }, "Img2ImgPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "required": [ "prompt", "model", "seed" ], "properties": { "prompt": { "description": "The main prompt for image generation", "type": "string", "example": "A beautiful sunset over mountains" }, "negative_prompt": { "description": "Elements to avoid in the generated image. Dropped (not forwarded to the worker) when the model declares `info.features.supports_negative_prompt: false`.", "type": [ "string", "null" ], "example": "blur, darkness, noise" }, "model": { "description": "The model to use for generation", "type": "string", "example": "QwenImageEdit_Plus_NF4" }, "loras": { "description": "Array of LoRA models to apply. Only models that publish a `loras` array in `GET /api/v2/models` have any to apply — the `model` example shown here publishes none, so leave the field out unless you switched to a model that does. Example is deliberately empty: a LoRA name is only valid for the one model that lists it.", "type": "array", "items": { "required": [ "name", "weight" ], "properties": { "name": { "description": "LoRA identifier, copied verbatim from `loras[].name` for your `model` in `GET /api/v2/models`. That is the value the API validates against — not the human-readable `loras[].display_name`.", "type": "string" }, "weight": { "description": "Weight of the LoRA model (must be non-negative)", "type": "number", "minimum": 0 } }, "type": "object" }, "example": [] }, "guidance": { "description": "Guidance scale. Bounded by `info.limits.min_guidance` / `max_guidance` from `GET /api/v2/models` (0–30 when the model declares none). Required when the model declares `info.features.supports_guidance: true`; optional when the flag is absent. When the model declares `supports_guidance: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "number", "example": 7.5 }, "steps": { "description": "Number of inference steps. Bounded by `info.limits.min_steps` / `max_steps` from `GET /api/v2/models` (1–100 when the model declares none). Required when the model declares `info.features.supports_steps: true`; optional when the flag is absent. When the model declares `supports_steps: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "integer", "example": 20 }, "quality": { "description": "Quality tier, for models that support one (e.g. gpt-image: low/medium/high/auto). Only the values listed in that model's available options are accepted; ignored for models without a quality tier. Accepted values are model-specific — read `info.limits.quality_options` for your `model` from `GET /api/v2/models`. A model with an empty or absent list does not support a quality tier and ignores the field.", "type": [ "string", "null" ], "example": "medium" }, "width": { "description": "Requested output width. Does not move the price; accepted so the quote applies the same per-model size box as the generation request (only on a model declaring `info.features.supports_custom_output_size`; ignored otherwise).", "type": [ "integer", "null" ], "example": 1024 }, "height": { "description": "Requested output height. Does not move the price; accepted so the quote applies the same per-model size box as the generation request (only on a model declaring `info.features.supports_custom_output_size`; ignored otherwise).", "type": [ "integer", "null" ], "example": 1024 }, "seed": { "description": "Random seed for generation", "type": "integer", "example": 42 } }, "type": "object" }, "Img2TxtPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "oneOf": [ { "required": [ "image", "model" ], "properties": { "image": { "description": "Image file to extract text from. Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.", "type": "string", "format": "binary" }, "model": { "description": "The OCR model to use for text extraction. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Nanonets_Ocr_S_F16" }, "language": { "description": "Language code for OCR processing (optional)", "type": [ "string", "null" ], "example": "en" }, "format": { "description": "Output format for extracted text", "type": [ "string", "null" ], "example": "text", "enum": [ "text", "json", null ] } }, "type": "object" }, { "required": [ "width", "height", "model" ], "properties": { "width": { "description": "Width of image in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1920 }, "height": { "description": "Height of image in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1080 }, "model": { "description": "The OCR model to use for text extraction. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Nanonets_Ocr_S_F16" }, "language": { "description": "Language code for OCR processing (optional)", "type": [ "string", "null" ], "example": "en" }, "format": { "description": "Output format for extracted text", "type": [ "string", "null" ], "example": "text", "enum": [ "text", "json", null ] } }, "type": "object" } ] }, "Img2VideoPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "required": [ "model", "width", "height", "frames", "fps" ], "properties": { "width": { "description": "Width of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "height": { "description": "Height of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "steps": { "description": "Number of inference steps. Bounded by `info.limits.min_steps` / `max_steps` from `GET /api/v2/models` (1–100 when the model declares none). Required when the model declares `info.features.supports_steps: true`; optional when the flag is absent. When the model declares `supports_steps: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "integer", "example": 1 }, "frames": { "description": "Number of video frames to generate. The accepted range is model-specific — read `info.limits.min_frames`/`max_frames` for your `model` from `GET /api/v2/models`; a value outside it is rejected with 422.", "type": "integer", "example": 120 }, "fps": { "description": "FPS of the generated video. The model dictates the value: read `info.defaults.fps` for your `model` from `GET /api/v2/models`. Where `min_fps` equals `max_fps` that is the only accepted value; anything outside the range is rejected with 422.", "type": "integer", "example": 30 }, "model": { "description": "The model to use for video generation. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Ltxv_13B_0_9_8_Distilled_FP8" }, "ref_images_count": { "description": "How many `ref_images` the generation request will carry. **More than 2 reference images multiplies the price by 2** (self-hosted models; a partner-served model is priced by its provider's own rate, without this surcharge). The source image of an img2video request is not a reference image and does not count, so exactly 2 is still unmultiplied. Send the count here rather than the files — a quote never requires an upload.", "type": "integer", "example": 4, "default": 0, "minimum": 0 }, "ref_videos_count": { "description": "How many `ref_videos` the generation request will carry. **Any reference video multiplies the price by 3** (self-hosted models only). The two surcharges do not compound: the highest applicable multiplier wins, so 4 reference images plus a reference video is x3, not x6. Reference audio carries no surcharge.", "type": "integer", "example": 1, "default": 0, "minimum": 0 }, "ref_videos_duration": { "description": "Total length in seconds of the `ref_videos` the generation request will carry. Some partner models bill reference video seconds as well as output seconds, at a different rate. Leave it out and such a model quotes its minimum billed input length, so a longer reference costs more than the quote. The job itself is priced from the real files.", "type": "number", "format": "float", "example": 4.5, "default": 0, "minimum": 0 }, "ref_audios_count": { "description": "How many `ref_audios` the generation request will carry. No surcharge; accepted so the quote applies the same per-model reference limits (`info.limits.max_ref_*`, `info.features.supports_*_refs`) as the generation request. The example set here belongs to the `model` example shown.", "type": "integer", "example": 0, "default": 0, "minimum": 0 } }, "type": "object" }, "ImageRemoveBgPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "oneOf": [ { "required": [ "image", "model" ], "properties": { "image": { "description": "Image file to remove background from. Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.", "type": "string", "format": "binary" }, "model": { "description": "The background removal model to use", "type": "string", "example": "Ben2" } }, "type": "object" }, { "required": [ "width", "height", "model" ], "properties": { "width": { "description": "Width of image in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1920 }, "height": { "description": "Height of image in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1080 }, "model": { "description": "The background removal model to use", "type": "string", "example": "Ben2" } }, "type": "object" } ] }, "ImageUpscalePriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "oneOf": [ { "required": [ "image", "model" ], "properties": { "image": { "description": "Image file to upscale. Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.", "type": "string", "format": "binary" }, "model": { "description": "The upscaling model to use", "type": "string", "example": "RealESRGAN_x4" } }, "type": "object" }, { "required": [ "width", "height", "model" ], "properties": { "width": { "description": "Width of image in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1920 }, "height": { "description": "Height of image in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1080 }, "model": { "description": "The upscaling model to use", "type": "string", "example": "RealESRGAN_x4" } }, "type": "object" } ] }, "Txt2ImgPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "required": [ "prompt", "model", "width", "height", "seed" ], "properties": { "prompt": { "description": "The main prompt for image generation", "type": "string", "example": "A beautiful sunset over mountains" }, "negative_prompt": { "description": "Elements to avoid in the generated image. Dropped (not forwarded to the worker) when the model declares `info.features.supports_negative_prompt: false`.", "type": [ "string", "null" ], "example": "blur, darkness, noise" }, "model": { "description": "The model to use for image generation. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Flux1schnell" }, "loras": { "description": "Array of LoRA models to apply. Accepted only by models that publish a `loras` array in `GET /api/v2/models` — a LoRA not listed for the selected `model` is rejected with a 422. The example below belongs to the `model` example shown and is not portable to another model.", "type": "array", "items": { "required": [ "name", "weight" ], "properties": { "name": { "description": "LoRA identifier, copied verbatim from `loras[].name` for your `model` in `GET /api/v2/models`. That is the value the API validates against — not the human-readable `loras[].display_name`.", "type": "string", "example": "PepeFluxSchnellLora" }, "weight": { "description": "Weight of the LoRA model (must be non-negative)", "type": "number", "example": 0.75, "minimum": 0 } }, "type": "object" } }, "width": { "description": "Width of the generated image in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "height": { "description": "Height of the generated image in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "guidance": { "description": "Guidance scale. Bounded by `info.limits.min_guidance` / `max_guidance` from `GET /api/v2/models` (0–30 when the model declares none). Required when the model declares `info.features.supports_guidance: true`; optional when the flag is absent. When the model declares `supports_guidance: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "number", "example": 7.5 }, "steps": { "description": "Number of inference steps. Bounded by `info.limits.min_steps` / `max_steps` from `GET /api/v2/models` (1–100 when the model declares none). Required when the model declares `info.features.supports_steps: true`; optional