> ## Documentation Index > Fetch the complete documentation index at: https://docs.omniall.ai/llms.txt > Use this file to discover all available pages before exploring further. # Claude Messages > Anthropic Messages API relayed by Omniall AI. **Base path:** `POST https://api.omniall.ai/v1/messages` Send `anthropic-version` (recommended: `2023-06-01`). Auth via `Authorization: Bearer sk-...` or `x-api-key`. ### Scenarios - **Vision**: image content blocks - **Documents**: `document` blocks (PDF) - **Web search**: server tool `web_search_*` when enabled for the model/channel - **Agent**: Claude `tools` + `tool_choice` - **Thinking**: `thinking: { type: enabled, budget_tokens }` Official reference: https://docs.anthropic.com/en/api/messages ## OpenAPI ````yaml openapi/xgapi-public.yaml POST /v1/messages openapi: 3.0.3 info: title: Omniall AI Public API description: >- Omniall AI public API. Website: https://omniall.ai — API host: https://api.omniall.ai — Model Square: https://omniall.ai/pricing version: 1.1.0 servers: - url: https://api.omniall.ai description: Production security: - bearerAuth: [] tags: - name: Models description: List models available to your API key. - name: ChatGPT Chat Completions x-group: ChatGPT description: OpenAI Chat Completions (`POST /v1/chat/completions`). - name: Responses description: OpenAI Responses API (`POST /v1/responses`). - name: Claude description: Anthropic Messages API (`POST /v1/messages`). - name: Gemini description: Google Gemini generateContent / streamGenerateContent. - name: Images description: >- Image generation (OpenAI Images), vendor guides, and Midjourney proxy APIs. - name: Video description: Async video tasks. - name: Audio description: Speech and related audio APIs. - name: Rerank description: Document reranking. paths: /v1/messages: post: tags: - Claude summary: Claude Messages description: > Anthropic Messages API relayed by Omniall AI. **Base path:** `POST https://api.omniall.ai/v1/messages` Send `anthropic-version` (recommended: `2023-06-01`). Auth via `Authorization: Bearer sk-...` or `x-api-key`. ### Scenarios - **Vision**: image content blocks - **Documents**: `document` blocks (PDF) - **Web search**: server tool `web_search_*` when enabled for the model/channel - **Agent**: Claude `tools` + `tool_choice` - **Thinking**: `thinking: { type: enabled, budget_tokens }` Official reference: https://docs.anthropic.com/en/api/messages operationId: createMessage parameters: - name: anthropic-version in: header required: true schema: type: string example: '2023-06-01' description: Anthropic API version header. - name: x-api-key in: header required: false schema: type: string description: Optional Anthropic-style key (also accepted as Bearer). requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ClaudeRequest' examples: basic: summary: Basic Messages value: model: claude-sonnet-4 max_tokens: 1024 messages: - role: user content: Hello, Claude vision: summary: Image understanding value: model: claude-sonnet-4 max_tokens: 1024 messages: - role: user content: - type: image source: type: url url: https://example.com/photo.jpg - type: text text: Describe this image document: summary: PDF / document analysis value: model: claude-sonnet-4 max_tokens: 2048 messages: - role: user content: - type: document source: type: base64 media_type: application/pdf data: JVBERi0xLjQ... - type: text text: Summarize the document web_search: summary: Web search tool (server tool) value: model: claude-sonnet-4 max_tokens: 2048 tools: - type: web_search_20250305 name: web_search max_uses: 5 messages: - role: user content: What happened in AI regulation this week? agent: summary: Agent / tool use value: model: claude-sonnet-4 max_tokens: 1024 tools: - name: get_stock_price description: Get stock price input_schema: type: object properties: symbol: type: string required: - symbol messages: - role: user content: Price of AAPL? thinking: summary: Extended thinking value: model: claude-sonnet-4 max_tokens: 16000 thinking: type: enabled budget_tokens: 10000 messages: - role: user content: 'Solve this step by step: ...' responses: '200': description: Claude message response (or SSE stream). content: application/json: schema: $ref: '#/components/schemas/ClaudeResponse' '400': description: Invalid request body or unsupported parameter for the model. content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' example: error: message: '无效的令牌 (request id: ...)' type: new_api_error code: '' '403': description: Forbidden (banned user, IP allowlist, group access). content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' '429': description: Rate