> ## Documentation Index > Fetch the complete documentation index at: https://docs.antarah.dev/llms.txt > Use this file to discover all available pages before exploring further. # Create a message ## OpenAPI ````yaml POST /v1/messages openapi: 3.1.0 info: title: Antara API version: 1.0.0 description: OpenAI- and Anthropic-compatible inference plus organization management. servers: - url: https://api.antarah.dev security: [] paths: /v1/messages: post: summary: >- Create a message (Anthropic Messages, translated to the upstream's Chat Completions); `stream: true` answers with server-sent events requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/MessageRequest' responses: '200': description: >- `application/json` when `stream` is false; otherwise `text/event-stream`: `event: ` + `data: `, ending with `message_stop` headers: x-request-id: schema: type: string description: Request ID (`req_…`); also sent as `request-id` required: false description: Request ID (`req_…`); also sent as `request-id` ratelimit-policy: schema: type: string description: e.g. `"rpm";q=60;w=60` (02 §8) required: false description: e.g. `"rpm";q=60;w=60` (02 §8) ratelimit: schema: type: string description: Scope closest to exhaustion, e.g. `"rpm";r=59;t=42` required: false description: Scope closest to exhaustion, e.g. `"rpm";r=59;t=42` x-ratelimit-limit-requests: schema: type: string description: RPM of the scope closest to exhaustion required: false description: RPM of the scope closest to exhaustion x-ratelimit-remaining-requests: schema: type: string description: Requests left in the window required: false description: Requests left in the window x-ratelimit-reset-requests: schema: type: string description: Duration, e.g. `"1s"`, `"6m0s"` required: false description: Duration, e.g. `"1s"`, `"6m0s"` x-ratelimit-limit-tokens: schema: type: string description: TPM of the scope closest to exhaustion required: false description: TPM of the scope closest to exhaustion x-ratelimit-remaining-tokens: schema: type: string description: Tokens left in the window required: false description: Tokens left in the window x-ratelimit-reset-tokens: schema: type: string description: Duration required: false description: Duration x-antara-policy-action: schema: type: string description: >- `blocked` when an enforcing policy refused before the headers were sent (02 §9.7) required: false description: >- `blocked` when an enforcing policy refused before the headers were sent (02 §9.7) deprecation: schema: type: string description: 'Deprecated model: `@` (RFC 9745)' required: false description: 'Deprecated model: `@` (RFC 9745)' sunset: schema: type: string description: 'Deprecated model: HTTP-date (RFC 8594)' required: false description: 'Deprecated model: HTTP-date (RFC 8594)' link: schema: type: string description: 'Deprecated model: `; rel="deprecation"`' required: false description: 'Deprecated model: `; rel="deprecation"`' content: application/json: schema: $ref: '#/components/schemas/Message' text/event-stream: schema: $ref: '#/components/schemas/MessageStreamEvent' '400': description: '`context_length_exceeded`, `unknown_policy`' content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '402': description: '`insufficient_credits`, `spend_limit_reached`' content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '502': description: '`upstream_error`' content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '503': description: '`upstream_unavailable`, `policy_evaluation_unavailable`' content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '504': description: '`upstream_timeout`' content: application/json: schema: $ref: '#/components/schemas/AnthropicError' default: description: Anthropic-shaped error (02 §4.1) content: application/json: schema: $ref: '#/components/schemas/AnthropicError' security: - projectKey: [] - session: [] components: schemas: MessageRequest: type: object properties: model: type: string minLength: 1 description: Public model ID, e.g. `a1` (A-05) example: a1 messages: type: array items: oneOf: - type: object properties: role: type: string enum: - user content: anyOf: - type: string - type: array items: oneOf: - type: object properties: type: type: string enum: - text text: type: string minLength: 1 required: - type - text - type: object properties: type: type: string enum: - image source: oneOf: - type: object properties: type: type: string enum: - base64 media_type: type: string enum: - image/png - image/jpeg - image/webp - image/gif data: type: string required: - type - media_type - data - type: object properties: type: type: string enum: - url url: type: string required: - type - url required: - type - source - type: object properties: type: type: string enum: - tool_result tool_use_id: type: string minLength: 1 content: anyOf: - type: string - type: array items: oneOf: - type: object properties: type: type: string enum: - text text: type: string minLength: 1 required: - type - text - type: object properties: type: type: string enum: - image source: oneOf: - type: object properties: type: type: string enum: - base64 media_type: type: string enum: - image/png - image/jpeg - image/webp - image/gif data: type: string required: - type - media_type - data - type: object properties: type: type: string enum: - url url: type: string required: - type - url required: - type - source is_error: type: boolean required: - type - tool_use_id - type: object properties: type: type: string enum: - document required: - type - type: object properties: type: type: string enum: - search_result required: - type minItems: 1 required: - role - content - type: object properties: role: type: string enum: - assistant content: anyOf: - type: string - type: array items: oneOf: - type: object properties: type: type: string enum: - text text: type: string minLength: 1 required: - type - text - type: object properties: type: type: string enum: - tool_use id: type: string minLength: 1 name: type: string minLength: 1 input: type: object additionalProperties: {} required: - type - id - name - input - type: object properties: type: type: string enum: - thinking thinking: type: string signature: type: string required: - type - thinking - type: object properties: type: type: string enum: - redacted_thinking data: type: string required: - type - data required: - role - content minItems: 1 maxItems: 10000 system: anyOf: - type: string - type: array items: type: object properties: type: type: string enum: - text text: type: string minLength: 1 required: - type - text tools: type: array items: type: object properties: type: type: string name: type: string minLength: 1 description: type: string input_schema: type: object additionalProperties: {} required: - name maxItems: 128 max_tokens: type: integer minimum: 1 description: Required. 