> ## Documentation Index > Fetch the complete documentation index at: https://together-ai-preview.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Create completion > Query a language, code, or image model. ## OpenAPI ````yaml together-openapi.yaml post /completions openapi: 3.0.0 info: title: Together API description: The Together REST API. Please see https://docs.together.ai for more details. version: 2.0.0 termsOfService: https://www.together.ai/terms-of-service contact: name: Together Support url: https://www.together.ai/contact license: name: MIT url: https://github.com/togethercomputer/openapi/blob/main/LICENSE servers: - url: https://api.together.xyz/v1 security: - bearerAuth: [] paths: /completions: post: tags: - Completion summary: Create completion description: Query a language, code, or image model. operationId: completions requestBody: content: application/json: schema: $ref: '#/components/schemas/CompletionRequest' responses: '200': description: '200' content: application/json: schema: $ref: '#/components/schemas/CompletionResponse' text/event-stream: schema: $ref: '#/components/schemas/CompletionStream' '400': description: BadRequest content: application/json: schema: $ref: '#/components/schemas/ErrorData' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorData' '404': description: NotFound content: application/json: schema: $ref: '#/components/schemas/ErrorData' '429': description: RateLimit content: application/json: schema: $ref: '#/components/schemas/ErrorData' '503': description: Overloaded content: application/json: schema: $ref: '#/components/schemas/ErrorData' '504': description: Timeout content: application/json: schema: $ref: '#/components/schemas/ErrorData' deprecated: false components: schemas: CompletionRequest: type: object required: - model - prompt properties: prompt: type: string description: A string providing context for the model to complete. example: [INST] What is the capital of France? [/INST] model: type: string description: The name of the model to query. example: mistralai/Mixtral-8x7B-Instruct-v0.1 max_tokens: type: integer description: The maximum number of tokens to generate. stop: type: array description: >- A list of string sequences that will truncate (stop) inference text output. items: type: string temperature: type: number description: Determines the degree of randomness in the response. format: float top_p: type: number description: >- The `top_p` (nucleus) parameter is used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities. format: float top_k: type: integer description: >- The `top_k` parameter is used to limit the number of choices for the next predicted word or token. format: int32 repetition_penalty: type: number description: >- A number that controls the diversity of generated text by reducing the likelihood of repeated sequences. Higher values decrease repetition. format: float stream: type: boolean description: >- If set, tokens are returned as Server-Sent Events as they are made available. Stream terminates with `data: [DONE]` logprobs: type: integer minimum: 0 maximum: 1 description: >- Determines the number of most likely tokens to return at each token position log probabilities to return echo: type: boolean description: >- If set, the response will contain the prompt, and will also return prompt logprobs if set with logprobs. 'n': type: integer description: Number of generations to return minimum: 1 maximum: 128 safety_model: type: string description: The name of the safety model to use. example: safety_model_name min_p: type: number description: >- The `min_p` parameter is a number between 0 and 1 and an alternative to `temperature`. format: float presence_penalty: type: number description: >- The `presence_penalty` parameter is a number between -2.0 and 2.0 where a positive value will increase the likelihood of a model talking about new topics. format: float frequency_penalty: type: number description: >- The `frequency_penalty` parameter is a number between -2.0 and 2.0 where a positive value will decrease the likelihood of repeating tokens that were mentioned prior. format: float logit_bias: type: object additionalProperties: type: number format: float description: >- The `logit_bias` parameter allows us to adjust the likelihood of specific tokens appearing in the generated output. example: '105': 21.4 '1024': -10.5 CompletionResponse: type: object properties: id: type: string choices: $ref: '#/components/schemas/CompletionChoicesData' prompt: $ref: '#/components/schemas/PromptPart' usage: $ref: '#/components/schemas/UsageData' created: type: integer model: type: string object: type: string enum: - text_completion required: - id - choices - usage - created - model - object CompletionStream: oneOf: - $ref: '#/components/schemas/CompletionEvent' - $ref: '#/components/schemas/StreamSentinel' ErrorData: type: object required: - error properties: error: type: object properties: message: type: string nullable: false type: type: string nullable: false param: type: string nullable: true default: null code: type: string nullable: true default: null required: - type - message - param - code CompletionChoicesData: type: array items: type: object properties: text: type: string example: >- The capital of France is Paris. It's located in the north-central part of the country and is one of the most populous and visited cities in the world, known for its iconic landmarks like the Eiffel Tower, Louvre Museum, Notre-Dame Cathedral, and more. Paris is also the capital of the Île-de-France region and is a major global center for art, fashion, gastronomy, and culture. finish_reason: $ref: '#/components/schemas/FinishReason' logprobs: allOf: - $ref: '#/components/schemas/LogprobsPart' - nullable: true PromptPart: type: array items: type: object properties: text: type: string example: [INST] What is the capital of France? [/INST] logprobs: $ref: '#/components/schemas/LogprobsPart' UsageData: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer required: - prompt_tokens - completion_tokens - total_tokens nullable: true CompletionEvent: type: object required: - data properties: data: $ref: '#/components/schemas/CompletionChunk' StreamSentinel: type: object required: - data properties: data: title: stream_signal type: string enum: - '[DONE]' FinishReason: type: string enum: - stop - eos - length - tool_calls LogprobsPart: type: object properties: tokens: type: array items: type: string description: List of token strings token_logprobs: type: array items: type: number format: float description: List of token log probabilities CompletionChunk: type: object required: - id - token - choices - usage - finish_reason properties: id: type: string token: $ref: '#/components/schemas/CompletionToken' choices: title: CompletionChoices type: array items: $ref: '#/components/schemas/CompletionChoice' usage: allOf: - $ref: '#/components/schemas/UsageData' - nullable: true finish_reason: allOf: - $ref: '#/components/schemas/FinishReason' - nullable: true CompletionToken: type: object required: - id - text - logprob - special properties: id: type: integer text: type: string logprob: type: number format: float special: type: boolean CompletionChoice: type: object required: - index properties: text: type: string securitySchemes: bearerAuth: type: apiKey in: header name: Authorization x-bearer-format: bearer x-default: default ````