> ## Documentation Index > Fetch the complete documentation index at: https://docs.near.ai/llms.txt > Use this file to discover all available pages before exploring further. # List available models > Returns all AI models available for completions. OpenAI-compatible endpoint. ## OpenAPI ````yaml /api-reference/openapi.json get /v1/models openapi: 3.1.0 info: title: NEAR AI Cloud API description: >- NEAR AI Cloud API for private AI model inference and organization administration. contact: name: NEAR AI Team email: support@near.ai license: name: MIT version: 1.0.0 servers: - url: https://cloud-api.near.ai description: NEAR AI Cloud security: - session_token: [] - api_key: [] tags: - name: Chat description: Chat completion endpoints for AI model inference - name: Images description: Image generation endpoints - name: Audio description: Audio transcription endpoints - name: Rerank description: Document reranking endpoints - name: Score description: Text similarity scoring endpoints - name: Privacy description: Privacy classification (PII span detection) endpoints - name: Models description: Public model catalog and information - name: Responses description: >- Stateless response inference (`store: false` only). Raw request/response content, response items, and history are not persisted. Clients must include any prior context in each request. Every successful Responses inference makes exactly one Chat Completions call. Only custom `function` tools are supported. They are client-managed: Cloud returns `function_call` items but never executes them; a later `store: false` request replays the individual call (the raw item from output is accepted) with its matching `function_call_output`, alongside caller-managed message history and the same function tool definitions. The minimal replay path also accepts assistant `message` text parts of type `output_text`, but not reasoning or arbitrary full `response.output` items. Server-executed tools (`web_search`, `web_context_search`, `file_search`, `code_interpreter`, `computer`, and remote `mcp`) and image-generation/editing models are rejected. The separate `POST /mcp` endpoint continues to expose its `web_search` tool independently of Responses; use `/v1/images/*` for image generation/editing. Existing completed-response gateway attestation is preserved best-effort: when the signature write succeeds, `GET /v1/signature/resp_*` retrieves signatures over SHA-256 request/response digests, never raw content. Interrupted streams create no `resp_*` attestation record or legacy disconnect fallback. Conversations, response history, and file input are rejected. - name: Organizations description: Organization management - name: Organization Members description: Organization member and invitation management - name: Workspaces description: Workspace and API key management - name: Users description: User profile and token management - name: Invitations description: Token-based invitation handling - name: Usage description: Usage tracking and billing information - name: Reporting description: Read-only customer usage reporting - name: Billing description: Billing costs endpoint (HuggingFace integration) - name: Staking Farm description: House of Stake farm credit configuration and synchronization - name: Health description: Health check endpoints - name: Attestation description: Attestation and verification endpoints - name: Gateway description: Model gateway integration endpoints - name: Admin description: Administrative endpoints (admin access required) - name: Services description: Public platform services (e.g. web_search pricing) paths: /v1/models: get: tags: - Chat summary: List available models description: >- Returns all AI models available for completions. OpenAI-compatible endpoint. operationId: models responses: '200': description: List of available models content: application/json: schema: $ref: '#/components/schemas/ModelsResponse' '500': description: Server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - {} components: schemas: ModelsResponse: type: object required: - object - data properties: data: type: array items: $ref: '#/components/schemas/ModelInfo' object: type: string ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorDetail' ModelInfo: type: object required: - id - object - created - owned_by - supported_sampling_parameters - supported_features properties: architecture: oneOf: - type: 'null' - $ref: '#/components/schemas/ModelArchitecture' description: >- Model architecture (input/output modalities), legacy nested camelCase shape. context_length: type: - integer - 'null' format: int32 description: Context length in tokens. created: type: integer format: int64 datacenters: type: - array - 'null' items: $ref: '#/components/schemas/Datacenter' description: |- Datacenters the model runs in (OpenRouter `datacenters`), e.g. `[{ "country_code": "US" }]`. Omitted when unset. deprecation_date: type: - string - 'null' description: >- OpenRouter `deprecation_date`: planned deprecation date as an ISO 8601 string. Omitted when there is no planned deprecation. description: type: - string - 'null' description: Human-readable description (OpenRouter `description`). hugging_face_id: type: - string - 'null' description: HuggingFace identifier (OpenRouter `hugging_face_id`). id: type: string input_modalities: type: - array - 'null' items: type: string description: >- OpenRouter `input_modalities`: flat snake_case duplicate of architecture.input. is_ready: type: - boolean - 'null' description: >- OpenRouter `is_ready`: `false` keeps the model hidden on OpenRouter's side, `true` enables auto-staging. Exposed verbatim; omitted when unset. max_output_length: type: - integer - 'null' format: int32 description: Maximum output tokens (OpenRouter `max_output_length`). name: type: - string - 'null' description: Human-readable model name (OpenRouter `name`). object: type: string openrouter: oneOf: - type: 'null' - $ref: '#/components/schemas/OpenRouter' description: >- OpenRouter slug override: `{ "slug": "" }`. Present only when an override is set (our `id` does not match OpenRouter's canonical slug). Omitted entirely when unset. output_modalities: type: - array - 'null' items: type: string description: >- OpenRouter `output_modalities`: flat snake_case duplicate of architecture.output. owned_by: type: string pricing: oneOf: - type: 'null' - $ref: '#/components/schemas/ModelPricing' description: Pricing information (HuggingFace + OpenRouter compatible). quantization: type: - string - 'null' description: |- Quantization label (OpenRouter `quantization`): int4/int8/fp4/fp6/fp8/fp16/bf16/fp32. supported_features: type: array items: type: string description: Feature capabilities (OpenRouter `supported_features`). supported_sampling_parameters: type: array items: type: string description: >- Sampling parameters accepted by the model (OpenRouter `supported_sampling_parameters`). top_provider: oneOf: - type: 'null' - $ref: '#/components/schemas/TopProvider' description: 'OpenRouter `top_provider`: per-provider context/output limits.' ErrorDetail: type: object required: - message - type properties: code: type: - string - 'null' message: type: string param: type: - string - 'null' type: type: string ModelArchitecture: type: object description: Model architecture describing input/output modalities required: - inputModalities - outputModalities properties: inputModalities: type: array items: type: string description: >- Input modalities the model accepts, e.g., ["text"], ["text", "image"] outputModalities: type: array items: type: string description: Output modalities the model produces, e.g., ["text"], ["image"] Datacenter: type: object description: |- OpenRouter `datacenters` entry: a single datacenter the model runs in. The provider spec (https://openrouter.ai/docs/guides/community/for-providers) models `datacenters` as an array of objects, each with an ISO 3166 Alpha-2 `country_code`. We store only the country codes (a `TEXT[]`) and reconstruct this object wrapper at serialization time. required: - country_code properties: country_code: type: string description: ISO 3166 Alpha-2 country code (e.g. "US"), uppercase. OpenRouter: type: object description: >- OpenRouter slug-override block. OpenRouter's provider spec (https://openrouter.ai/docs/guides/community/for-providers) requires the model `id` to EXACTLY match OpenRouter's canonical slug, OR for the provider to supply an explicit override via a nested `openrouter` object carrying the canonical slug. We emit this object only when an override is configured. required: - slug properties: slug: type: string description: >- OpenRouter's canonical slug for this model (lowercase `author/slug`). ModelPricing: type: object description: >- Model pricing information. `input` / `output` are the legacy HuggingFace-style fields (USD per million tokens, as floats). The remaining fields match OpenRouter's provider spec (USD per single token, serialized as strings to avoid float precision issues): https://openrouter.ai/docs/guides/community/for-providers required: - input - output - prompt - completion - image - request properties: completion: type: string description: 'OpenRouter: USD per output token, as a string.' image: type: string description: 'OpenRouter: USD per image, as a string ("0" when not applicable).' input: type: number format: double description: >- Price per million input tokens in USD (legacy field, kept for back-compat). input_cache_read: type: - string - 'null' description: >- OpenRouter: USD per cached input token, as a string. Omitted when cache-read pricing is disabled; `"0"` means cached input tokens are genuinely free. output: type: number format: double description: >- Price per million output tokens in USD (legacy field, kept for back-compat). prompt: type: string description: 'OpenRouter: USD per input token, as a string.' request: type: string description: 'OpenRouter: USD per request, as a string ("0" when not applicable).' TopProvider: type: object description: |- OpenRouter `top_provider` block: context length and max output tokens in the field names OpenRouter's `/api/v1/models` schema uses. required: - is_moderated properties: context_length: type: - integer - 'null' format: int32 description: Context length in tokens (mirrors top-level `context_length`). is_moderated: type: boolean description: >- Whether the provider moderates content. We do not, so this is always false. max_completion_tokens: type: - integer - 'null' format: int32 description: >- Maximum output tokens per response (mirrors top-level `max_output_length`). securitySchemes: session_token: type: http scheme: bearer bearerFormat: JWT description: >- JWT access token for user authentication (Authorization: Bearer ). Create via POST /users/me/access_tokens. api_key: type: http scheme: bearer bearerFormat: api_key description: 'API key for programmatic access (Authorization: Bearer sk-)' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.