> ## Documentation Index > Fetch the complete documentation index at: https://docs.zerogpu.ai/llms.txt > Use this file to discover all available pages before exploring further. # Chat completions > OpenAI-style chat inference for models that use this route. Some models are invoked with a **chat-completions** style body (`messages` array) instead of the [Responses](/api-reference/responses) `input` field. The dashboard and [model catalog](/docs/model-catalog) indicate which route applies. Each model page has its own playground with the right examples for that model. Install the official SDK from [npm](https://www.npmjs.com/package/zerogpu-api) or [PyPI](https://pypi.org/project/zerogpu-api/) (`pip install zerogpu-api`). Source: [zerogpu/SDK](https://github.com/zerogpu/SDK). Response JSON shape depends on the model; handle errors the same way as [API error codes](/docs/production-patterns#handle-status-codes-explicitly). ## OpenAPI ````yaml api-reference/openapi/zerogpu.openapi.json POST /chat/completions openapi: 3.1.0 info: title: ZeroGPU API version: '1.0' description: >- REST API for ZeroGPU model inference: `POST /v1/responses` and `POST /v1/chat/completions` (model-dependent). Authentication uses `x-api-key` and `x-project-id` headers on every request. Documentation: https://docs.zerogpu.ai **Per-model playgrounds** are listed on [Model playgrounds](/api-reference/models) with request examples for each model's use cases. These endpoint pages show a generic shape only. servers: - url: https://api.zerogpu.ai/v1 description: Production security: - ApiKey: [] ProjectId: [] paths: /chat/completions: post: tags: - Chat summary: Chat-completions style inference description: OpenAI-compatible chat body for models that use the messages route. operationId: createChatCompletion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionRequest' example: model: llama-3.1-8b-instruct-fast messages: - role: user content: >- NASA announced that its Artemis III mission is now scheduled for late 2026, marking the first time astronauts will land on the lunar surface since Apollo 17 in 1972. The mission will send a crew of four to the Moon aboard the Orion spacecraft, with two astronauts descending to the south pole using SpaceX Starship as a lunar lander. Scientists are particularly excited about exploring permanently shadowed craters that may contain water ice, which could be critical for sustaining long-term human presence on the Moon. responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' example: id: chatcmpl_abc123 object: chat.completion created: 1710000000 model: llama-3.1-8b-instruct-fast choices: - index: 0 message: role: assistant content: >- Artemis III, slated for late 2026, will return astronauts to the Moon for the first time since 1972, landing two crew at the south pole to study shadowed craters that may hold water ice. finish_reason: stop usage: prompt_tokens: 112 completion_tokens: 44 total_tokens: 156 '400': description: Bad request (invalid body) '401': description: Unauthorized (invalid or missing API key) '403': description: Forbidden (invalid project ID or permissions) '420': description: Insufficient quota (insufficient_quota) content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: code: insufficient_quota message: You have insufficient quota to complete this request. '500': description: Internal server error components: schemas: CreateChatCompletionRequest: type: object required: - model - messages properties: model: type: string description: >- Model identifier. Open a [model page](/api-reference/models) for a dedicated playground with the correct body for that model. enum: - llama-3.1-8b-instruct-fast - LFM2.5-1.2B-Instruct - LFM2.5-1.2B-Thinking - deberta-v3-small - gliner2-base-v1 - gliner-multi-pii-v1 - zlm-v1-followup-questions-edge - zlm-v1-iab-classify-edge - zlm-v1-iab-classify-edge-enriched - zlm-v1-iab-domain-classifier example: llama-3.1-8b-instruct-fast messages: type: array minItems: 1 description: Ordered list of messages making up the conversation so far. items: $ref: '#/components/schemas/ChatMessage' metadata: type: object additionalProperties: true description: >- Optional model-specific parameters, passed through to the model. For example, PII models accept `mask` and `usecase`. See the relevant [model page](/api-reference/models) for supported keys. ChatCompletionResponse: type: object description: An OpenAI-compatible chat completion. properties: id: type: string description: Unique identifier for the completion. example: chatcmpl_abc123 object: type: string description: Object type. Always `chat.completion`. example: chat.completion created: type: integer description: Unix timestamp (seconds) when the completion was created. example: 1710000000 model: type: string description: The model used for inference. example: llama-3.1-8b-instruct-fast choices: type: array description: List of completion choices. items: $ref: '#/components/schemas/ChatChoice' usage: $ref: '#/components/schemas/ChatUsage' ErrorResponse: type: object description: Error payload returned on a failed request. properties: error: type: object properties: code: type: string description: Machine-readable error code, for example `insufficient_quota`. example: insufficient_quota message: type: string description: Human-readable description of the error. example: You have insufficient quota to complete this request. ChatMessage: type: object required: - role - content properties: role: type: string description: Role of the message author. enum: - system - user - assistant content: type: string minLength: 1 format: textarea maxLength: 131072 description: The message text. ChatChoice: type: object description: A single completion choice. properties: index: type: integer description: Position of this choice in the list. example: 0 message: $ref: '#/components/schemas/ChatMessage' finish_reason: type: string description: Why the model stopped generating, for example `stop` or `length`. example: stop ChatUsage: type: object description: Token usage statistics for the request. properties: prompt_tokens: type: integer description: Number of tokens in the prompt. example: 112 completion_tokens: type: integer description: Number of tokens in the generated completion. example: 44 total_tokens: type: integer description: Total tokens consumed (prompt plus completion). example: 156 securitySchemes: ApiKey: type: apiKey in: header name: x-api-key description: >- Your ZeroGPU API key. Create one in the dashboard under API keys. Send it on every request. ProjectId: type: apiKey in: header name: x-project-id description: >- The UUID of the project the request is billed to. Find it in the dashboard project settings. ````