> ## Documentation Index > Fetch the complete documentation index at: https://docs.aurous-labs.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a chat completion > OpenAI-compatible chat completion. Supports streaming (`stream: true` returns `text/event-stream` SSE), function calling (`tools` / `tool_choice`), multimodal input (image_url / video_url content parts), reasoning_effort, and structured output (`response_format`). Pricing: credits are debited from team balance at completion, snapshotted to the per-model pricing version that was active when the credit hold was placed. `Idempotency-Key` is honored on non-streamed requests only (24h replay window). Streamed requests echo `Aurous-Idempotency-Status: ignored_streaming` and emit a warning frame as the first SSE data line; use `stream=false` for at-most-once semantics. Image and video rates are frozen per `Aurous-Version`: customers pinned to an older version see the rate card that was current when their version shipped, so price changes are never silently retroactive. Chat and embedding rates are NOT frozen per `Aurous-Version` — they track the most recently published rate version for each model, because LLM provider economics shift on weekly cadence. The receipt echoed on every chat / embedding response carries the exact rate that applied at dispatch time, so audit trails remain stable. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/chat/completions openapi: 3.0.0 info: title: Aurous Labs API description: >- Generate AI images with custom LoRA styles. ## Authentication All requests require an API key passed in the `X-Api-Key` header. Create API keys in your [dashboard](https://app.aurous-labs.com/dashboard/api-keys). ## Closed-beta access gate API keys are scoped to a user. If that user's account is not approved for the closed beta, every request returns `403` with one of these `error.code` values: - `account_pending` — awaiting review - `account_rejected` — declined post-signup - `account_suspended` — was approved, then suspended There is no retry — contact support to be approved. The same codes are emitted by the WebSocket gateway via 4001 close. ## Common headers Every response carries `Aurous-Request-Id` (a server-minted `req_` for support tracing) and `Aurous-Version` (the API version applied to the response). Optionally pin a version on the request with `Aurous-Version: YYYY-MM-DD` — defaults to your team's pinned version. ## Quick Start ```bash curl -X POST https://api.aurous-labs.com/v1/images \ -H "X-Api-Key: al_live_your_key" \ -H "Content-Type: application/json" \ -d '{"prompt": "A golden sunset over mountains", "lora_id": "your-lora-id", "size": "2k_1_1"}' ``` version: 1.0.0 contact: {} servers: - url: https://api.aurous-labs.com description: Production - url: https://api.preprod.aurous-labs.com description: Preprod (staging) security: [] tags: - name: Seedance (raw) description: >- Drop-in raw passthrough for Seedance video generation. Point the official Seedance provider SDK at this API's base URL and authenticate with your Aurous API key in the `X-Api-Key` header — request bodies are forwarded to the provider verbatim and responses come back shape-identical, so you keep the provider's exact request/response shapes. Task ids are Aurous-native `vid_…` ids. Billing rides response headers, not the body: `Aurous-Credits-Held` on the create response and `Aurous-Credits-Charged` on a settled, succeeded task read — the body itself stays provider-shaped. paths: /v1/chat/completions: post: tags: - Chat summary: Create a chat completion description: >- OpenAI-compatible chat completion. Supports streaming (`stream: true` returns `text/event-stream` SSE), function calling (`tools` / `tool_choice`), multimodal input (image_url / video_url content parts), reasoning_effort, and structured output (`response_format`). Pricing: credits are debited from team balance at completion, snapshotted to the per-model pricing version that was active when the credit hold was placed. `Idempotency-Key` is honored on non-streamed requests only (24h replay window). Streamed requests echo `Aurous-Idempotency-Status: ignored_streaming` and emit a warning frame as the first SSE data line; use `stream=false` for at-most-once semantics. Image and video rates are frozen per `Aurous-Version`: customers pinned to an older version see the rate card that was current when their version shipped, so price changes are never silently retroactive. Chat and embedding rates are NOT frozen per `Aurous-Version` — they track the most recently