> ## Documentation Index > Fetch the complete documentation index at: https://gomodel-docs-benchmark-writeup-and-tooling.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Create a chat completion ## OpenAPI ````yaml /openapi.json post /v1/chat/completions openapi: 3.0.0 info: description: >- AI gateway routing requests to multiple LLM providers (OpenAI, Anthropic, Gemini, Groq, OpenRouter, DeepSeek, Z.ai, xAI, MiniMax, Xiaomi MiMo, OpenCode Go, Oracle, Ollama, Bailian). Drop-in OpenAI-compatible API. title: GoModel API contact: {} version: '1.0' servers: - url: '{base_url}' description: Edit the base URL to point at your GoModel deployment. variables: base_url: default: http://localhost:8080 description: Your GoModel deployment URL security: [] paths: /v1/chat/completions: post: tags: - chat summary: Create a chat completion requestBody: content: application/json: schema: $ref: '#/components/schemas/core.ChatRequest' description: Chat completion request required: true responses: '200': description: JSON response or SSE stream when stream=true content: application/json: schema: $ref: '#/components/schemas/core.ChatResponse' text/event-stream: schema: $ref: '#/components/schemas/core.ChatResponse' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' text/event-stream: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' text/event-stream: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' '429': description: Too Many Requests content: application/json: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' text/event-stream: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' '502': description: Bad Gateway content: application/json: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' text/event-stream: schema: $ref: '#/components/schemas/core.OpenAIErrorEnvelope' security: - BearerAuth: [] components: schemas: core.ChatRequest: type: object properties: max_tokens: type: integer messages: type: array items: $ref: '#/components/schemas/core.Message' model: type: string parallel_tool_calls: type: boolean provider: description: Gateway routing hint; stripped before upstream execution. type: string reasoning: $ref: '#/components/schemas/core.Reasoning' service_tier: type: string stream: type: boolean stream_options: $ref: '#/components/schemas/core.StreamOptions' temperature: type: number tool_choice: description: string or object tools: type: array items: type: object additionalProperties: {} top_p: type: number user: type: string core.ChatResponse: type: object properties: choices: type: array items: $ref: '#/components/schemas/core.Choice' created: type: integer id: type: string model: type: string object: type: string provider: type: string system_fingerprint: type: string usage: $ref: '#/components/schemas/core.Usage' core.OpenAIErrorEnvelope: type: object required: - error properties: error: $ref: '#/components/schemas/core.OpenAIErrorObject' core.Message: type: object properties: content: description: |- ContentSchema documents that `content` accepts either a plain string or an array of ContentPart values. type: array items: $ref: '#/components/schemas/core.ContentPart' x-oneof: >- [{"type":"null"},{"type":"string"},{"type":"array","items":{"$ref":"#/definitions/core.ContentPart"}}] role: type: string tool_call_id: type: string tool_calls: type: array items: $ref: '#/components/schemas/core.ToolCall' core.Reasoning: type: object properties: effort: description: >- Effort controls how much reasoning effort the model should use. Valid values are "low", "medium", "high", "xhigh", and "max". "xhigh" and "max" are supported by newer models such as Claude Opus 4.8; providers downgrade unsupported levels to their nearest equivalent. type: string core.StreamOptions: type: object properties: include_usage: description: >- IncludeUsage requests token usage information in streaming responses. When true, the final streaming chunk will include usage statistics. type: boolean core.Choice: type: object properties: finish_reason: type: string index: type: integer logprobs: type: object message: $ref: '#/components/schemas/core.ResponseMessage' core.Usage: type: object properties: completion_tokens: type: integer completion_tokens_details: $ref: '#/components/schemas/core.CompletionTokensDetails' prompt_tokens: type: integer prompt_tokens_details: $ref: '#/components/schemas/core.PromptTokensDetails' raw_usage: type: object additionalProperties: {} total_tokens: type: integer core.OpenAIErrorObject: type: object required: - code - message - param - type properties: code: type: string nullable: true message: type: string param: type: string nullable: true type: $ref: '#/components/schemas/core.ErrorType' core.ContentPart: type: object properties: image_url: $ref: '#/components/schemas/core.ImageURLContent' input_audio: $ref: '#/components/schemas/core.InputAudioContent' text: type: string type: type: string core.ToolCall: type: object properties: function: $ref: '#/components/schemas/core.FunctionCall' id: type: string type: type: string core.ResponseMessage: type: object properties: content: type: array items: $ref: '#/components/schemas/core.ContentPart' x-oneof: >- [{"type":"null"},{"type":"string"},{"type":"array","items":{"$ref":"#/definitions/core.ContentPart"}}] role: type: string tool_calls: type: array items: $ref: '#/components/schemas/core.ToolCall' core.CompletionTokensDetails: type: object properties: accepted_prediction_tokens: type: integer audio_tokens: type: integer reasoning_tokens: type: integer rejected_prediction_tokens: type: integer core.PromptTokensDetails: type: object properties: audio_tokens: type: integer cached_tokens: type: integer image_tokens: type: integer text_tokens: type: integer core.ErrorType: type: string enum: - provider_error - rate_limit_error - invalid_request_error - authentication_error - not_found_error x-enum-varnames: - ErrorTypeProvider - ErrorTypeRateLimit - ErrorTypeInvalidRequest - ErrorTypeAuthentication - ErrorTypeNotFound core.ImageURLContent: type: object properties: detail: type: string media_type: type: string url: type: string core.InputAudioContent: type: object properties: data: type: string format: type: string core.FunctionCall: type: object properties: arguments: type: string name: type: string securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT ````