> ## 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. # Document reranking endpoint > Ranks documents by relevance to a query using a reranker model. **Concurrent Request Limits:** Each organization has a per-model concurrent request limit (default: 64). When the limit is reached, new requests will fail with 429 status code. Wait for in-flight requests to complete before retrying. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/rerank 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/rerank: post: tags: - Rerank summary: Document reranking endpoint description: >- Ranks documents by relevance to a query using a reranker model. **Concurrent Request Limits:** Each organization has a per-model concurrent request limit (default: 64). When the limit is reached, new requests will fail with 429 status code. Wait for in-flight requests to complete before retrying. operationId: rerank requestBody: content: application/json: schema: $ref: '#/components/schemas/RerankRequest' required: true responses: '200': description: Successful rerank content: application/json: schema: $ref: '#/components/schemas/RerankResponse' '400': description: Invalid request (empty documents, invalid model, etc.) content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized (missing or invalid API key) content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Model not found content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: >- Rate limited or overloaded — retry with backoff. Check error.type: rate_limit_exceeded or service_overloaded. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Server error (billing failure, provider error) content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - ApiKeyAuth: [] components: schemas: RerankRequest: type: object description: Request for document reranking required: - model - query - documents properties: documents: type: array items: type: string description: Documents to rerank model: type: string description: Model ID to use for reranking query: type: string description: Query to rerank documents against return_documents: type: - boolean - 'null' description: Whether to include document text in each result. Defaults to true. top_n: type: - integer - 'null' description: Maximum number of ranked results to return minimum: 0 RerankResponse: type: object description: Response from document reranking required: - id - model - results properties: id: type: string description: Unique identifier for the rerank request model: type: string description: Model used for reranking results: type: array items: $ref: '#/components/schemas/RerankResult' description: Reranked results usage: oneOf: - type: 'null' - $ref: '#/components/schemas/RerankUsage' description: Usage information (optional) ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorDetail' RerankResult: type: object description: Individual reranked result required: - index - relevance_score properties: document: description: The document (can be string or object depending on provider) index: type: integer format: int32 description: Index of the document in the original input relevance_score: type: number format: double description: Relevance score (typically 0.0 to 1.0) RerankUsage: type: object description: Usage information for rerank request properties: prompt_tokens: type: - integer - 'null' format: int32 description: Input tokens total_tokens: type: - integer - 'null' format: int32 description: Total number of tokens used ErrorDetail: type: object required: - message - type properties: code: type: - string - 'null' message: type: string param: type: - string - 'null' type: type: string 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.