published rate version for each model, because LLM provider economics shift on weekly cadence. The receipt echoed on every chat / embedding response carries the exact rate that applied at dispatch time, so audit trails remain stable. operationId: V1ChatCompletionsController_create parameters: - name: Aurous-Idempotency-Status in: header description: >- Echoed on the response. `ignored_streaming` when `stream=true` (idempotency does not apply); otherwise reflects the interceptor decision. required: false schema: type: string - name: Idempotency-Key in: header description: >- Stripe-style idempotency key. Honored only when `stream=false`. Same key + same canonical-JSON body returns the cached response with `Aurous-Idempotent-Replayed: true`. Same key + different body returns 409 `idempotency_key_in_use`. Replay window is 24 hours. required: false schema: type: string - name: Aurous-Version in: header required: false description: >- Optional API version pin (YYYY-MM-DD). Defaults to your team's pinned version, or the system default `2026-07-16` for unauthenticated requests. schema: type: string example: '2026-07-16' pattern: ^\d{4}-\d{2}-\d{2}$ requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionDto' responses: '200': description: >- Chat completion. Content type depends on `stream`: `application/json` for `stream:false` (full response body); `text/event-stream` for `stream:true` (SSE). content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' text/event-stream: schema: type: string description: >- SSE frames: `data: {}\n\n` for each generation chunk (OpenAI-shape), optionally `data: {"warning":{...}}` if `Idempotency-Key` was sent, and `data: [DONE]\n\n` to signal stream end. On provider error mid-stream a `data: {"error":{code,type,message,request_id}}\n\n` frame precedes `[DONE]`. headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' Aurous-Idempotent-Replayed: description: >- Present (literal `true`) when this response was served from a stored idempotent replay — the same `Idempotency-Key` + canonical body was seen within the 24h window and the original response is returned WITHOUT re-executing (no second charge, no second task). Absent on the first (fresh) execution and on any request sent without an `Idempotency-Key`. Only on the idempotency-aware create routes. schema: type: string enum: - 'true' example: 'true' Aurous-Idempotency-Status: description: >- Streaming idempotency signal on `POST /v1/chat/completions`. `ignored_streaming` when a streamed request (`stream: true`) also carried an `Idempotency-Key` — idempotent replay does not apply to SSE streams; `not_set` when a streamed request carried no key. Non-streamed idempotent replays are signalled by `Aurous-Idempotent-Replayed` instead. schema: type: string enum: - ignored_streaming - not_set example: ignored_streaming '400': description: >- Validation error, `model_wrong_kind`, `max_tokens_exceeds_hard_cap`, `missing_max_tokens_no_model_default`, `tool_choice_required_unsupported`, `response_format_too_large`, `response_format_too_deep`, or `max_input_tokens_exceeded`. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' '402': description: '`balance_too_low` — team has insufficient credits.' content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' '403': description: '`model_disabled` or insufficient scope.' content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' '404': description: '`model_not_found`.' content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' '429': description: RPM or TPM rate limit exceeded. See `Retry-After` header. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 Retry-After: description: >- Seconds to wait before retrying. Present on 429 (rate limit) and on 503 provider_unavailable. Prefer this over computing X-RateLimit-Reset − now. schema: type: integer example: 12 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' '502': description: '`chat_provider_unavailable` — upstream issue.' content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' '503': description: '`provider_rate_limited`.' content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: Aurous-Request-Id: description: Server-minted request id. Quote this in support tickets. schema: type: string example: req_01HXMQ7Z3K8Y2NABCDEFGHJKMP Aurous-Version: description: API version pin applied to this response (YYYY-MM-DD). schema: type: string example: '2026-07-16' X-RateLimit-Limit: description: Bucket capacity (max tokens) for this endpoint class. schema: type: integer example: 