when the flag is absent. When the model declares `supports_steps: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "integer", "example": 4 }, "quality": { "description": "Quality tier, for models that support one (e.g. gpt-image: low/medium/high/auto). Only the values listed in that model's available options are accepted; ignored for models without a quality tier. Accepted values are model-specific — read `info.limits.quality_options` for your `model` from `GET /api/v2/models`. A model with an empty or absent list does not support a quality tier and ignores the field.", "type": [ "string", "null" ], "example": "medium" }, "seed": { "description": "Random seed for generation", "type": "integer", "example": 42 } }, "type": "object" }, "Txt2AudioPriceRequestBody": { "required": [ "model", "lang", "speed", "format", "sample_rate" ], "properties": { "text": { "description": "Text to be converted to speech. Either this or count_text must be provided.", "type": [ "string", "null" ], "example": "A beautiful sunset over mountains" }, "count_text": { "description": "Number of characters for price calculation. Either this or text must be provided.", "type": [ "integer", "null" ], "example": 1000 }, "model": { "description": "The model to use for speech generation. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Kokoro" }, "mode": { "description": "TTS mode: custom_voice (default), voice_clone, or voice_design.", "type": [ "string", "null" ], "example": "custom_voice", "enum": [ "custom_voice", "voice_clone", "voice_design", null ] }, "voice": { "description": "Name of the voice to be used. Only relevant for custom_voice mode.", "type": [ "string", "null" ], "example": "af_sky" }, "lang": { "description": "Language to be used during audio generation", "type": "string", "example": "en-us" }, "speed": { "description": "Generated audio speech speed", "type": "number", "example": 1 }, "format": { "description": "Audio output format. Read `info.limits.output_formats` for your `model` from `GET /api/v2/models` and send one of the listed values; anything else is rejected with 422.", "type": "string", "example": "mp3" }, "sample_rate": { "description": "Sample rate of generated audio", "type": "number", "example": 24000 }, "instruct": { "description": "Natural language voice description for voice_design mode price calculation.", "type": [ "string", "null" ], "example": "Read this in a calm, measured tone" }, "ref_audio": { "description": "Optional on the quote (`mode: voice_clone`). When sent, held to the model's `info.limits.min_ref_audio_duration` / `max_ref_audio_duration` exactly as on generation, so a quote cannot succeed for a reference the job rejects.", "type": "string", "format": "binary" } }, "type": "object" }, "Txt2EmbeddingPriceRequestBody": { "required": [ "input", "model" ], "properties": { "input": { "description": "Input text(s) to generate embeddings for. Can be a single string or array of strings (max 2048 items). Each input limited to 8192 tokens, total request limited to 300k tokens.", "oneOf": [ { "type": "string", "example": "This is a sample text for embedding generation." }, { "type": "array", "items": { "type": "string" }, "example": [ "First text for embedding", "Second text for embedding" ] } ] }, "model": { "description": "The embedding model to use. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Bge_M3_FP16" } }, "type": "object" }, "Txt2VideoPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "required": [ "model", "width", "height", "frames", "fps" ], "properties": { "width": { "description": "Width of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "height": { "description": "Height of the generated video in pixels. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 512 }, "steps": { "description": "Number of inference steps. Bounded by `info.limits.min_steps` / `max_steps` from `GET /api/v2/models` (1–100 when the model declares none). Required when the model declares `info.features.supports_steps: true`; optional when the flag is absent. When the model declares `supports_steps: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "integer", "example": 1 }, "frames": { "description": "Number of video frames to generate. The accepted range is model-specific — read `info.limits.min_frames`/`max_frames` for your `model` from `GET /api/v2/models`; a value outside it is rejected with 422.", "type": "integer", "example": 120 }, "fps": { "description": "FPS of the generated video. The model dictates the value: read `info.defaults.fps` for your `model` from `GET /api/v2/models`. Where `min_fps` equals `max_fps` that is the only accepted value; anything outside the range is rejected with 422.", "type": "integer", "example": 30 }, "model": { "description": "The model to use for video generation. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "Ltxv_13B_0_9_8_Distilled_FP8" } }, "type": "object" }, "TranscribePriceRequestBody": { "description": "Exactly ONE input source per request — `source_url`, `source_file` or `duration_seconds` — hence the three variants below. They are mutually exclusive, not a menu of optional fields: sending two of them is a 422. `platform` belongs to the `duration_seconds` variant alone; with a URL or an upload the platform is derived from the source itself and passing it is rejected. Everything else (`include_ts`, `ts_level`, `include_metadata`, `diarize`, `lang`, `model`) applies to all three.", "oneOf": [ { "title": "From a source URL", "required": [ "source_url", "model" ], "properties": { "source_url": { "description": "URL of video/audio to estimate price for. Mutually exclusive with `source_file` and `duration_seconds`; `platform` must NOT be sent with it, as it is derived from the URL.", "type": "string", "example": "https://www.youtube.com/watch?v=jNQXAC9IVRw" }, "include_ts": { "description": "Should transcription include timestamps. Implied when `diarize` is true. Whether it raises the quote depends on `ts_level` — segment-level timing is included in the base price. Pass