> ## Documentation Index > Fetch the complete documentation index at: https://docs.tokensmind.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create chat completion ## OpenAPI ````yaml chat-completion.yaml POST /v1/chat/completions openapi: 3.0.1 info: title: '' version: 1.0.0 servers: - url: https://tokensmind.ai description: Production security: - bearer: [] paths: /v1/chat/completions: post: tags: - Chat / Native OpenAI format summary: Chat completions format description: | Generates a model response for the given chat conversation operationId: createChatCompletion parameters: - name: Content-Type in: header description: '' required: true example: application/json schema: type: string enum: - application/json x-apifox-enum: - value: application/json name: application/json description: '' - name: Authorization in: header description: 'Bearer authentication: Bearer {{API key}}.' required: true example: Bearer sk-*** schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string description: Model ID example: gpt-4 messages: type: array items: $ref: '#/components/schemas/Message' description: Conversation messages temperature: type: number minimum: 0 maximum: 2 default: 1 description: >- Sampling temperature between 0 and 2. Higher values (e.g. 0.8) make output more random; lower values (e.g. 0.2) make it more focused and deterministic. We generally recommend changing either this or top_p, not both. top_p: type: number description: >- An alternative to temperature, called nucleus sampling: the model considers tokens whose cumulative probability mass is top_p. So 0.1 means only the top 10% probability mass is considered. We generally recommend changing either this or temperature, not both. minimum: 0 maximum: 1 default: 1 exclusiveMinimum: true nullable: true 'n': type: integer minimum: 1 maximum: 128 default: 1 description: > How many completions to generate for each prompt. Note: This can consume your token quota quickly. Use with care and set max_tokens and stop to reasonable values. stream: type: boolean default: false description: >- Whether to stream partial progress. When enabled, tokens are sent as data-only server-sent events (SSE) as they become available; the stream ends with a data: [DONE] message. stream_options: type: object properties: include_usage: type: boolean x-apifox-orders: - include_usage description: >- Options for streaming responses. Only set when stream is true. stop: type: string description: > Up to 4 sequences where the API will stop generating further tokens. Returned text includes the stop sequence. max_tokens: type: integer description: >- Maximum number of tokens to generate If your prompt (prior messages) plus max_tokens would exceed the model context length, behavior depends on context_length_exceeded_behavior. By default, max_tokens is reduced to fit the context window instead of returning an error. max_completion_tokens: type: integer description: Maximum completion tokens presence_penalty: type: number minimum: -2 maximum: 2 default: 0 description: >- Positive values penalize new tokens based on whether they appear in the text so far, increasing the chance the model talks about new topics. For mild repetition reduction, try roughly 0.1 to 1. For strong suppression, you can increase toward 2, but quality may drop. Negative values encourage repetition. See also frequency_penalty for penalizing tokens by how often they appear. Required range: -2 < x < 2 frequency_penalty: type: number minimum: -2 maximum: 2 default: 0 description: >- Positive values penalize new tokens based on their existing frequency in the text, reducing the chance of repeating the same line verbatim. For mild repetition reduction, try roughly 0.1 to 1. For strong suppression, you can increase toward 2, but quality may drop. Negative values encourage repetition. See also presence_penalty for a fixed penalty on tokens that appear at least once. Required range: -2 < x < 2 logit_bias: type: object additionalProperties: type: number properties: {} x-apifox-orders: [] description: >- Modifies the likelihood of specified tokens appearing in the completion. Accepts a JSON object mapping tokens to bias values between -100 and 100. Mathematically, the bias is added to the logits before sampling. Exact behavior varies by model. For example, "logit_bias":{"1024": 6} increases the likelihood of token ID 1024. tools: type: array items: $ref: '#/components/schemas/Tool' description: > Tools the model may call. Currently only functions are supported. Provide a list of functions the model can generate JSON arguments for. See the [function calling guide](/docs/model/llm-function-calling) for more. nullable: true tool_choice: oneOf: - type: string enum: - none - auto - required - type: object properties: type: type: string function: type: object properties: name: type: string x-apifox-orders: - name x-apifox-orders: - type - function response_format: type: object properties: {} x-apifox-orders: [] nullable: true seed: type: integer description: >- If specified, the system will try to sample deterministically so repeated requests with the same seed and parameters return the same result. reasoning_effort: type: string enum: - low - medium - high description: Reasoning effort (for models that support reasoning) modalities: type: array items: type: string enum: - text - audio audio: type: object properties: voice: type: string format: type: string x-apifox-orders: - voice - format repetition_penalty: type: integer description: >- Penalty on repeated tokens to discourage or encourage repetition. 