> ## Documentation Index > Fetch the complete documentation index at: https://docs.abliteration.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create a message > Creates a message using the Anthropic Messages API format. Set stream: true for server-sent events. ## OpenAPI ````yaml https://api.abliteration.ai/openapi.json post /v1/messages openapi: 3.0.3 info: title: abliteration.ai API version: '2026-04-14' description: >- OpenAI-compatible chat completions and responses APIs for abliteration.ai, plus Anthropic-compatible messages and Policy Gateway endpoints for enforcement, config, simulations, and audits. termsOfService: https://abliteration.ai/terms-of-service contact: email: help@abliteration.ai servers: - url: https://api.abliteration.ai description: Production - url: http://localhost:8080 description: Local development security: [] tags: - name: Chat Completions description: OpenAI-compatible chat completions. - name: Responses description: OpenAI-compatible Responses API. - name: Policy Gateway description: Policy-enforced chat completions. - name: Anthropic Messages description: Anthropic-compatible Messages API. - name: Models description: OpenAI-compatible model listing. paths: /v1/messages: post: tags: - Anthropic Messages summary: Create a message description: >- Creates a message using the Anthropic Messages API format. Set stream: true for server-sent events. operationId: createAnthropicMessage parameters: - name: X-Free-Tier in: header description: Set to true to use the single anonymous free request. required: false schema: type: string enum: - 'true' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AnthropicMessagesRequest' examples: basic: summary: Basic request value: model: abliterated-model messages: - role: user content: Write one sentence about Stonehenge. max_tokens: 256 streaming: summary: Streaming request value: model: abliterated-model messages: - role: user content: Stream a short greeting. max_tokens: 128 stream: true multiTurn: summary: Multi-turn conversation value: model: abliterated-model messages: - role: user content: What is abliteration? - role: assistant content: >- Abliteration removes refusal vectors from language models. - role: user content: How does it work? max_tokens: 1024 withSystem: summary: With system prompt value: model: abliterated-model system: You are a helpful coding assistant. messages: - role: user content: Write a Python function that reverses a string. max_tokens: 512 temperature: 0.3 responses: '200': description: Message response content: application/json: schema: $ref: '#/components/schemas/AnthropicMessagesResponse' examples: success: summary: 200 OK value: id: msg_01XFDUDYJgAACzvnptvVoYEL type: message role: assistant model: abliterated-model content: - type: text text: >- Stonehenge is a prehistoric monument in Wiltshire, England, consisting of a ring of standing stones dating back to around 3000 BCE. stop_reason: end_turn stop_sequence: null usage: input_tokens: 14 output_tokens: 32 remaining_credits: 487 estimated_credits_used: 1 estimated_cost_usd: 0.00023 text/event-stream: schema: type: string description: >- Streaming response as server-sent events following the Anthropic streaming protocol. examples: stream: summary: SSE stream value: > event: message_start data: {"type":"message_start","message":{"id":"msg_01XFDUDYJgAACzvnptvVoYEL","type":"message","role":"assistant","model":"abliterated-model","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":14,"output_tokens":0}}} event: content_block_start data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}} event: content_block_delta data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello!"}} event: content_block_stop data: {"type":"content_block_stop","index":0} event: message_delta data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"output_tokens":2}} event: message_stop data: {"type":"message_stop"} '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/AnthropicErrorResponse' examples: invalidRequest: summary: Invalid request body value: type: error error: type: invalid_request_error message: Invalid request body. '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/AnthropicErrorResponse' examples: unauthorized: summary: Missing or invalid credentials value: type: error error: type: authentication_error message: Sign up to continue after your free request. '402': description: Insufficient credits content: application/json: schema: $ref: '#/components/schemas/AnthropicErrorResponse' examples: noCredits: summary: Credit balance exhausted value: type: error error: type: permission_error message: Insufficient credits. Top up to keep chatting. '429': description: Rate limited content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '502': description: Upstream unavailable content: application/json: schema: $ref: '#/components/schemas/AnthropicErrorResponse' '504': description: Gateway timeout content: application/json: schema: $ref: '#/components/schemas/AnthropicErrorResponse' security: - BearerAuth: [] - AnthropicApiKeyAuth: [] components: schemas: AnthropicMessagesRequest: type: object required: - model - messages properties: model: type: string description: Model id (e.g. abliterated-model). messages: type: array description: >- Non-empty array of message objects. Each has role (user or assistant) and content (string or content-block array). items: $ref: '#/components/schemas/AnthropicMessage' minItems: 1 max_tokens: type: integer minimum: 1 description: Maximum number of tokens to generate. temperature: type: number minimum: 0 maximum: 2 description: Sampling temperature. stream: type: boolean default: false description: Enable Server-Sent Events streaming. system: description: System prompt. Can be a string or an array of content blocks. oneOf: - type: string - type: array items: type: object flagged_categories: type: array description: >- Optional moderation categories to block. Supported: harassment, hate, illicit, sexual. Self-harm and sexual/minors are always blocked. items: type: string AnthropicMessagesResponse: type: object required: - id - type - role - model - content properties: id: type: string description: Unique message id (e.g. msg_01XFDUDYJgAACzvnptvVoYEL). type: type: string enum: - message role: type: string enum: - assistant model: type: string content: type: array items: $ref: '#/components/schemas/AnthropicContentBlock' stop_reason: type: string nullable: true description: Reason the model stopped generating (e.g. end_turn, max_tokens). stop_sequence: type: string nullable: true usage: $ref: '#/components/schemas/AnthropicUsage' remaining_credits: type: integer nullable: true description: User's remaining credit balance after this call. estimated_credits_used: type: integer description: Credits consumed by this call. estimated_cost_usd: type: number description: Estimated cost in USD. AnthropicErrorResponse: type: object required: - type - error properties: type: type: string enum: - error error: type: object required: - type - message properties: type: type: string description: >- Error type (e.g. invalid_request_error, authentication_error, permission_error, api_error). message: type: string ErrorResponse: type: object required: - error properties: error: type: string code: type: string AnthropicMessage: type: object required: - role - content properties: role: type: string enum: - user - assistant content: description: Text string or array of content blocks (text, image). oneOf: - type: string - type: array items: $ref: '#/components/schemas/AnthropicContentBlock' AnthropicContentBlock: oneOf: - type: object required: - type - text properties: type: type: string enum: - text text: type: string - type: object required: - type - source properties: type: type: string enum: - image source: type: object required: - type - media_type - data properties: type: type: string enum: - base64 media_type: type: string data: type: string AnthropicUsage: type: object properties: input_tokens: type: integer description: Number of input tokens. output_tokens: type: integer description: Number of output tokens. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: Use a JWT or abliteration.ai API key as a Bearer token. AnthropicApiKeyAuth: type: apiKey in: header name: x-api-key description: >- Anthropic SDK compatibility. Use an abliteration.ai API key starting with ak_. ````