it exactly as you will pass it to POST /api/v2/audio/transcriptions.", "type": [ "boolean", "null" ], "example": false, "default": false }, "ts_level": { "description": "Timestamp granularity. Validated against the model exactly as on POST /api/v2/audio/transcriptions, so a price quote is never returned for a combination the job request would reject. Granularity affects the price on models that price timestamps separately: `segment` is included in the base price, while `word` and `char` carry a surcharge.", "type": [ "string", "null" ], "example": "word", "default": "segment", "enum": [ "segment", "word", "char", null ] }, "include_metadata": { "description": "Whether the job will be asked to attach source metadata. Carries a flat surcharge on models that price it, so pass it exactly as you will pass it to POST /api/v2/audio/transcriptions or the quote will come in under the amount charged. The surcharge applies only to sources that can actually return metadata: uploads always return null and are never charged for it. Every recognised platform, YouTube included, does return metadata and is charged the surcharge.", "type": [ "boolean", "null" ], "example": false, "default": false }, "diarize": { "description": "Label each timed unit with a detected speaker. Requires a model that supports diarization. Implies `include_ts` and carries the timestamp surcharge at ANY granularity, including `segment`.", "type": [ "boolean", "null" ], "example": false, "default": false }, "lang": { "description": "Language hint for the transcription. Does not affect the price, but is validated against the model the same way as on the job request: a language outside a model's published `info.limits.languages` is rejected.", "type": [ "string", "null" ], "example": "en", "maxLength": 16 }, "model": { "description": "The model to use for transcription.", "type": "string", "example": "WhisperLargeV3" } }, "type": "object" }, { "title": "From an uploaded file", "required": [ "source_file", "model" ], "properties": { "source_file": { "description": "Audio or video file to estimate price for. Mutually exclusive with `source_url` and `duration_seconds`; `platform` must NOT be sent with it, as an upload belongs to no platform.", "type": "string", "format": "binary" }, "include_ts": { "description": "Should transcription include timestamps. Implied when `diarize` is true. Whether it raises the quote depends on `ts_level` — segment-level timing is included in the base price. Pass it exactly as you will pass it to POST /api/v2/audio/transcriptions.", "type": [ "boolean", "null" ], "example": false, "default": false }, "ts_level": { "description": "Timestamp granularity. Validated against the model exactly as on POST /api/v2/audio/transcriptions, so a price quote is never returned for a combination the job request would reject. Granularity affects the price on models that price timestamps separately: `segment` is included in the base price, while `word` and `char` carry a surcharge.", "type": [ "string", "null" ], "example": "word", "default": "segment", "enum": [ "segment", "word", "char", null ] }, "include_metadata": { "description": "Whether the job will be asked to attach source metadata. An upload always returns null metadata and is never charged the surcharge, so this flag does not move the quote on this variant. Pass it exactly as you will pass it to POST /api/v2/audio/transcriptions.", "type": [ "boolean", "null" ], "example": false, "default": false }, "diarize": { "description": "Label each timed unit with a detected speaker. Requires a model that supports diarization. Implies `include_ts` and carries the timestamp surcharge at ANY granularity, including `segment`.", "type": [ "boolean", "null" ], "example": false, "default": false }, "lang": { "description": "Language hint for the transcription. Does not affect the price, but is validated against the model the same way as on the job request: a language outside a model's published `info.limits.languages` is rejected.", "type": [ "string", "null" ], "example": "en", "maxLength": 16 }, "model": { "description": "The model to use for transcription.", "type": "string", "example": "WhisperLargeV3" } }, "type": "object" }, { "title": "From a known duration", "required": [ "duration_seconds", "model" ], "properties": { "duration_seconds": { "description": "Duration in seconds for direct price estimation. Mutually exclusive with `source_url` and `source_file`. This mode never fetches the source, so pass `platform` alongside it on models that price per platform — without it the quote uses the model base rate and no duration rounding, and can come in under the amount charged.", "type": "number", "example": 3600, "minimum": 0.1 }, "platform": { "description": "The platform the source comes from. Valid ONLY on this variant, where there is no URL to derive it from — with `source_url` or `source_file` it is rejected, because the platform is taken from the source itself. Some models price per platform, and TikTok is priced from a length-band card, so a duration-only quote that omits this is priced at the model base rate and can come in under the amount charged. Pass the platform you will actually submit.", "type": [ "string", "null" ], "example": "tiktok", "enum": [ "youtube", "twitter", "twitch", "kick", "tiktok", null ] }, "include_ts": { "description": "Should transcription include timestamps. Implied when `diarize` is true. Whether it raises the quote depends on `ts_level` — segment-level timing is included in the base price. Pass it exactly as you will pass it to POST /api/v2/audio/transcriptions.", "type": [ "boolean", "null" ], "example": false, "default": false }, "ts_level": { "description": "Timestamp granularity. Validated against the model exactly as on POST /api/v2/audio/transcriptions, so a price quote is never returned for a combination the job request would reject. Granularity affects the price on models that price timestamps separately: `segment` is included in the base price, while `word` and `char` carry