> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt > Use this file to discover all available pages before exploring further. # claude-sonnet-5 > Send a structured list of input messages with text and/or image content, and Claude Sonnet 5 will generate the next message in the conversation. ## OpenAPI ````yaml api-reference/model-api/anthropic/openapi/claude-sonnet-5/openapi.yaml POST /v1/messages openapi: 3.1.0 info: title: Claude Sonnet 5 description: >- Anthropic Claude Sonnet 5 via Anyfast. Adaptive thinking is on by default, max output is 128K tokens, and manual extended thinking is not supported. version: 1.0.0 servers: - url: https://www.anyfast.ai security: - bearerAuth: [] paths: /v1/messages: post: summary: Create a Message description: >- Send a structured list of input messages with text and/or image content, and Claude Sonnet 5 will generate the next message in the conversation. operationId: createMessageClaudeSonnet5 requestBody: required: true content: application/json: schema: type: object required: - model - max_tokens - messages properties: model: type: string enum: - claude-sonnet-5 description: Model ID. example: claude-sonnet-5 messages: type: array minItems: 1 description: Input messages. Each message has a role and content. items: type: object required: - role - content properties: role: type: string enum: - user - assistant description: The role of the message author. content: oneOf: - type: string - type: array items: type: object properties: type: type: string enum: - text - image text: type: string source: type: object properties: type: type: string media_type: type: string data: type: string description: >- The content of the message. Either a string or an array of content blocks. example: - role: user content: Hello, Claude! max_tokens: type: integer minimum: 1 maximum: 128000 description: >- The maximum number of tokens to generate before stopping. Claude Sonnet 5 supports up to 128K output tokens. example: 1024 system: oneOf: - type: string - type: array items: type: object properties: type: type: string text: type: string description: System prompt. Provides context and instructions to Claude. metadata: type: object properties: user_id: type: string description: >- An external identifier for the user who is associated with the request. description: An object describing metadata about the request. stop_sequences: type: array items: type: string description: >- Custom text sequences that will cause the model to stop generating. temperature: type: number minimum: 0 maximum: 1 default: 1 description: >- Amount of randomness injected into the response. On Claude Sonnet 5, non-default values return a 400 error. example: 1 top_p: type: number minimum: 0 maximum: 1 description: >- Use nucleus sampling. On Claude Sonnet 5, non-default values return a 400 error. top_k: type: integer minimum: 0 description: >- Only sample from the top K options for each subsequent token. On Claude Sonnet 5, non-default values return a 400 error. stream: type: boolean default: false description: >- Whether to incrementally stream the response using server-sent events. tools: type: array items: type: object required: - name - input_schema properties: name: type: string description: Name of the tool. description: type: string description: Description of what the tool does. input_schema: type: object description: JSON Schema for the tool input. description: Definitions of tools that the model may use. tool_choice: type: object properties: type: type: string enum: - auto - any - tool description: How the model should use the provided tools. name: type: string description: The name of the tool to use (when type is "tool"). description: How the model should use the provided tools. output_config: type: object properties: effort: type: string enum: - low - medium - high - xhigh - max default: high description: >- Controls adaptive thinking depth and token usage. Claude Sonnet 5 defaults to high. description: >- Output controls for models that support adaptive thinking effort. thinking: type: object properties: type: type: string enum: - adaptive - disabled description: >- Whether to explicitly use adaptive thinking or disable thinking. description: >- Adaptive thinking configuration. Claude Sonnet 5 uses adaptive thinking by default; use output_config.effort to control depth. Manual extended thinking is not supported. responses: '200': description: Message created successfully content: application/json: schema: $ref: '#/components/schemas/Message' '400': description: Invalid request content: application/json: schema: $ref: a4eee0ef-c999-4ba4-9266-02fa6ffdf936 '401': description: Unauthorized content: application/json: schema: $ref: a4eee0ef-c999-4ba4-9266-02fa6ffdf936 '429': description: Rate limit exceeded content: application/json: schema: $ref: a4eee0ef-c999-4ba4-9266-02fa6ffdf936 components: schemas: Message: type: object required: - id - type - role - content - model - stop_reason - usage properties: id: type: string example: msg_01XFDUDYJgAACzvnptvVoYEL type: type: string example: message role: type: string example: assistant content: type: array items: type: object properties: type: type: string enum: - text - thinking - tool_use text: type: string thinking: type: string id: type: string name: type: string input: type: object example: - type: text text: Hello! How can I help you today? model: type: string example: claude-sonnet-5 stop_reason: type: string enum: - end_turn - max_tokens - stop_sequence - tool_use - refusal - null description: Includes `refusal` for requests that the model declines. stop_sequence: type: string nullable: true usage: type: object properties: input_tokens: type: integer output_tokens: type: integer cache_creation_input_tokens: type: integer cache_read_input_tokens: type: integer ````