> ## Documentation Index > Fetch the complete documentation index at: https://docs.subconscious.dev/llms.txt > Use this file to discover all available pages before exploring further. # Create Message > Generates a model response for the given conversation. This endpoint is fully compatible with the Anthropic Messages API, so you can use the Anthropic SDK by pointing its base URL at Subconscious. ## OpenAPI ````yaml api-reference/openapi.json POST /messages openapi: 3.1.0 info: title: Subconscious API version: 1.0.0 description: OpenAI-compatible inference API servers: - url: https://api.subconscious.dev/v1 security: - bearerAuth: [] paths: /messages: post: summary: Create a message description: >- Generates a model response for the given conversation. This endpoint is fully compatible with the Anthropic Messages API, so you can use the Anthropic SDK by pointing its base URL at Subconscious. operationId: createMessage requestBody: required: true content: application/json: schema: type: object required: - model - messages - max_tokens properties: model: type: string description: The model to use for completion. enum: - subconscious/tim-qwen3.6-27b example: subconscious/tim-qwen3.6-27b messages: type: array description: >- The conversation history. Each message has a role and content. Content is either a string or an array of content blocks (text, image, tool_use, tool_result, thinking). items: type: object required: - role - content properties: role: type: string enum: - user - assistant description: >- The role of the message author. System prompts are passed via the top-level `system` field, not as a message. content: oneOf: - type: string - type: array items: type: object description: >- A content block. `type` selects the block shape: `text` ({text}), `image` ({source}), `tool_use` ({id, name, input}), `tool_result` ({tool_use_id, content, is_error}), `thinking` ({thinking}). properties: type: type: string enum: - text - image - tool_use - tool_result - thinking text: type: string source: type: object description: >- Image source. Either base64 ({type:"base64", media_type, data}) or url ({type:"url", url}). properties: type: type: string enum: - base64 - url media_type: type: string example: image/png data: type: string url: type: string id: type: string description: tool_use block id. name: type: string description: tool_use block tool name. input: type: object description: tool_use block arguments. tool_use_id: type: string description: >- tool_result block: the id of the tool_use it answers. content: description: >- tool_result block content (string or array of blocks). is_error: type: boolean description: >- tool_result block: whether the tool call errored. thinking: type: string description: thinking block reasoning text. example: - role: user content: What is the capital of France? max_tokens: type: integer description: >- The maximum number of tokens to generate before stopping. Required. example: 1024 system: oneOf: - type: string - type: array items: type: object properties: type: type: string enum: - text text: type: string description: >- A system prompt: a string or an array of text content blocks. stream: type: boolean default: false description: >- If true, responses are streamed as Server-Sent Events using the Anthropic event protocol (`message_start`, `content_block_start`, `content_block_delta`, `content_block_stop`, `message_delta`, `message_stop`). temperature: type: number minimum: 0 maximum: 1 description: Amount of randomness injected into the response. top_p: type: number minimum: 0 maximum: 1 description: Nucleus sampling parameter. top_k: type: integer description: >- Only sample from the top K options for each subsequent token. stop_sequences: type: array items: type: string description: >- Custom text sequences that will cause the model to stop generating. tools: type: array description: Definitions of tools the model may use. items: type: object required: - name - input_schema properties: name: type: string description: type: string input_schema: type: object description: JSON Schema for the tool's input. tool_choice: type: object description: How the model should use the provided tools. properties: type: type: string enum: - auto - any - tool name: type: string description: >- Required when type is `tool`: the tool the model must use. thinking: type: object description: >- Enable extended thinking. When enabled, the response includes `thinking` content blocks before the final `text` block. properties: type: type: string enum: - enabled budget_tokens: type: integer description: Token budget for reasoning. metadata: type: object description: An object describing metadata about the request. properties: user_id: type: string chat_template_kwargs: type: object description: >- Subconscious extension. Controls model-specific features such as auto-compaction (Subconscious Cache). properties: enable_auto_compaction: type: boolean description: >- If false, disables automatic context compaction so you can control Subconscious Cache manually. responses: '200': description: Successful message content: application/json: schema: type: object properties: id: type: string description: A unique identifier for the message. example: msg_abc123 type: type: string enum: - message description: The object type. role: type: string enum: - assistant content: type: array description: >- An array of content blocks. Text blocks ({type:"text", text}), thinking blocks ({type:"thinking", thinking, signature}), and tool_use blocks ({type:"tool_use", id, name, input}). items: type: object properties: type: type: string enum: - text - thinking - tool_use text: type: string thinking: type: string signature: type: string id: type: string name: type: string input: type: object model: type: string example: subconscious/tim-qwen3.6-27b stop_reason: type: string enum: - end_turn - max_tokens - tool_use description: The reason the model stopped generating. stop_sequence: type: - string - 'null' description: The custom stop sequence that was generated, if any. usage: type: object properties: input_tokens: type: integer description: Number of input tokens used. output_tokens: type: integer description: Number of output tokens generated. cache_read_input_tokens: type: integer description: Number of input tokens read from cache. '400': description: Bad request due to invalid parameters or unsupported options '401': description: Unauthorized because of a missing or invalid API key '429': description: Rate limited due to too many requests or tokens per minute '500': description: Internal server error security: - apiKeyAuth: [] - bearerAuth: [] x-codeSamples: - lang: python label: Python (Anthropic SDK) source: |- from anthropic import Anthropic client = Anthropic( auth_token="your-api-key", base_url="https://api.subconscious.dev", ) message = client.messages.create( model="subconscious/tim-qwen3.6-27b", max_tokens=1024, messages=[{"role": "user", "content": "What is the capital of France?"}], ) print(message.content[0].text) - lang: javascript label: Node.js (Anthropic SDK) source: |- import Anthropic from "@anthropic-ai/sdk"; const client = new Anthropic({ authToken: "your-api-key", baseURL: "https://api.subconscious.dev", }); const message = await client.messages.create({ model: "subconscious/tim-qwen3.6-27b", max_tokens: 1024, messages: [{ role: "user", content: "What is the capital of France?" }], }); console.log(message.content[0].text); - lang: bash label: cURL source: |- curl https://api.subconscious.dev/v1/messages \ -H "x-api-key: YOUR_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{ "model": "subconscious/tim-qwen3.6-27b", "max_tokens": 1024, "messages": [{"role": "user", "content": "What is the capital of France?"}] }' components: securitySchemes: bearerAuth: type: http scheme: bearer description: API key from your Subconscious dashboard apiKeyAuth: type: apiKey in: header name: x-api-key description: >- API key from your Subconscious dashboard. Accepted by the Anthropic Messages endpoints in place of the Authorization header, for use with the Anthropic SDK. ````