a surcharge.", "type": [ "string", "null" ], "example": "word", "default": "segment", "enum": [ "segment", "word", "char", null ] }, "include_metadata": { "description": "Whether the job will be asked to attach source metadata. Carries a flat surcharge on models that price it, so pass it exactly as you will pass it to POST /api/v2/audio/transcriptions or the quote will come in under the amount charged. The surcharge applies only to sources that can actually return metadata: uploads always return null and are never charged for it. Every recognised platform, YouTube included, does return metadata and is charged the surcharge.", "type": [ "boolean", "null" ], "example": false, "default": false }, "diarize": { "description": "Label each timed unit with a detected speaker. Requires a model that supports diarization. Implies `include_ts` and carries the timestamp surcharge at ANY granularity, including `segment`.", "type": [ "boolean", "null" ], "example": false, "default": false }, "lang": { "description": "Language hint for the transcription. Does not affect the price, but is validated against the model the same way as on the job request: a language outside a model's published `info.limits.languages` is rejected.", "type": [ "string", "null" ], "example": "en", "maxLength": 16 }, "model": { "description": "The model to use for transcription.", "type": "string", "example": "WhisperLargeV3" } }, "type": "object" } ] }, "Txt2MusicPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "required": [ "model", "duration", "inference_steps" ], "properties": { "model": { "description": "The model to use for music generation. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "AceStep_1_5_Turbo" }, "duration": { "description": "Duration in seconds (10-600). The accepted range is model-specific — read `info.limits.min_duration`/`max_duration` for your `model` from `GET /api/v2/models`. Some models additionally cap duration per output format via `info.limits.max_duration_by_format`.", "type": "number", "example": 30 }, "inference_steps": { "description": "Number of diffusion inference steps (1-100). Use 8 for turbo models, 32+ for base models. The accepted range is model-specific — read `info.limits.min_steps`/`max_steps` for your `model` from `GET /api/v2/models`; several models pin it to a single value.", "type": "integer", "example": 8 }, "guidance_scale": { "description": "Optional on the quote. Validated against `info.limits.min_guidance` / `max_guidance` exactly as on generation, so a quote cannot succeed for a value the job rejects.", "type": "number", "example": 1 }, "bpm": { "description": "Optional on the quote. Validated against `info.limits.min_bpm` / `max_bpm` exactly as on generation.", "type": [ "integer", "null" ], "example": 120 }, "caption": { "description": "Optional on the quote. Validated against `info.limits.min_caption` / `max_caption` (character length) exactly as on generation.", "type": "string", "example": "calm lo-fi beats" }, "lyrics": { "description": "Optional on the quote. Validated exactly as on generation when sent.", "type": "string", "example": "[Instrumental]" }, "keyscale": { "description": "Optional on the quote. Validated exactly as on generation when sent.", "type": [ "string", "null" ], "example": "C major" }, "timesignature": { "description": "Optional on the quote. Must be 2, 3, 4, or 6 — validated exactly as on generation when sent.", "type": [ "integer", "null" ], "example": 4 }, "vocal_language": { "description": "Optional on the quote. Validated exactly as on generation when sent.", "type": [ "string", "null" ], "example": "en" }, "reference_audio": { "description": "Optional on the quote. When sent, held to the model's `info.limits.min_ref_audio_duration` / `max_ref_audio_duration` exactly as on generation.", "type": "string", "format": "binary" } }, "type": "object" }, "VideoDescriptionPriceRequestBody": { "description": "Exactly ONE input source per request — `video_url`, `video_file` or `duration_seconds` — hence the three variants below. They are mutually exclusive, not a menu of optional fields: sending two of them is a 422. `platform` belongs to the `duration_seconds` variant alone. `model` and `preset` apply to all three, and are validated exactly as on POST /api/v2/videos/descriptions, so a quote is never returned for a request the job endpoint would reject.", "oneOf": [ { "title": "From a video URL", "required": [ "video_url", "model" ], "properties": { "video_url": { "description": "URL of the video to quote. Mutually exclusive with `video_file` and `duration_seconds`; `platform` must NOT be sent with it, as it is derived from the URL. Quotes from a TikTok URL are refused (the lookup itself costs money) — quote TikTok by `duration_seconds` + `platform: tiktok` instead.", "type": "string", "example": "https://www.youtube.com/watch?v=jNQXAC9IVRw" }, "preset": { "description": "The preset you will submit. It sets how much machine time the description takes (`detail` is roughly 3.75× `fast` per hour of material), which is what the price follows; on a TikTok, where the price is a fixed card, it multiplies the card ×0.75 / ×1 / ×1.5 for `fast` / `balanced` / `detail`. Omitted quotes at the model default (`balanced`). Ignored on a model without `info.features.supports_presets`.", "type": [ "string", "null" ], "example": "balanced", "enum": [ "fast", "balanced", "detail", null ] }, "include_metadata": { "description": "Whether the job will ask for source metadata. Carries a flat surcharge on URL sources (an upload always returns null metadata and is never charged), so pass it exactly as you will pass it to POST /api/v2/videos/descriptions.", "type": [ "boolean", "null" ], "example": false, "default": false }, "model": { "description": "The model to use.", "type": "string", "example": "Marlin_2B" } }, "type": "object" }, { "title": "From an uploaded file", "required": [ "video_file", "model" ], "properties": { "video_file": { "description": "Video file to quote. Mutually exclusive with `video_url` and `duration_seconds`. Only the duration is read from it here.", "type": "string", "format": "binary" }, "preset": { "description": "The preset you will submit. It sets how much machine time the description takes (`detail` is roughly 3.75× `fast` per hour of material), which is what the price follows; on a TikTok, where the price is a fixed card, it multiplies the card ×0.75 / ×1 / ×1.5 for `fast` / `balanced` / `detail`. Omitted quotes at the model default (`balanced`). Ignored on a model without `info.features.supports_presets`.", "type": [ "string", "null" ], "example": "balanced", "enum": [ "fast", "balanced", "detail", null ] }, "include_metadata": { "description": "Whether the job will ask for source metadata. Carries a flat surcharge on URL sources (an upload always returns null metadata and is never charged), so pass it exactly as you will pass it to POST /api/v2/videos/descriptions.", "type": [ "boolean", "null" ], "example": false, "default": false }, "model": { "description": "The model to use.", "type": "string", "example": "Marlin_2B" } }, "type": "object" }, { "title": "From a known duration", "required": [ "duration_seconds", "model" ], "properties": { "duration_seconds": { "description": "Source duration in seconds. Mutually exclusive with `video_url` and `video_file`. This mode never fetches the source.", "type": "number", "example": 600, "minimum": 0.1 }, "platform": { "description": "The platform the source comes from. Valid ONLY on this variant, where there is no URL to derive it from — with `video_url` or `video_file` it is rejected. It changes the price: `tiktok` is quoted on the fixed length card (and capped at 10 minutes), every other value on machine time, and `platform` also decides whether `include_metadata` carries its surcharge — only platform sources can return metadata. A duration-only quote that omits it is priced as an upload, so for a URL job it can come in under the amount actually charged.", "type": [ "string", "null" ], "example": "youtube", "enum": [ "youtube", "twitter", "twitch", "kick", "tiktok", null ] }, "preset": { "description": "The preset you will submit. It sets how much machine time the description takes (`detail` is roughly 3.75× `fast` per hour of material), which is what the price follows; on a TikTok, where the price is a fixed card, it multiplies the card ×0.75 / ×1 / ×1.5 for `fast` / `balanced` / `detail`. Omitted quotes at the model default (`balanced`). Ignored on a model without `info.features.supports_presets`.", "type": [ "string", "null" ], "example": "balanced", "enum": [ "fast", "balanced", "detail", null ] }, "include_metadata": { "description": "Whether the job will ask for source metadata. Carries a flat surcharge on URL sources (an upload always returns null metadata and is never charged), so pass it exactly as you will pass it to POST /api/v2/videos/descriptions.", "type": [ "boolean", "null" ], "example": false, "default": false }, "model": { "description": "The model to use.", "type": "string", "example": "Marlin_2B" } }, "type": "object" } ] }, "VideoRemoveBgPriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "oneOf": [ { "required": [ "video", "model" ], "properties": { "video": { "description": "Video file to remove background from. Supported formats: MP4, MPEG, QuickTime, AVI, WMV, OGG. Maximum file size: 10 MB.", "type": "string", "format": "binary" }, "model": { "description": "The background removal model to use", "type": "string", "example": "RMBG-1.4" } }, "type": "object" }, { "required": [ "width", "height", "model" ], "properties": { "width": { "description": "Width of video in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1920 }, "height": { "description": "Height of video in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1080 }, "model": { "description": "The background removal model to use", "type": "string", "example": "RMBG-1.4" } }, "type": "object" } ] }, "VideoUpscalePriceRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.", "oneOf": [ { "required": [ "video", "model" ], "properties": { "video": { "description": "Video file to upscale. Supported formats: MP4, MPEG, QuickTime, AVI, WMV, OGG. Maximum file size: 10 MB.", "type": "string", "format": "binary" }, "model": { "description": "The upscaling model to use", "type": "string", "example": "RealESRGAN_Vid_x4" }, "scale": { "description": "Upscale factor. Accepted ONLY by models that publish `info.limits.min_scale`/`max_scale` in `GET /api/v2/models`, and REQUIRED by those models — read them for your `model` before sending. A fixed-scale model (both limits absent or null, e.g. `RealESRGAN_Vid_x4`) rejects this field with a 422; a configurable one rejects its absence. Deliberately carries no example, because no single value is valid across models.", "type": [ "integer", "null" ], "maximum": 16, "minimum": 1 } }, "type": "object" }, { "required": [ "width", "height", "duration", "model" ], "properties": { "width": { "description": "Width of video in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 1024 }, "height": { "description": "Height of video in pixels for price calculation. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": "integer", "example": 576 }, "duration": { "description": "Video duration in seconds. Required when no `video` file is sent: the price is linear in the number of frames, so a quote cannot be made without it. Its maximum is model-specific — read `info.limits.max_video_duration_seconds` for your `model` from `GET /api/v2/models`; a longer duration is rejected with a 422.", "type": "number", "format": "float", "example": 12.5, "minimum": 0.1 }, "model": { "description": "The upscaling model to use", "type": "string", "example": "RealESRGAN_Vid_x4" }, "scale": { "description": "Upscale factor. Accepted ONLY by models that publish `info.limits.min_scale`/`max_scale` in `GET /api/v2/models`, and REQUIRED by those models — read them for your `model` before sending. A fixed-scale model (both limits absent or null, e.g. `RealESRGAN_Vid_x4`) rejects this field with a 422; a configurable one rejects its absence. Deliberately carries no example, because no single value is valid across models.", "type": [ "integer", "null" ], "maximum": 16, "minimum": 1 } }, "type": "object" } ] }, "Img2ImgRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422.