> ## 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. # List chat, embedding, and video models > Returns the catalog of chat, embedding, and video models available to your team. Shape mirrors OpenAI's `GET /v1/models` envelope (`{ object: "list", data: [...] }`) so SDK clients that already speak OpenAI drop in unchanged. Platform-specific fields (capability tags, lifecycle pointers) live under `aurous_metadata` on each entry. Per-model pricing lives on top-level `chat_pricing` (chat models), `embedding_pricing` (embedding models), or `video_pricing` (video models) — the unused siblings are null. Video rates are a matrix in credits per million VIDEO tokens, keyed by output resolution and whether the request includes video input; listed video rates use standard (non-team) pricing. Customers can compute credits-per-1K by dividing the published `credits_per_M` value by 1000. When the catalog is empty the response is `200` with `data: []` — never `404`. No query, path, or body parameters are accepted. 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 get /v1/models 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/models: get: tags: - Models summary: List chat, embedding, and video models description: >- Returns the catalog of chat, embedding, and video models available to your team. Shape mirrors OpenAI's `GET /v1/models` envelope (`{ object: "list", data: [...] }`) so SDK clients that already speak OpenAI drop in unchanged. Platform-specific fields (capability tags, lifecycle pointers) live under `aurous_metadata` on each entry. Per-model pricing lives on top-level `chat_pricing` (chat models), `embedding_pricing` (embedding models), or `video_pricing` (video models) — the unused siblings are null. Video rates are a matrix in credits per million VIDEO tokens, keyed by output resolution and whether the request includes video input; listed video rates use standard (non-team) pricing. Customers can compute credits-per-1K by dividing the published `credits_per_M` value by 1000. When the catalog is empty the response is `200` with `data: []` — never `404`. No query, path, or body parameters are accepted. 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: V1ModelsController_list parameters: - 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}$ responses: '200': description: List of available chat, embedding, and video models. content: application/json: schema: $ref: '#/components/schemas/ModelsListResponse' 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 '400': description: >- `Aurous-Version` header is pinned to a value that is not a recognised version date or is malformed. Use a published date or omit the header to receive the platform default. 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 '401': description: Unauthorized — 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 '403': description: >- Account not approved for closed beta. error.code is one of `account_pending`, `account_rejected`, `account_suspended`. There is no retry — contact support to be approved. 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 '429': description: Rate limit exceeded — retry after the seconds in `Retry-After`. 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 security: - api-key: [] components: schemas: ModelsListResponse: type: object properties: object: type: string description: Discriminator — always `list`. example: list enum: - list data: description: >- All active + public models in the catalog. Order matches the admin-configured `sort_order`. Empty catalog returns `data: []` (NEVER 404). type: array items: $ref: '#/components/schemas/ModelResponse' required: - object - data ErrorResponse: type: object properties: error: description: Error payload allOf: - $ref: '#/components/schemas/ErrorPayload' required: - error ModelResponse: type: object properties: object: type: string description: Discriminator — always `model`. example: model enum: - model id: type: string description: >- Public, customer-facing slug. STABLE — pin in production code. The opaque DB primary key is never exposed. example: aurous-chat-pro created: type: number description: >- Unix timestamp (seconds) for when this model record was created in the catalog. Mirrors OpenAI's field shape. example: 1716076800 owned_by: type: string description: >- Owner of the model. Always `aurous` — we abstract the underlying providers. example: aurous enum: - aurous kind: type: string description: >- Model kind. `chat` models accept POST /v1/chat/completions; `embedding` models accept POST /v1/embeddings; `video` models publish a credits-denominated rate matrix under `video_pricing`. example: chat enum: - chat - embedding - video display_name: type: string description: >- Customer-facing display name (UI labels, model picker). Sanitized on the server before it is returned. May change without notice; do not key off this field — use `id` for stable identity. example: Aurous Chat Pro description: type: string description: >- Short marketing description of the model. Sanitized on the server on the same rule that applies to `display_name`. Empty string when the admin has not authored a description. example: Flagship multimodal chat model with 256K context. chat_pricing: description: >- Chat pricing — present (non-null) only when `kind === 'chat'`. `credits_per_M` reflects the caller's effective rate after per-team and per-model overrides. NOT frozen per `Aurous-Version`; recompute on every poll. nullable: true allOf: - $ref: '#/components/schemas/ChatPricing' embedding_pricing: description: >- Embedding pricing — present (non-null) only when `kind === 'embedding'`. Modalities the model does not bill for surface as `credits_per_M: 0` so the shape stays uniform. nullable: true allOf: - $ref: '#/components/schemas/EmbeddingPricing' video_pricing: description: >- Video pricing — present (non-null) only when `kind === 'video'`. Rates are credits per million VIDEO tokens, keyed by output resolution and whether the request includes video input. Listed rates use STANDARD (non-team) pricing; the credit hold and final charge for a specific request are echoed on the generation response. nullable: true allOf: - $ref: '#/components/schemas/VideoPricing' aurous_metadata: description: >- Aurous-specific metadata. Capabilities, lifecycle pointers, and embedding-only sizing live here so the OpenAI-compatible top-level fields stay clean for drop-in SDKs. allOf: - $ref: '#/components/schemas/ModelAurousMetadata' required: - object - id - created - owned_by - kind - display_name - description - chat_pricing - embedding_pricing - video_pricing - aurous_metadata 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 - 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 ChatPricing: type: object properties: input: description: Input-token pricing. allOf: - $ref: '#/components/schemas/ModelPricingDimension' output: description: Output-token pricing. allOf: - $ref: '#/components/schemas/ModelPricingDimension' required: - input - output EmbeddingPricing: type: object properties: text: description: Text-modality input pricing. allOf: - $ref: '#/components/schemas/ModelPricingDimension' visual: description: >- Visual-modality input pricing. Applies to `image_url` content parts. `video_url` input is no longer accepted on `POST /v1/embeddings` (rejected with `400 embeddings_video_unsupported`). Embed images via `image_url` parts only. allOf: - $ref: '#/components/schemas/ModelPricingDimension' required: - text - visual VideoPricing: type: object properties: unit: type: string description: >- Billing unit for every rate in `rates`. Always `credits_per_M_tokens`. example: credits_per_M_tokens enum: - credits_per_M_tokens rates: description: >- Rate matrix keyed by output resolution and whether the request includes video input. Listed rates use STANDARD (non-team) pricing — the catalog is team-agnostic. The exact credit hold and final charge for a specific request are always echoed on the generation response. type: array items: $ref: '#/components/schemas/VideoRateEntry' required: - unit - rates ModelAurousMetadata: type: object properties: context_window: type: number description: >- Maximum input context window in tokens. Includes prompt, system, tool descriptions, and accumulated chat history. Excludes the model's reserved output budget. Null when the kind is `embedding` (use `max_input_items` instead). example: 256000 nullable: true default_max_output_tokens: type: number description: >- Default max_tokens applied when `max_tokens` is omitted on a POST /v1/chat/completions request. Holds and credit estimates use this value when no explicit cap is provided. Null for embedding models (no output budget concept). example: 4096 nullable: true max_output_tokens_hard_cap: type: number description: >- Hard cap on `max_tokens` for POST /v1/chat/completions. Requests that exceed this cap are rejected with `400 invalid_request:max_tokens_exceeds_hard_cap`. Null for embedding models. example: 128000 nullable: true capabilities: description: >- Capability tags this model supports. Boolean flags only (e.g., `streaming`, `tools`, `multimodal_input`, `structured_output`, `supports_logprobs`, `supports_seed`, `reasoning_effort`). Vendor-name tags are stripped to keep the brand surface clean. Array-valued capabilities (e.g., `dimensions` on embeddings) are surfaced as their own dedicated top-level fields. example: - streaming - tools - structured_output type: array items: type: string dimensions: description: >- Supported embedding output dimensions (request as `dimensions` on POST /v1/embeddings). Defaults to the first entry when the request omits it. Null for chat models. example: - 256 - 512 - 1024 nullable: true type: array items: type: number max_input_items: type: number description: >- Max number of input items per POST /v1/embeddings request. Null for chat models. example: 96 nullable: true resolutions: description: >- Output resolutions this video model supports. Cross-reference with `video_pricing.rates[].resolutions` for the per-resolution billing rate. Null for chat and embedding models. example: - 480p - 720p - 1080p - 4k nullable: true type: array items: type: string duration: description: >- Supported output clip duration range in seconds. Null for chat and embedding models. nullable: true allOf: - $ref: '#/components/schemas/VideoDurationRange' fps: type: number description: >- Output frame rate in frames per second. Null for chat and embedding models. example: 24 nullable: true aliases: description: >- Alternate model ids accepted wherever a model id is accepted; each alias resolves to this model. Prefer `id` for stable pinning. Null for chat and embedding models. example: - seedance-2.0 - seedance-2.0-pro nullable: true type: array items: type: string deprecated_at: type: string description: >- ISO 8601 timestamp after which the model is scheduled for removal. Null when the model is not scheduled for deprecation. Customers integrate against this field to build migration alerts BEFORE the model goes dark. example: null nullable: true replaced_by_slug: type: string description: >- Slug of the recommended replacement model when `deprecated_at` is set. Null when no successor is published. Pair with `deprecated_at` to swap automatically on deprecation. example: null nullable: true required: - context_window - default_max_output_tokens - max_output_tokens_hard_cap - capabilities - deprecated_at - replaced_by_slug ModelPricingDimension: type: object properties: credits_per_M: type: number description: >- Credits per million tokens at the caller's effective rate. Customers can compute credits-per-1K by dividing by 1000. Reflects the team's pricing overrides (per-team markup, per-model markup, per-team credit anchor) when present; otherwise the platform default. Recompute on every poll — overrides may be flipped without advancing `Aurous-Version`. example: 75 required: - credits_per_M VideoRateEntry: type: object properties: resolutions: description: >- Output resolutions this rate applies to. Match the resolution you request (e.g. `720p`) against this array to find your billing rate. example: - 720p type: array items: type: string video_input: type: boolean description: >- Whether this rate applies to requests that include video input (reference video). `false` = text/image-driven generation; `true` = video-driven generation (typically cheaper per token). example: false credits_per_M: type: number description: >- Credits per million video tokens for this cell. Divide by 1000 for credits per 1K tokens. Video tokens scale with clip duration, output resolution, and frame rate. example: 1138.8889 required: - resolutions - video_input - credits_per_M VideoDurationRange: type: object properties: min: type: number description: Minimum clip duration in seconds. example: 4 max: type: number description: Maximum clip duration in seconds. example: 15 adaptive: type: boolean description: >- When true, the model may choose a duration within [min, max] on requests that ask for an adaptive-length clip. example: true required: - min - max - adaptive securitySchemes: api-key: type: apiKey in: header name: X-Api-Key description: Your team API key (starts with `al_live_`). ````