120 X-RateLimit-Remaining: description: Tokens remaining after this request. schema: type: integer example: 119 X-RateLimit-Reset: description: >- Epoch seconds when the bucket would be full again, assuming no further requests. schema: type: integer example: 1700000060 Retry-After: description: >- Seconds to wait before retrying. Present on 429 (rate limit) and on 503 provider_unavailable. Prefer this over computing X-RateLimit-Reset − now. schema: type: integer example: 12 X-RateLimit-TPM-Limit: description: >- Tokens-per-minute bucket capacity for this endpoint class. Only set on TPM-throttled routes (/v1/chat/completions, /v1/embeddings). schema: type: integer example: 100000 X-RateLimit-TPM-Remaining: description: >- Tokens remaining in the current minute bucket after this request. Clamped to 0 in the header (deductions can push the internal bucket negative for one burst). schema: type: integer example: 87500 X-RateLimit-TPM-Reset: description: ISO 8601 timestamp when the TPM bucket resets to full. schema: type: string format: date-time example: '2026-05-19T18:14:00.000Z' security: - api-key: [] components: schemas: CreateChatCompletionDto: type: object properties: model: type: string description: >- Public model slug from GET /v1/models. Example: `aurous-grow-2.0-pro`. example: aurous-grow-2.0-pro maxLength: 128 messages: description: Conversation messages, ordered oldest → newest. 1-200 messages. type: array items: $ref: '#/components/schemas/ChatMessageDto' max_tokens: type: number minimum: 1 description: >- Maximum tokens to generate. Defaults to the model’s `default_max_output_tokens`. Requests with `max_tokens` > the model’s `max_output_tokens_hard_cap` return 400 `max_tokens_exceeds_hard_cap`. temperature: type: number minimum: 0 maximum: 2 top_p: type: number minimum: 0 maximum: 1 stream: type: boolean description: >- If `true`, response is text/event-stream (SSE) with OpenAI-shaped chunks. When streaming, `Idempotency-Key` is ignored and a warning frame is emitted in the first chunk; use `stream=false` for at-most-once semantics. stream_options: type: object description: >- OpenAI-compatible stream options. When `stream: true`, `include_usage: true` (the default on Aurous Labs) causes the final non-`[DONE]` SSE frame to carry the `usage` block with token counts + credits_charged. Set `include_usage: false` to suppress (matches OpenAI behavior when the flag is omitted on their side). Ignored when `stream: false`. tools: type: array items: $ref: '#/components/schemas/ChatToolDto' tool_choice: type: object description: >- Function-calling routing: `auto` | `none` | `{type:"function", function:{name}}`. `required` is NOT supported and returns 400 `tool_choice_required_unsupported`. response_format: type: object description: >- Structured output. `{type:"text"|"json_object"|"json_schema", json_schema?:{...}}`. For `json_schema`, the schema must be ≤10KB JSON-stringified and ≤5 levels deep, else 400 `response_format_too_large` / `response_format_too_deep`. reasoning_effort: type: string enum: - minimal - low - medium - high description: >- Reasoning depth for reasoning-capable models. Higher values increase latency + token cost (reasoning tokens billed separately at the model’s output rate). seed: type: number description: Random seed for reproducibility (when supported by the model). stop: type: object description: >- Up to 4 stop sequences (string or array of strings; each ≤200 chars). presence_penalty: type: number minimum: -2 maximum: 2 frequency_penalty: type: number minimum: -2 maximum: 2 logprobs: type: boolean description: Return log-probabilities for output tokens. top_logprobs: type: number minimum: 0 maximum: 20 required: - model - messages ChatCompletionResponse: type: object properties: id: type: string description: Opaque chat-completion id. example: cmp_01HXMQ7Z3K8Y2ABCDEFGHJKM object: type: string enum: - chat.completion created: type: number description: Unix timestamp (seconds). example: 1731948000 model: type: string description: Aurous model slug used. example: aurous-grow-2.0-pro choices: description: Always exactly 1 entry in v1.0. type: array items: $ref: '#/components/schemas/ChatChoice' usage: $ref: '#/components/schemas/ChatUsage' status: type: string description: >- Aurous extension: terminal state of the chat completion. `completed` is the normal happy path. `in_progress` means the request is still being processed (only possible when polling GET /:id during a streamed request). `failed` means the provider or platform errored — see `error` for the typed reason. `cancelled` means a cancel was requested or the client disconnected. enum: - completed - in_progress - failed - cancelled example: completed error: description: >- Aurous extension: present only when `status` is `failed` or `cancelled` (in addition to the main error response when applicable). Echoes the typed error envelope shape so customers can branch on `error.code` without parsing string messages. example: code: chat_provider_unavailable type: server_error message: Provider request failed. allOf: - $ref: '#/components/schemas/ChatCompletionResponseError' required: - id - object - created - model - choices - usage - status ErrorResponse: type: object properties: error: description: Error payload allOf: - $ref: '#/components/schemas/ErrorPayload' required: - error ChatMessageDto: type: object properties: role: type: string enum: - system - user - assistant - tool content: description: >- Message content. String OR an array of content parts (text + image_url + video_url) for multimodal input. Whitespace-only strings are rejected. oneOf: - type: string - type: array items: $ref: '#/components/schemas/ChatContentPartDto' name: type: string description: Optional participant name. tool_call_id: type: string description: 'When role=tool: the id of the tool call this message responds to.' required: - role - content ChatToolDto: type: object properties: type: type: string enum: - function function: type: object description: >- JSON Schema-ish function descriptor. `name` and `parameters` required; `description` recommended. example: name: get_weather description: Get current weather for a city. parameters: type: object properties: city: type: string required: - city required: - type - function ChatChoice: type: object properties: index: type: number example: 0 description: Choice index (always 0 today; multi-choice not supported in v1.0). message: $ref: '#/components/schemas/ChatChoiceMessage' finish_reason: type: string enum: - stop - length - tool_calls - content_filter nullable: true description: >- `stop` — normal completion. `length` — hit `max_tokens`. `tool_calls` — model invoked tools. `content_filter` — provider blocked output (no charge if no content produced). required: - index - message ChatUsage: type: object properties: prompt_tokens: type: number description: Tokens consumed by the prompt + system message. example: 200 completion_tokens: type: number description: Tokens produced in the assistant content. example: 600 reasoning_tokens: type: number description: Reasoning tokens (present when reasoning_effort was passed). example: 50 total_tokens: type: number description: prompt + completion + reasoning. example: 850 credits_charged: type: number description: 'Aurous extension: total credits charged for this request.' example: 0.2856 breakdown: description: 'Aurous extension: itemized breakdown.' allOf: - $ref: '#/components/schemas/ChatUsageBreakdown' required: - prompt_tokens - completion_tokens - total_tokens - credits_charged - breakdown ChatCompletionResponseError: type: object properties: code: type: string description: Typed error code. Same taxonomy as the top-level error envelope. example: chat_provider_unavailable type: type: string description: High-level error category for retry-stance decisions. example: server_error message: type: string description: Human-readable, vendor-neutral message. example: Provider request failed. required: - code - type - message ErrorPayload: type: object properties: type: type: string description: Broad error category example: invalid_request enum: - invalid_request - authentication - not_found - rate_limit - server_error code: type: string description: >- Stable error code (programmatic discriminator). Closed-beta gate emits one of `account_pending`, `account_rejected`, `account_suspended` on 403. example: balance_too_low enum: - invalid_request - missing_field - invalid_format - value_out_of_range - unsupported_lora_for_mode - generation_not_cancellable - prompt_blocked - reference_blocked - output_moderation_rejected - unknown_version - mutually_exclusive_input - character_not_ready - parameter_invalid_combination - too_many_reference_images - action_not_available - upload_invalid - balance_too_low - idempotency_key_in_use - api_key_not_found - payload_too_large - missing_api_key - invalid_api_key - revoked_api_key - resource_not_found - forbidden_resource - account_pending - account_rejected - account_suspended - already_approved - already_rejected - already_suspended - invalid_reinstate_target - invalid_suspend_target - cannot_moderate_admin - too_many_requests - concurrency_limit_exceeded - tpm_rate_limit_exceeded - internal_error - provider_unavailable - provider_timeout - provider_not_configured - invalid_time_range - invalid_bucket_width - too_many_buckets - too_many_group_by - invalid_filter - invalid_page_token - export_too_large - user_already_exists - self_invite_forbidden - invite_link_failed - invite_rate_limited - model_not_found - model_disabled - model_wrong_kind - max_tokens_exceeds_hard_cap - chat_model_misconfigured - embeddings_input_too_large - embeddings_unsupported_dimensions - pricing_frozen - provider_rate_limited - chat_provider_request_invalid - chat_provider_auth_failed - chat_provider_unavailable - max_input_tokens_exceeded - chat_provider_unknown_error - embeddings_provider_unknown_error - embeddings_batch_not_supported - embeddings_input_too_many_items - embeddings_video_unsupported - encoding_format_unsupported - missing_max_tokens_no_model_default - chat_cancel_target_not_found - chat_completion_not_found - chat_cancel_target_already_terminal - chat_cancel_target_not_cancellable - tool_choice_required_unsupported - response_format_too_large - response_format_too_deep - invalid_cursor - invalid_cursor_for_endpoint - model_slug_exists - output_expired - output_not_available - content_filtered - image_generation_failed - reference_media_invalid - reference_media_cap_reached - reference_fetch_failed - unsupported_auth_method - insufficient_scope - uploads_expired - provider_unknown_error message: type: string description: Human-readable message example: Team available balance is 1.5 credits, generation requires 2.0. param: type: object description: Field name when the error is parameter-scoped example: prompt nullable: true doc_url: type: string description: Documentation link for this error code example: https://docs.aurous-labs.com/errors#balance_too_low request_id: type: string description: Echoes Aurous-Request-Id — quote in support tickets example: req_01HXMQ7Z3K8Y2ABCDEFGHJKM required: - type - code - message - doc_url - request_id ChatContentPartDto: type: object properties: type: type: string enum: - text - image_url - video_url text: type: string description: Plain text. Required when type=text. image_url: type: object example: url: https://example.com/img.png detail: high description: >- Image input. Required when type=image_url. `detail` (`low`|`high`|`auto`) affects token cost. video_url: type: object example: url: https://example.com/video.mp4 description: >- Video input. Required when type=video_url. Charged at video-token tier. required: - type ChatChoiceMessage: type: object properties: role: type: string enum: - assistant content: type: object nullable: true description: >- Assistant text. Null when finish_reason is content_filter with no content, or tool_calls only. tool_calls: description: Present when the model invoked one or more tools. type: array items: $ref: '#/components/schemas/ChatChoiceToolCall' required: - role ChatUsageBreakdown: type: object properties: input_credits: type: number description: Input tokens converted to credits (with markup applied). example: 0.0006 output_credits: type: number description: Output (non-reasoning) tokens converted to credits. example: 0.27 reasoning_credits: type: number description: >- Reasoning tokens converted to credits. Present only when `reasoning_effort` was passed AND the model emitted reasoning tokens. example: 0.015 model: type: string description: Aurous model slug used. example: aurous-grow-2.0-pro pricing_version: type: number description: >- Pricing version snapshot at hold-placement time. Receipts replay deterministically even if the model rates change later. See `GET /v1/models` for the live per-model credits-per-million. example: 7 required: - input_credits - output_credits - model - pricing_version ChatChoiceToolCall: type: object properties: id: type: string description: Opaque tool-call id assigned by the model. example: call_01HXM... type: type: string enum: - function function: $ref: '#/components/schemas/ChatChoiceFunction' required: - id - type - function ChatChoiceFunction: type: object properties: name: type: string example: get_weather arguments: type: string description: >- JSON-stringified arguments. Use JSON.parse on your end before invoking the tool. example: '{"city":"Tokyo"}' required: - name - arguments securitySchemes: api-key: type: apiKey in: header name: X-Api-Key description: Your team API key (starts with `al_live_`). ````