> ## Documentation Index > Fetch the complete documentation index at: https://docs.liquid.ai/llms.txt > Use this file to discover all available pages before exploring further. # Chat completions > Generate a model response for a chat conversation. See [Text generation](https://docs.liquid.ai/api/guides/text-generation). ## OpenAPI ````yaml /api/openapi.json post /openai/v1/chat/completions openapi: 3.1.0 info: title: Liquid inference API version: 1.0.0 description: >- OpenAI-compatible inference API plus native endpoints. **Authentication** — Every request needs an API key, sent as a bearer token: `Authorization: Bearer $LIQUID_API_KEY`. Create a key on the [API keys](https://console.liquid.ai/dashboard/api-keys) page of Liquid Console; it is shown once. **Batch uploads** — Batch input files are uploaded through a presigned URL from `POST /v1/files`; see the [Batch guide](https://docs.liquid.ai/api/guides/batch). **Decision models** — `POST /decisions/v1/systemone` implements TypeSafe's System One API for typed Choice, Score, and Noul decisions from decision models such as `d1.1` and `d1-ultra`. servers: - url: https://api.liquid.ai security: - apiKey: [] tags: - name: Models - name: Chat - name: Decision models - name: Files - name: Batches - name: Large uploads paths: /openai/v1/chat/completions: post: tags: - Chat summary: Chat completions description: >- Generate a model response for a chat conversation. See [Text generation](https://docs.liquid.ai/api/guides/text-generation). operationId: chat-completions requestBody: required: true content: application/json: schema: type: object properties: model: type: string description: The model id to use. example: $MODEL_ID messages: type: array items: {} description: >- The conversation so far. Messages follow OpenAI role-specific content requirements. User messages may include `image_url` parts for models that take images, each a base64 `data:` URL or an http(s) URL, and `input_audio` parts (base64 WAV, `format: "wav"`) for models that take audio; other models return 400. Liquid downloads linked images itself before the request reaches the model, from public addresses only, and returns 400 when one cannot be downloaded or is not a PNG, JPEG, WebP, or GIF image; a request may link up to 8 images, of at most 10 MB each and 20 MB together. stream: type: boolean description: When true, tokens stream back as server-sent events. modalities: type: array items: {} description: >- Output types. ["text", "audio"] asks a model with speech output for a spoken reply, returned in `message.audio` (or streamed in `delta.audio`) beside the text. Defaults to ["text"]; models without speech output return 400. audio: type: object additionalProperties: true description: >- Spoken reply options when `modalities` includes "audio", as in OpenAI: `{ "voice", "format" }`. `format` is `pcm16` (headerless 16-bit PCM, 24 kHz mono), or `wav` (each streamed chunk a complete WAV file); other formats return 400. The reply arrives in `message.audio` or streamed `delta.audio`, with its words in `transcript`. `voice` is accepted but does not change the voice. required: - model - messages example: model: $MODEL_ID messages: - role: system content: You are a helpful assistant. - role: user content: Hello! responses: '200': description: Successful response. content: application/json: example: id: chatcmpl-abc123 object: chat.completion created: 1730419200 model: $MODEL_ID choices: - index: 0 message: role: assistant content: Hello! How can I help you today? finish_reason: stop usage: prompt_tokens: 19 completion_tokens: 10 total_tokens: 29 schema: type: object properties: id: type: string description: The completion id. object: type: string description: Always "chat.completion". created: type: integer description: Unix timestamp (seconds). model: type: string description: The model that generated the response. choices: type: array items: {} description: The generated choices. usage: type: object additionalProperties: true description: >- Token counts: { prompt_tokens, completion_tokens, total_tokens }, plus `cost` in USD when the model is priced. Audio models also report OpenAI's `prompt_tokens_details` and `completion_tokens_details`, whose `audio_tokens` say how much of each total was audio. Some vision models bill each image as a multiple of its tokens, counted in `prompt_tokens` as OpenAI does. Streaming responses report it on the final usage chunk. '429': description: >- The organization's request or token limit for the model was exceeded. headers: Retry-After: description: Integral seconds until the request can be retried. schema: type: integer minimum: 1 x-ratelimit-limit-requests: description: >- Maximum requests per minute (per second when only that limit is set), when a request limit applies. schema: type: integer minimum: 1 x-ratelimit-remaining-requests: description: Requests remaining in that window. schema: type: integer minimum: 0 x-ratelimit-reset-requests: description: >- Rounded-up duration until that window resets, such as 42s or 1m0s. schema: type: string pattern: ^([1-9][0-9]*h)?([0-9]+m)?[0-9]+s$ x-ratelimit-limit-tokens: description: >- Estimated tokens per minute (per second when only that limit is set), when a token limit applies. schema: type: integer minimum: 1 x-ratelimit-remaining-tokens: description: Estimated tokens remaining in that window. schema: type: integer minimum: 0 x-ratelimit-reset-tokens: description: >- Rounded-up duration until that window resets, such as 42s or 1m0s. schema: type: string pattern: ^([1-9][0-9]*h)?([0-9]+m)?[0-9]+s$ content: application/json: example: error: message: >- Rate limit exceeded for model `$MODEL_ID`. To request a higher limit, contact us at https://www.liquid.ai/connect. type: rate_limit_error param: null code: rate_limit_exceeded x-codeSamples: - lang: curl label: cURL source: |- curl https://api.liquid.ai/openai/v1/chat/completions \ -H "Authorization: Bearer $LIQUID_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "$MODEL_ID", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ] }' components: securitySchemes: apiKey: type: http scheme: bearer description: >- A Liquid API key from the [API keys](https://console.liquid.ai/dashboard/api-keys) page of Liquid Console, sent as `Authorization: Bearer $LIQUID_API_KEY`. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.