1.0 means no penalty and free repetition. Values above 1.0 penalize repetition. Values between 0.0 and 1.0 reward repetition. A balanced value is often around 1.2. The penalty applies to generated output and, in decoder-only models, to the prompt. Required range: 0 < x < 2 top_k: type: integer description: >- Top-k sampling keeps only the k most likely next tokens and redistributes probability mass among them. k controls how many candidates are considered per step. minimum: 0 maximum: 128 exclusiveMaximum: true exclusiveMinimum: true nullable: true min_p: type: number minimum: 0 maximum: 1 description: > Minimum relative probability for a token to be considered, compared to the most likely token. nullable: true logprobs: type: boolean description: > Whether to return log probabilities of output tokens. If true, returns logprobs for each output token in the message content. default: false nullable: true top_logprobs: type: integer minimum: 0 maximum: 20 description: >- Integer between 0 and 20: how many most likely tokens to return at each position, each with an associated log probability. If you use this, set logprobs to true. nullable: true x-apifox-refs: {} x-apifox-orders: - model - messages - temperature - top_p - top_k - min_p - 'n' - stream - stream_options - stop - max_tokens - max_completion_tokens - presence_penalty - frequency_penalty - repetition_penalty - logit_bias - logprobs - top_logprobs - tools - tool_choice - response_format - seed - reasoning_effort - modalities - audio required: - model - messages example: model: messages: - content: type: text: image_url: video_url: role: name: max_tokens: 123 stream: {} stream_options: include_usage: true 'n': {} seed: {} frequency_penalty: {} presence_penalty: {} repetition_penalty: {} stop: {} temperature: {} top_p: {} top_k: {} min_p: {} logit_bias: {} logprobs: {} top_logprobs: {} tools: type: function: name: description: {} parameters: {} strict: true response_format: type: json_schema: name: description: {} schema: {} strict: true separate_reasoning: {} enable_thinking: {} required: true responses: '200': description: Response created successfully content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' headers: {} x-apifox-name: Success x-apifox-ordering: 0 '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: {} x-apifox-name: Bad request x-apifox-ordering: 1 '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: {} x-apifox-ordering: 2 deprecated: false security: - bearer: [] components: schemas: Message: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool - developer description: Message role content: oneOf: - type: string - type: array items: $ref: '#/components/schemas/MessageContent' description: Message content name: type: string description: Sender name tool_calls: type: array items: $ref: '#/components/schemas/ToolCall' tool_call_id: type: string description: Tool call ID (for tool role messages) reasoning_content: type: string description: Reasoning content x-apifox-orders: - role - content - name - tool_calls - tool_call_id - reasoning_content x-apifox-ignore-properties: [] x-apifox-folder: '' Tool: type: object properties: type: type: string example: function function: type: object properties: name: type: string description: type: string parameters: type: object description: Parameter definition in JSON Schema format properties: {} x-apifox-orders: [] x-apifox-ignore-properties: [] x-apifox-orders: - name - description - parameters x-apifox-ignore-properties: [] x-apifox-orders: - type - function x-apifox-ignore-properties: [] x-apifox-folder: '' ChatCompletionResponse: type: object properties: id: type: string object: type: string example: chat.completion created: type: integer model: type: string choices: type: array items: type: object properties: index: type: integer message: $ref: '#/components/schemas/Message' finish_reason: type: string enum: - stop - length - tool_calls - content_filter x-apifox-orders: - index - message - finish_reason x-apifox-ignore-properties: [] usage: $ref: '#/components/schemas/Usage' system_fingerprint: type: string x-apifox-orders: - id - object - created - model - choices - usage - system_fingerprint x-apifox-ignore-properties: [] x-apifox-folder: '' ErrorResponse: type: object properties: error: type: object properties: message: type: string description: Error message type: type: string description: Error type param: type: string description: Related parameter nullable: true code: type: string description: Error code nullable: true x-apifox-orders: - message - type - param - code x-apifox-ignore-properties: [] x-apifox-orders: - error x-apifox-ignore-properties: [] x-apifox-folder: '' MessageContent: type: object properties: type: type: string enum: - text - image_url - input_audio - file - video_url text: type: string image_url: type: object properties: url: type: string description: Image URL or base64 detail: type: string enum: - low - high - auto x-apifox-orders: - url - detail x-apifox-ignore-properties: [] input_audio: type: object properties: data: type: string description: Base64-encoded audio data format: type: string enum: - wav - mp3 x-apifox-orders: - data - format x-apifox-ignore-properties: [] file: type: object properties: filename: type: string file_data: type: string file_id: type: string x-apifox-orders: - filename - file_data - file_id x-apifox-ignore-properties: [] video_url: type: object properties: url: type: string x-apifox-orders: - url x-apifox-ignore-properties: [] x-apifox-orders: - type - text - image_url - input_audio - file - video_url x-apifox-ignore-properties: [] x-apifox-folder: '' ToolCall: type: object properties: id: type: string type: type: string example: function function: type: object properties: name: type: string arguments: type: string x-apifox-orders: - name - arguments x-apifox-ignore-properties: [] x-apifox-orders: - id - type - function x-apifox-ignore-properties: [] x-apifox-folder: '' Usage: type: object properties: prompt_tokens: type: integer description: Prompt tokens completion_tokens: type: integer description: Completion tokens total_tokens: type: integer description: Total tokens prompt_tokens_details: type: object properties: cached_tokens: type: integer text_tokens: type: integer audio_tokens: type: integer image_tokens: type: integer x-apifox-orders: - cached_tokens - text_tokens - audio_tokens - image_tokens x-apifox-ignore-properties: [] completion_tokens_details: type: object properties: text_tokens: type: integer audio_tokens: type: integer reasoning_tokens: type: integer x-apifox-orders: - text_tokens - audio_tokens - reasoning_tokens x-apifox-ignore-properties: [] x-apifox-orders: - prompt_tokens - completion_tokens - total_tokens - prompt_tokens_details - completion_tokens_details x-apifox-ignore-properties: [] x-apifox-folder: '' securitySchemes: bearer: type: http scheme: bearer ````