> ## 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. # Batch upsert models metadata (Admin only) > Upserts (inserts or updates) pricing and metadata for one or more models. Only authenticated admins can perform this operation. The body should be an array of objects where each key is a model name and the value is the model data. ## OpenAPI ````yaml /api-reference/openapi.json patch /v1/admin/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/admin/models: patch: tags: - Admin summary: Batch upsert models metadata (Admin only) description: >- Upserts (inserts or updates) pricing and metadata for one or more models. Only authenticated admins can perform this operation. The body should be an array of objects where each key is a model name and the value is the model data. operationId: batch_upsert_models requestBody: content: application/json: schema: $ref: '#/components/schemas/HashMap' required: true responses: '200': description: Models upserted successfully content: application/json: schema: type: array items: $ref: '#/components/schemas/ModelWithPricing' '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - session_token: [] components: schemas: HashMap: type: object additionalProperties: type: object description: Request to update model pricing (admin endpoint) properties: aliases: type: - array - 'null' items: type: string allowFree: type: - boolean - 'null' description: >- If true, this model may be activated even when both cost fields are 0. Required to be set explicitly when activating a zero-price model. attestationSupported: type: - boolean - 'null' description: Whether this model supports TEE attestation cacheReadCostPerToken: oneOf: - type: 'null' - $ref: '#/components/schemas/DecimalPriceRequest' description: >- Cost per cached input token. Tri-state PATCH semantics: - omitted → leave unchanged - `null` → disable cache pricing (cached tokens billed at the full input rate; `cacheReadCostPerToken` / `input_cache_read` omitted from catalog responses) - a price → set verbatim (an amount of 0 = genuinely free cache reads) changeReason: type: - string - 'null' contextLength: type: - integer - 'null' format: int32 costPerImage: oneOf: - type: 'null' - $ref: '#/components/schemas/DecimalPriceRequest' datacenters: type: - array - 'null' items: $ref: '#/components/schemas/Datacenter' description: |- Datacenters the model runs in (OpenRouter `datacenters`), as `[{ "country_code": "US" }]`. Country codes must be 2-letter uppercase ISO 3166 Alpha-2. deprecationDate: type: - string - 'null' description: >- OpenRouter `deprecation_date`: ISO 8601 string (`YYYY-MM-DD` or `YYYY-MM-DDTHH:00:00Z`). Validated at the write path; rejected if it does not parse. Tri-state PATCH semantics: - omitted → leave unchanged - `null` → clear back to "no planned deprecation" (column set to NULL) - a string → set to the normalized deprecation timestamp huggingFaceId: type: - string - 'null' description: >- HuggingFace identifier (required by OpenRouter when the model is on HF). inferenceUrl: type: - string - 'null' description: Base URL for the model's inference endpoint inputCostPerToken: oneOf: - type: 'null' - $ref: '#/components/schemas/DecimalPriceRequest' inputModalities: type: - array - 'null' items: type: string description: >- Input modalities the model accepts, e.g., ["text"], ["text", "image"] isActive: type: - boolean - 'null' isReady: type: - boolean - 'null' description: >- OpenRouter `is_ready`. Stored and exposed verbatim on `GET /v1/models`. Tri-state PATCH semantics: - omitted → leave unchanged - `null` → clear back to "unset" (column set to NULL) - `true`/`false` → set verbatim maxOutputLength: type: - integer - 'null' format: int32 description: >- Maximum number of output tokens the model can produce in a single response. modelDescription: type: - string - 'null' modelDisplayName: type: - string - 'null' modelIcon: type: - string - 'null' openrouterSlug: type: - string - 'null' description: >- OpenRouter `openrouter.slug` override (lowercase `author/slug`, e.g. `z-ai/glm-5.1`). Set when our canonical `model_name` does not match OpenRouter's slug; surfaced as the nested `openrouter: { slug }` object on `GET /v1/models`. Validated at the write path; rejected if it does not match the `author/slug` shape. Tri-state PATCH semantics: - omitted → leave unchanged - `null` → clear back to "unset" (column set to NULL) - a string → set verbatim outputCostPerToken: oneOf: - type: 'null' - $ref: '#/components/schemas/DecimalPriceRequest' outputModalities: type: - array - 'null' items: type: string description: Output modalities the model produces, e.g., ["text"], ["image"] ownedBy: type: - string - 