> ## Documentation Index > Fetch the complete documentation index at: https://docs.apiany.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create chat completion > OpenAI-compatible chat completion endpoint. Streaming support is reserved for a future capability. ## OpenAPI ````yaml /openapi.json post /v1/chat/completions openapi: 3.1.0 info: title: APIAny.AI Public API version: 1.0.0 description: >- Public API for APIAny.AI model aggregation, async media tasks, chat completions, billing visibility, and task lookup. servers: - url: https://apiany.ai description: Production security: - bearerAuth: [] tags: - name: Models description: Public model catalog. - name: Chat description: Text generation and chat-compatible endpoints. - name: Images description: Image generation and editing endpoints. - name: Videos description: Video generation endpoints. - name: Moderation description: Image safety and moderation endpoints. - name: Tasks description: Async task lookup. - name: Account description: Account and credit visibility. - name: Free APIs description: Free utility APIs protected by API key rate limits. paths: /v1/chat/completions: post: tags: - Chat summary: Create chat completion description: >- OpenAI-compatible chat completion endpoint. Streaming support is reserved for a future capability. operationId: createChatCompletion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' examples: basic: value: model: gpt-5.4 messages: - role: user content: Write a concise product tagline for APIAny.AI. temperature: 0.7 responses: '200': description: OpenAI-compatible chat completion. content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/RateLimited' components: schemas: ChatCompletionRequest: type: object properties: model: type: string example: gpt-5.4 messages: type: array items: $ref: '#/components/schemas/ChatMessage' temperature: type: number minimum: 0 maximum: 2 description: Sampling temperature. top_p: type: number minimum: 0 maximum: 1 description: Nucleus sampling probability mass. max_tokens: type: integer minimum: 1 deprecated: true description: >- Deprecated compatibility alias for max_completion_tokens. APIAny converts it only when the selected model route requires the newer field. max_completion_tokens: type: integer minimum: 1 maximum: 1048576 description: >- Maximum reasoning plus final-answer tokens. Kimi K3 defaults to 131072 when omitted and supports up to 1048576. reasoning_effort: type: string enum: - max description: >- Kimi K3 reasoning effort. K3 always reasons and currently supports only max. stop: oneOf: - type: string - type: array items: type: string description: Up to 4 stop sequences. 'n': type: integer minimum: 1 description: Number of completions to generate. frequency_penalty: type: number minimum: -2 maximum: 2 presence_penalty: type: number minimum: -2 maximum: 2 seed: type: integer description: Best-effort deterministic sampling seed. response_format: type: object description: >- Force JSON object or JSON-schema output, e.g. { "type": "json_object" }. additionalProperties: true tools: type: array description: Tool / function declarations the model may call. items: type: object additionalProperties: true tool_choice: description: >- Tool selection: 'auto' | 'none' | 'required' | { type: 'function', function: { name } }. oneOf: - type: string - type: object additionalProperties: true logprobs: type: boolean top_logprobs: type: integer minimum: 0 maximum: 20 logit_bias: type: object additionalProperties: true user: type: string description: End-user identifier for abuse monitoring. stream: type: boolean description: >- If true, partial deltas are streamed as server-sent events (OpenAI chat.completion.chunk), terminated by 'data: [DONE]'. required: - model - messages ChatCompletionResponse: type: object properties: id: type: string object: type: string example: chat.completion created: type: integer model: type: string choices: type: array items: type: object additionalProperties: true usage: $ref: '#/components/schemas/TokenUsage' required: - id - object - created - model - choices ChatMessage: type: object properties: role: type: string enum: - system - user - assistant - tool content: oneOf: - type: string - type: array items: type: object additionalProperties: true reasoning_content: type: string description: >- Reasoning trace returned by supported thinking models. Preserve it in Kimi K3 assistant-message history. partial: type: boolean default: false description: >- Kimi partial mode. Set true only on the final assistant prefix message. tools: type: array description: >- Kimi K3 dynamic tool declarations carried by a content-less system message. items: type: object additionalProperties: true required: - role TokenUsage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer input_tokens: type: integer output_tokens: type: integer cached_input_tokens: type: integer additionalProperties: true ErrorResponse: type: object properties: error: type: object properties: type: type: string enum: - invalid_request - auth_error - rate_limit - insufficient_quota - content_policy - timeout - network_error - service_error - billable_error - unknown message: type: string param: type: - string - 'null' code: type: - string - 'null' required: - type - message required: - error responses: BadRequest: description: Invalid request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' Unauthorized: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' RateLimited: description: Rate limit exceeded. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API key ````