\n\nAn input image is MANDATORY and comes in exactly one of two shapes — `image` for a single file, or `images[]` for several. Sending neither is a 422 (\"At least one image is required\"), and sending both is a 422 as well; the `oneOf` below is that choice, not a pair of optional fields. Everything else applies to both shapes.", "required": [ "prompt", "model", "seed" ], "properties": { "prompt": { "description": "The main prompt for image generation", "type": "string", "example": "A beautiful sunset over mountains" }, "negative_prompt": { "description": "Elements to avoid in the generated image. Dropped (not forwarded to the worker) when the model declares `info.features.supports_negative_prompt: false`.", "type": [ "string", "null" ], "example": "blur, darkness, noise" }, "image": { "description": "Single source image to edit. Required if \"images[]\" is not provided. Mutually exclusive with \"images[]\". Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.", "type": "string", "format": "binary" }, "images[]": { "description": "Multiple source images for editing. Maximum count is model-dependent (see model specs max_input_images, defaults to 1), never more than 16. Required if \"image\" is not provided. Mutually exclusive with \"image\". Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size per image: 10 MB.", "type": "array", "items": { "type": "string", "format": "binary" } }, "width": { "description": "Output image width in pixels. Optional - defaults to first input image width if not specified. Subject to model-specific min/max limits. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": [ "integer", "null" ], "example": 512 }, "height": { "description": "Output image height in pixels. Optional - defaults to first input image height if not specified. Subject to model-specific min/max limits. The accepted range is model-specific — read `info.limits.min_width`/`max_width` and `min_height`/`max_height` for your `model` from `GET /api/v2/models`. Some models also publish `dimension_multiple` or `resolution_step`: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. `max_pixels` and `max_ratio`, where present, cap total area and aspect ratio on top of the per-side bounds.", "type": [ "integer", "null" ], "example": 512 }, "model": { "description": "The model to use for image editing. Available models can be retrieved via the GET /api/v2/models endpoint.", "type": "string", "example": "QwenImageEdit_Plus_NF4" }, "loras": { "description": "Array of LoRA models to apply. Only models that publish a `loras` array in `GET /api/v2/models` have any to apply — the `model` example shown here publishes none, so leave the field out unless you switched to a model that does. Example is deliberately empty: a LoRA name is only valid for the one model that lists it.", "type": "array", "items": { "required": [ "name", "weight" ], "properties": { "name": { "description": "LoRA identifier, copied verbatim from `loras[].name` for your `model` in `GET /api/v2/models`. That is the value the API validates against — not the human-readable `loras[].display_name`.", "type": "string" }, "weight": { "description": "Weight of the LoRA model (must be non-negative)", "type": "number", "minimum": 0 } }, "type": "object" }, "example": [] }, "guidance": { "description": "Guidance scale. Bounded by `info.limits.min_guidance` / `max_guidance` from `GET /api/v2/models` (0–30 when the model declares none). Required when the model declares `info.features.supports_guidance: true`; optional when the flag is absent. When the model declares `supports_guidance: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "number", "example": 7.5 }, "steps": { "description": "Number of inference steps. Bounded by `info.limits.min_steps` / `max_steps` from `GET /api/v2/models` (1–100 when the model declares none). Required when the model declares `info.features.supports_steps: true`; optional when the flag is absent. When the model declares `supports_steps: false` the value is accepted and dropped — it is neither forwarded to the worker nor priced.", "type": "integer", "example": 20 }, "quality": { "description": "Quality tier, for models that support one (e.g. gpt-image: low/medium/high/auto). Only the values listed in that model's available options are accepted; ignored for models without a quality tier. Accepted values are model-specific — read `info.limits.quality_options` for your `model` from `GET /api/v2/models`. A model with an empty or absent list does not support a quality tier and ignores the field.", "type": [ "string", "null" ], "example": "medium" }, "seed": { "description": "Random seed for generation", "type": "integer", "example": 42 }, "enhance_prompt": { "description": "When true, the prompt is boosted by the inline prompt booster before generation (async pre-step). Requires a prompt-booster guide configured for the model; the boost fee is billed on the job. Rejected with 422 if no guide exists for the model or the account balance cannot cover the boost fee.", "type": "boolean", "example": false, "default": false }, "webhook_url": { "description": "Optional HTTPS URL to receive webhook notifications for job status changes (processing, completed, failed). Must be HTTPS. Max 2048 characters. A per-request URL is self-contained: it is delivered even when the account has no webhook configuration, or the account webhook is disabled. See the `webhooks` block at the top level of this document for the event payloads and the headers each delivery carries.", "type": [ "string", "null" ], "format": "uri", "example": "https://your-server.com/webhooks/deapi", "maxLength": 2048 }, "webhook_secret": { "description": "Optional per-request HMAC secret (min. 32 chars) used to sign the webhook callback. Overrides the account-default secret for this job only. If omitted, the account-default secret signs the callback; if no secret exists at all, the callback is still delivered but UNSIGNED (empty X-DeAPI-Signature header). Requires `webhook_url` to also be set.", "type": [ "string", "null" ], "example": "a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5", "maxLength": 255, "minLength": 32 } }, "type": "object", "oneOf": [ { "title": "One image", "required": [ "image" ], "type": "object" }, { "title": "Several images", "required": [ "images[]" ], "type": "object" } ] }, "Img2TxtRequestBody": { "required": [ "image", "model" ], "properties": { "image": { "description": "Image file to extract text from. Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.", "type": "string", "format": "binary" }, "model": { "description": "The OCR model to use for text extraction", "type": "string", "example": "Nanonets_Ocr_S_F16" }, "language": { "description": "Language code for OCR processing (optional)", "type": [ "string", "null" ], "example": "en" }, "format": { "description": "Output format for extracted text", "type": [ "string", "null" ], "example": "text", "enum": [ "text", "json", null ] }, "return_result_in_response": { "description": "If true, the result will be returned directly in the response instead of only download url. Optional parameter.", "type": [ "boolean", "null" ], "example": false, "default": false }, "webhook_url": { "description": "Optional HTTPS URL to receive webhook notifications for job status changes (processing, completed, failed). Must be HTTPS. Max 2048 characters. A per-request URL is self-contained: it is delivered even when the account has no webhook configuration, or the account webhook is disabled. See the `webhooks` block at the top level of this document for the event payloads and the headers each delivery carries.", "type": [ "string", "null" ], "format": "uri", "example": "https://your-server.com/webhooks/deapi", "maxLength": 2048 }, "webhook_secret": { "description": "Optional per-request HMAC secret (min. 32 chars) used to sign the webhook callback. Overrides the account-default secret for this job only. If omitted, the account-default secret signs the callback; if no secret exists at all, the callback is still delivered but UNSIGNED (empty X-DeAPI-Signature header). Requires `webhook_url` to also be set.", "type": [ "string", "null" ], "example": "a1b2c3d4e5f60708091a2b3c4d5e6f7081920a1b2c3d4e5f60708091a2b3c4d5", "maxLength": 255, "minLength": 32 } }, "type": "object" }, "Img2VideoRequestBody": { "description": "Every example in this schema is a working set for the `model` example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read `info.limits` and `info.defaults` for the model you actually intend to use from `GET /api/v2/models`. Substituting a different `model` while keeping these values is the most common source of a 422. Reference inputs (`ref_images`/`ref_videos`/`ref_audios`) are bounded per model too: a model that advertises `supports_image_refs`/`supports_video_refs`/`supports_audio_refs` always publishes the effective `info.limits.max_ref_images`, `max_ref_videos`, `max_ref_audios`, `max_ref_files` (the cap across all three types), `min/max_ref_video_duration`, `min/max_ref_audio_duration` and `min/max_ref_image_ratio` — read them rather than the ceilings quoted on each field, which are only the outer envelope of self-hosted models (never more than 9 / 1 / 3 files and 12 in total; a partner-served model publishes its own, possibly higher, limits). An unsupported type publishes `0`. Every uploaded image, keyframe or reference, must be 64–5000 px per side.", "required": [ "prompt", "model", "width", "height", "seed", "frames", "fps" ], "properties": { "prompt": { "description": "The main prompt for video generation", "type": "string", "example": "A beautiful sunset over mountains" }, "negative_prompt": { "description": "Elements to avoid in the generated video. Dropped (not forwarded to the worker) when the model declares `info.features.supports_negative_prompt: false`.", "type": [ "string", "null" ], "example": "blur, darkness, noise" }, "first_frame_image": { "description": "Image for the first frame of video. Required unless reference inputs (`ref_images`/`ref_videos`) are supplied — the two modes are mutually exclusive. Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB, 64–5000 px per side. Any aspect ratio: a keyframe is fitted to the generation canvas, so the 1:4–4:1 rule that applies to `ref_images` does not apply here.", "type": "string", "format": "binary" }, "ref_images": { "description": "Ordered reference images (full-reference mode). **Order is binding**: `ref_images[0]` is\naddressed in the prompt as ``, `ref_images[1]` as ``, and so on —\nnumbering is 1-based and counted within images only. Send the parts in index order, or\nindex them explicitly (`ref_images[0]`, `ref_images[1]`, …); the list must start at 0 and\nhave no gaps. Reordering the list rebinds every label in your prompt and produces a\ndifferent video with no error. Mutually exclusive with `first_frame_image`/`last_frame_image`.\nRequires a model whose specs advertise image-reference support; video and audio\nreferences are advertised separately, so a model may accept one type and not another.\nSupported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB, 64–5000 px\nper side. Each image must be within a 1:4–4:1 aspect ratio (`info.limits.min_ref_image_ratio`\n/ `max_ref_image_ratio`) — a reference keeps its own aspect, unlike a keyframe, which is\nfitted to the canvas. **The number of entries is model-specific — read\n`info.limits.max_ref_images` for your `model` from `GET /api/v2/models`.** Self-hosted models take at\nmost 9; partner-served models publish their own, possibly higher, limit.", "type": [ "array", "null" ], "items": { "type": "string", "format": "binary" } }, "ref_videos": { "description": "Ordered reference videos (full-reference mode). `ref_videos[0]` is addressed as `