> ## Documentation Index > Fetch the complete documentation index at: https://docs.aihubmax.com/llms.txt > Use this file to discover all available pages before exploring further. # Claude Format - Messages > - Generic Anthropic Messages API reference for all compatible models - Minimal parameters for quick start - Send structured input message lists containing text content - System prompts: customize AI role and behavior - Supports streaming and non-streaming responses ## OpenAPI ````yaml openapi/en/claude-format-messages.json POST /v1/messages openapi: 3.1.0 info: title: Claude Format - Messages version: '1.0' servers: - url: https://api.aihubmax.com security: - BearerAuth: [] paths: /v1/messages: post: tags: - Text Series > Claude Format summary: Claude Format - Messages description: | - Generic Anthropic Messages API reference for all compatible models - Minimal parameters for quick start - Send structured input message lists containing text content - System prompts: customize AI role and behavior - Supports streaming and non-streaming responses operationId: claude-format-messages requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ClaudeMessagesRequest' examples: single-turn: summary: Single Turn description: Basic single-turn Q&A value: model: claude-sonnet-4-6 max_tokens: 1024 messages: - role: user content: >- Compare the main differences between PostgreSQL and MySQL multi-turn: summary: Multi-turn description: With system prompt and multi-turn context value: model: claude-sonnet-4-6 max_tokens: 2048 system: >- You are an experienced product manager, skilled in user needs analysis and product design messages: - role: user content: >- Our SaaS product has only 30% user retention. How can we improve it? - role: assistant content: >- 30% retention is indeed low. I need more details to give targeted advice: 1. Is this 7-day or 30-day retention? 2. At which stage are users dropping off? 3. Have you conducted user interviews or surveys? - role: user content: >- It's 30-day retention. Users mainly drop off on day 3 after sign-up. We haven't done user research yet streaming: summary: Streaming description: Enable streaming for real-time content generation value: model: claude-sonnet-4-6 max_tokens: 4096 messages: - role: user content: >- Write a technical blog post about the pros and cons of microservices architecture stream: true with-image: summary: With Image description: Send an image for model analysis (vision) value: model: claude-sonnet-4-6 max_tokens: 1024 messages: - role: user content: - type: text text: What improvements can be made to this UI design? - type: image source: type: url url: >- https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg with-pdf: summary: With File (PDF) description: Send a PDF file for document analysis value: model: claude-sonnet-4-6 max_tokens: 4096 messages: - role: user content: - type: text text: >- Please summarize the core content of this document and extract key points - type: document source: type: url url: https://example.com/report.pdf responses: '200': $ref: '#/components/responses/ClaudeMessagesSuccess' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/PaymentRequired' '403': $ref: '#/components/responses/Forbidden' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: ClaudeMessagesRequest: type: object required: - model - messages - max_tokens properties: model: type: string description: Model name, e.g. claude-sonnet-4-6 example: claude-sonnet-4-6 messages: type: array description: List of messages in the conversation items: type: object required: - role - content properties: role: type: string description: Role of the message sender enum: - user - assistant content: type: string description: Content of the message (string or array of content blocks) max_tokens: type: integer description: Maximum number of tokens to generate (required) system: oneOf: - type: string description: System prompt as a string - type: array description: System prompt as an array of content blocks items: type: object properties: type: type: string enum: - text text: type: string description: System prompt temperature: type: number description: Sampling temperature (0-1) minimum: 0 maximum: 1 top_p: type: number description: Nucleus sampling parameter (0-1) minimum: 0 maximum: 1 top_k: type: integer description: Top-K sampling parameter stream: type: boolean description: Whether to stream the response default: false stop_sequences: type: array description: Custom stop sequences that will cause the model to stop generating items: type: string tools: type: array description: List of tools the model may use items: type: object properties: name: type: string description: Tool name description: type: string description: Tool description input_schema: type: object description: JSON Schema for the tool input tool_choice: type: object description: How the model should use the provided tools properties: type: type: string description: Tool choice type enum: - auto - any - tool name: type: string description: Tool name (when type is 'tool') metadata: type: object description: Request metadata properties: user_id: type: string description: External user ID for abuse detection ClaudeMessagesResponse: type: object properties: id: type: string description: Unique message ID example: msg_abc123 type: type: string description: Object type enum: - message role: type: string description: Role enum: - assistant content: type: array description: Response content blocks items: type: object properties: type: type: string enum: - text text: type: string example: Hello! How can I help you today? model: type: string description: Model used stop_reason: type: string description: Reason the generation stopped enum: - end_turn - max_tokens - stop_sequence - tool_use example: end_turn usage: type: object description: Token usage statistics properties: input_tokens: type: integer description: Number of input tokens example: 25 output_tokens: type: integer description: Number of output tokens example: 150 ErrorResponse400: type: object properties: error: type: object properties: message: type: string example: Invalid request parameters type: type: string example: invalid_request_error ErrorResponse401: type: object properties: error: type: object properties: message: type: string example: Invalid API key type: type: string example: authentication_error ErrorResponse403: type: object properties: error: type: object properties: message: type: string example: Access denied type: type: string example: permission_error ErrorResponse429: type: object properties: error: type: object properties: message: type: string example: Rate limit exceeded type: type: string example: rate_limit_error ErrorResponse500: type: object properties: error: type: object properties: message: type: string example: Internal server error type: type: string example: server_error responses: ClaudeMessagesSuccess: description: Claude Messages API response content: application/json: schema: $ref: '#/components/schemas/ClaudeMessagesResponse' BadRequest: description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse401' PaymentRequired: description: Insufficient balance content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse403' TooManyRequests: description: Too Many Requests content: application/json: schema: $ref: '#/components/schemas/ErrorResponse429' InternalServerError: description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse500' securitySchemes: BearerAuth: type: http scheme: bearer description: | ## All APIs require Bearer Token authentication ## Add to request header: `Authorization: Bearer YOUR_API_KEY` ````