1…the model's `max_output_tokens` temperature: type: number minimum: 0 maximum: 1 description: 0–1 (Anthropic's range) top_p: type: number minimum: 0 maximum: 1 stop_sequences: type: array items: type: string maxItems: 4 tool_choice: oneOf: - type: object properties: type: type: string enum: - auto disable_parallel_tool_use: type: boolean required: - type - type: object properties: type: type: string enum: - any disable_parallel_tool_use: type: boolean required: - type - type: object properties: type: type: string enum: - none required: - type - type: object properties: type: type: string enum: - tool name: type: string minLength: 1 disable_parallel_tool_use: type: boolean required: - type - name thinking: anyOf: - type: boolean enum: - false - type: object properties: type: type: string enum: - enabled budget_tokens: type: integer minimum: 1 required: - type - budget_tokens - type: object properties: type: type: string enum: - disabled required: - type description: >- `budget_tokens` maps to a reasoning effort; `output_config.effort` wins output_config: type: object properties: effort: type: string enum: - none - minimal - low - medium - high - xhigh - max format: type: object properties: type: type: string enum: - json_schema schema: type: object additionalProperties: {} required: - type - schema description: >- Structured output → Chat `response_format: {type:"json_schema", json_schema:{name:"output", schema, strict:true}}` top_k: type: integer description: 'Rejected: `400 unsupported_parameter`' stream: type: boolean description: Default `false` include_reasoning: type: boolean description: '`false` drops `thinking` blocks from the output' policy_ids: type: - array - 'null' items: type: string minLength: 1 maxLength: 120 maxItems: 20 description: 'Antara extension: published policies to add for this request' metadata: type: object properties: user_id: type: - string - 'null' service_tier: type: string context_management: {} required: - model - messages - max_tokens additionalProperties: false description: >- Rejected with `400 unsupported_parameter`: `top_k`, server tools, `document` blocks, `container`, `mcp_servers`, and any field not listed here. Message: type: object properties: id: type: string pattern: ^msg_[0-9a-f]{32}$ example: msg_0193a6c2e7b47c3d9f1e2a4b5c6d7e8f type: type: string enum: - message role: type: string enum: - assistant model: type: string example: a1 content: type: array items: oneOf: - type: object properties: type: type: string enum: - thinking thinking: type: string signature: type: string enum: - '' required: - type - thinking - signature - type: object properties: type: type: string enum: - text text: type: string required: - type - text - type: object properties: type: type: string enum: - tool_use id: type: string name: type: string input: type: object additionalProperties: {} required: - type - id - name - input stop_reason: type: - string - 'null' enum: - end_turn - max_tokens - stop_sequence - tool_use - refusal - null stop_sequence: type: - string - 'null' usage: $ref: '#/components/schemas/MessageUsage' required: - id - type - role - model - content - stop_reason - stop_sequence - usage MessageStreamEvent: oneOf: - type: object properties: type: type: string enum: - message_start message: allOf: - $ref: '#/components/schemas/Message' - type: object properties: content: type: array items: {} maxItems: 0 stop_reason: type: 'null' required: - type - message - type: object properties: type: type: string enum: - content_block_start index: type: integer content_block: oneOf: - type: object properties: type: type: string enum: - thinking thinking: type: string enum: - '' signature: type: string enum: - '' required: - type - thinking - signature - type: object properties: type: type: string enum: - text text: type: string enum: - '' required: - type - text - type: object properties: type: type: string enum: - tool_use id: type: string name: type: string input: type: object properties: {} required: - type - id - name - input required: - type - index - content_block - type: object properties: type: type: string enum: - content_block_delta index: type: integer delta: oneOf: - type: object properties: type: type: string enum: - thinking_delta thinking: type: string required: - type - thinking - type: object properties: type: type: string enum: - text_delta text: type: string required: - type - text - type: object properties: type: type: string enum: - input_json_delta partial_json: type: string required: - type - partial_json required: - type - index - delta - type: object properties: type: type: string enum: - content_block_stop index: type: integer required: - type - index - type: object properties: type: type: string enum: - message_delta delta: type: object properties: stop_reason: type: - string - 'null' enum: - end_turn - max_tokens - stop_sequence - tool_use - refusal - null stop_sequence: type: - string - 'null' required: - stop_reason - stop_sequence usage: $ref: '#/components/schemas/MessageUsage' required: - type - delta - usage - type: object properties: type: type: string enum: - message_stop required: - type - type: object properties: type: type: string enum: - ping required: - type - type: object properties: type: type: string enum: - error error: type: object properties: type: type: string example: invalid_request_error message: type: string code: type: string required: - type - message - code request_id: type: string required: - type - error AnthropicError: type: object properties: type: type: string enum: - error error: type: object properties: type: type: string example: invalid_request_error message: type: string code: type: string required: - type - message - code request_id: type: string required: - type - error - request_id MessageUsage: type: object properties: input_tokens: type: integer description: Excludes cache reads (Anthropic's convention) output_tokens: type: integer cache_read_input_tokens: type: integer required: - input_tokens - output_tokens - cache_read_input_tokens securitySchemes: projectKey: type: http scheme: bearer description: '`ak_…` project API key (or `x-api-key`)' session: type: http scheme: bearer bearerFormat: JWT description: >- Supabase access token + `Antara-Organization` (management) or `Antara-Project` (inference) ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.