limited. content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' '500': description: Upstream or gateway internal error. content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' components: schemas: ClaudeRequest: type: object required: - model - messages - max_tokens description: >- Anthropic Messages request (`POST /v1/messages`). `model`, `messages`, and `max_tokens` are required. properties: model: type: string example: claude-sonnet-4 description: Claude model id from Model Square. messages: type: array description: >- Conversation turns with roles `user` / `assistant`. Content may be a string or content blocks (text, image, document, tool_use, tool_result). items: type: object required: - role - content properties: role: type: string enum: - user - assistant content: oneOf: - type: string - type: array items: type: object additionalProperties: true system: description: System prompt (string or content blocks). Sets overall behavior. oneOf: - type: string - type: array items: type: object additionalProperties: true max_tokens: type: integer minimum: 1 description: >- Maximum tokens Claude may generate. Required by Anthropic; also acts as a cost/latency control. temperature: type: number minimum: 0 maximum: 1 description: Randomness (0–1 for Claude). top_p: type: number description: Nucleus sampling. top_k: type: integer description: Top-K sampling. stream: type: boolean description: If true, stream SSE events. stop_sequences: type: array items: type: string description: Custom stop strings. tools: description: >- Claude tools: custom tools and/or server tools such as web_search when enabled for the model/channel. type: array items: type: object additionalProperties: true tool_choice: type: object properties: type: type: string enum: - auto - any - tool - none description: '`auto` / `any` / `tool` / `none`.' name: type: string description: Tool name when `type` is `tool`. disable_parallel_tool_use: type: boolean description: Disallow parallel tool calls when true. description: Tool selection policy. thinking: type: object properties: type: type: string enum: - enabled - disabled description: '`enabled` or `disabled`.' budget_tokens: type: integer description: >- Max tokens reserved for thinking when enabled (must be less than `max_tokens`). description: Extended thinking controls. mcp_servers: type: array items: type: object additionalProperties: true description: MCP server definitions when using Claude MCP features. metadata: type: object additionalProperties: true description: Request metadata passthrough. context_management: type: object additionalProperties: true description: Context management options (provider-specific). output_config: type: object additionalProperties: true description: Output configuration (e.g. effort), when supported. output_format: type: object additionalProperties: true description: Structured output format controls. cache_control: type: object additionalProperties: true description: Prompt caching controls when supported. ClaudeResponse: type: object properties: id: type: string description: Message id. type: type: string example: message description: Usually `message`. role: type: string example: assistant description: Usually `assistant`. model: type: string description: Model used. content: type: array items: type: object properties: type: type: string text: type: string name: type: string input: type: object additionalProperties: true description: >- Content blocks (`text`, `tool_use`, etc.). Concatenate text blocks for the visible answer. stop_reason: type: string enum: - end_turn - max_tokens - stop_sequence - tool_use description: >- Why Claude stopped: `end_turn`, `max_tokens`, `stop_sequence`, `tool_use`, etc. usage: type: object properties: input_tokens: type: integer description: Input tokens. output_tokens: type: integer description: Output tokens. description: Token usage. description: Anthropic Messages response. OpenAIErrorResponse: type: object description: OpenAI-style error envelope returned on auth/request failures. required: - error properties: error: type: object required: - message - type properties: message: type: string description: >- Human-readable error. The gateway may append a request id for support. type: type: string description: Error type, commonly `new_api_error`. example: new_api_error code: type: string description: >- Optional machine-readable code (e.g. `access_denied`). May be an empty string. description: Error object. securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Use Authorization: Bearer sk-... from https://omniall.ai/dashboard' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.