'null' providerConfig: description: JSON config for external providers (backend, base_url, etc.) providerType: type: - string - 'null' description: >- Provider type: "vllm" (default, TEE-enabled) or "external" (3rd party) quantization: type: - string - 'null' description: Quantization label (int4/int8/fp4/fp6/fp8/fp16/bf16/fp32). supportedFeatures: type: - array - 'null' items: type: string description: Feature capabilities (OpenRouter vocabulary). supportedSamplingParameters: type: - array - 'null' items: type: string description: Sampling parameters accepted by the model (OpenRouter vocabulary). verifiable: type: - boolean - 'null' propertyNames: type: string ModelWithPricing: type: object description: Model with pricing information required: - modelId - inputCostPerToken - outputCostPerToken - costPerImage - metadata properties: cacheReadCostPerToken: oneOf: - type: 'null' - $ref: '#/components/schemas/DecimalPrice' description: >- Cost per cached input token. Omitted when cache pricing is disabled; an amount of 0 means cached tokens are genuinely free. costPerImage: $ref: '#/components/schemas/DecimalPrice' inputCostPerToken: $ref: '#/components/schemas/DecimalPrice' metadata: $ref: '#/components/schemas/ModelMetadata' modelId: type: string outputCostPerToken: $ref: '#/components/schemas/DecimalPrice' ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorDetail' DecimalPriceRequest: type: object description: >- Decimal price for API requests The system internally uses a fixed scale of 9 (nano-dollars = 1 billionth of a dollar). Clients must provide amounts in nano-dollars. Examples: $100.00 USD: amount=100000000000, currency="USD" $1.00 USD: amount=1000000000, currency="USD" $0.01 USD: amount=10000000, currency="USD" required: - amount - currency properties: amount: type: integer format: int64 description: >- Amount in nano-dollars (scale 9). For example, $1.00 = 1000000000 nano-dollars. currency: type: string 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. DecimalPrice: type: object description: >- Decimal price for API responses The system uses a fixed scale of 9 (nano-dollars = 1 billionth of a dollar). The scale field is included in responses for client convenience. required: - amount - scale - currency properties: amount: type: integer format: int64 currency: type: string scale: type: integer format: int64 ModelMetadata: type: object description: Model metadata required: - verifiable - contextLength - modelDisplayName - modelDescription - ownedBy - providerType - attestationSupported properties: aliases: type: array items: type: string architecture: oneOf: - type: 'null' - $ref: '#/components/schemas/ModelArchitecture' description: Model architecture (input/output modalities) attestationSupported: type: boolean description: Whether this model supports TEE attestation contextLength: type: integer format: int32 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. deprecationDate: type: - string - 'null' description: >- OpenRouter `deprecation_date`: planned deprecation date as an ISO 8601 string. Omitted when there is no planned deprecation. huggingFaceId: type: - string - 'null' description: HuggingFace identifier (OpenRouter `hugging_face_id`). inferenceUrl: type: - string - 'null' description: Base URL for the model's inference endpoint isReady: type: - boolean - 'null' description: 'OpenRouter `is_ready`: stored/exposed verbatim. Omitted when unset.' maxOutputLength: type: - integer - 'null' format: int32 description: Maximum output tokens per response (OpenRouter `max_output_length`). modelDescription: type: string modelDisplayName: type: string modelIcon: type: - string - 'null' openrouterSlug: type: - string - 'null' description: >- OpenRouter `openrouter.slug` override (lowercase `author/slug`). Omitted when unset. On public `GET /v1/models` this surfaces as the nested `openrouter: { slug }` object; the admin view exposes the raw value. ownedBy: type: string providerConfig: description: JSON config for external providers (backend, base_url, etc.) providerType: type: string description: 'Provider type: "vllm" (TEE-enabled) or "external" (3rd party)' quantization: type: - string - 'null' description: Quantization label (int4/int8/fp4/fp6/fp8/fp16/bf16/fp32). supportedFeatures: type: array items: type: string description: Feature capabilities (OpenRouter `supported_features`). supportedSamplingParameters: type: array items: type: string description: >- Sampling parameters accepted by the model (OpenRouter `supported_sampling_parameters`). verifiable: type: boolean 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"] 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.