---
title: "Create a chat completion"
method: POST
path: "/chat/completions"
tags: ["Completions"]
---

# Create a chat completion

`POST /chat/completions`

Generates a chat completion based on the provided input.
The completion can be streamed to the client as it is generated.

## Query parameters

- `provider` 'ollama' | 'ollama_cloud' | 'groq' | 'llamacpp' | 'openai' | 'cloudflare' | 'cohere' | 'anthropic' | 'deepseek' | 'google' | 'mistral' | 'minimax' | 'moonshot' | 'nvidia' | 'zai'

## Request body

- CreateChatCompletionRequest
  - `model` string, required — Model ID to use
  - `messages` Message[], required — A list of messages comprising the conversation so far.
    - `role` 'system' | 'user' | 'assistant' | 'tool', required — Role of the message sender
    - `content` union, required — Message content - either text or multimodal content parts
      - string — Text content (backward compatibility)
      - ContentPart[] — Array of content parts for multimodal messages
        - union — A content part within a multimodal message
          - object — Text content part
            - `type` 'text', required — Content type identifier
            - `text` string, required — The text content
          - object — Image content part
            - `type` 'image_url', required — Content type identifier
            - `image_url` ImageURL, required — Image URL configuration
              - …
    - `tool_calls` ChatCompletionMessageToolCall[]
      - `id` string, required — The ID of the tool call.
      - `type` 'function', required — The type of the tool. Currently, only `function` is supported.
      - `function` ChatCompletionMessageToolCallFunction, required — The function that the model called.
        - `name` string, required — The name of the function to call.
        - `arguments` string, required — The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
      - `extra_content` ToolCallExtraContent — Provider-specific opaque data attached to a tool call. The contents are not interpreted by the gateway, but must be echoed back verbatim on the next request that references this tool call. Currently used by Google Gemini extended-thinking models to carry the per-call `thought_signature`. Other providers may ignore the field.
        - `google` object — Google Gemini-specific extra content.
          - `thought_signature` string — Opaque signature returned with reasoning-enabled tool calls. Must be echoed back verbatim in the next request that includes this tool call, or Google will reject the request.
    - `tool_call_id` string
    - `reasoning_content` string — The reasoning content of the chunk message.
    - `reasoning` string — The reasoning of the chunk message. Same as reasoning_content.
  - `max_tokens` integer — The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API. This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with o-series models.
  - `max_completion_tokens` integer — An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
  - `temperature` number — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
  - `top_p` number — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
  - `frequency_penalty` number — Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
  - `presence_penalty` number — Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
  - `n` integer — How many chat completion choices to generate for each input message.
  - `stop` union — Up to 4 sequences where the API will stop generating further tokens.
    - string
    - string[]
  - `seed` integer — If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
  - `logprobs` boolean — Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`.
  - `top_logprobs` integer — An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used.
  - `response_format` union — An object specifying the format that the model must output. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which guarantees the model will match your supplied JSON schema. Setting to `{ "type": "json_object" }` enables the older JSON mode, which ensures the message the model generates is valid JSON.
    - ResponseFormatText — Default response format. Used to generate text responses.
      - `type` 'text', required — The type of response format being defined. Always `text`.
    - ResponseFormatJsonSchema — JSON Schema response format. Used to generate structured JSON responses.
      - `type` 'json_schema', required — The type of response format being defined. Always `json_schema`.
      - `json_schema` object, required — Structured Outputs configuration options, including a JSON Schema.
        - `description` string — A description of what the response format is for, used by the model to determine how to respond in the format.
        - `name` string, required — The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        - `schema` ResponseFormatJsonSchemaSchema — The schema for the response format, described as a JSON Schema object.
        - `strict` boolean — Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`.
    - ResponseFormatJsonObject — JSON object response format. An older method of generating JSON responses. Using `json_schema` is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
      - `type` 'json_object', required — The type of response format being defined. Always `json_object`.
  - `logit_bias` object — Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. The bias is added to the logits generated by the model prior to sampling.
  - `user` string — A unique identifier representing your end-user, which can help to monitor and detect abuse.
  - `stream` boolean — If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
  - `stream_options` ChatCompletionStreamOptions — Options for streaming response. Only set this when you set `stream: true`.
    - `include_usage` boolean, required — If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value.
  - `tools` ChatCompletionTool[] — A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.
    - `type` 'function', required — The type of the tool. Currently, only `function` is supported.
    - `function` FunctionObject, required
      - `description` string — A description of what the function does, used by the model to choose when and how to call the function.
      - `name` string, required — The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
      - `parameters` FunctionParameters — The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. Omitting `parameters` defines a function with an empty parameter list.
      - `strict` boolean — Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](docs/guides/function-calling).
  - `tool_choice` union — Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools are present.
    - 'none' | 'auto' | 'required' — `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools.
    - ChatCompletionNamedToolChoice — Specifies a tool the model should use. Use to force the model to call a specific function.
      - `type` 'function', required — The type of the tool. Currently, only `function` is supported.
      - `function` object, required
        - `name` string, required — The name of the function to call.
  - `parallel_tool_calls` boolean — Whether to enable parallel function calling during tool use.
  - `reasoning_format` string — The format of the reasoning content. Can be `raw` or `parsed`. When specified as raw some reasoning models will output <think /> tags. When specified as parsed the model will output the reasoning under `reasoning` or `reasoning_content` attribute.
  - `reasoning_effort` 'minimal' | 'low' | 'medium' | 'high' — Constrains effort on reasoning for reasoning models. Currently supported values are `minimal`, `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

## Response `200`

Successful response

- CreateChatCompletionResponse — Represents a chat completion response returned by model, based on the provided input.
  - `id` string, required — A unique identifier for the chat completion.
  - `choices` ChatCompletionChoice[], required — A list of chat completion choices. Can be more than one if `n` is greater than 1.
    - `finish_reason` 'stop' | 'length' | 'tool_calls' | 'content_filter' | 'function_call', required — The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool.
    - `index` integer, required — The index of the choice in the list of choices.
    - `message` Message, required — Message structure for provider requests
      - `role` 'system' | 'user' | 'assistant' | 'tool', required — Role of the message sender
      - `content` union, required — Message content - either text or multimodal content parts
        - string — Text content (backward compatibility)
        - ContentPart[] — Array of content parts for multimodal messages
          - union — A content part within a multimodal message
            - object — Text content part
              - …
            - object — Image content part
              - …
      - `tool_calls` ChatCompletionMessageToolCall[]
        - `id` string, required — The ID of the tool call.
        - `type` 'function', required — The type of the tool. Currently, only `function` is supported.
        - `function` ChatCompletionMessageToolCallFunction, required — The function that the model called.
          - `name` string, required — The name of the function to call.
          - `arguments` string, required — The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
        - `extra_content` ToolCallExtraContent — Provider-specific opaque data attached to a tool call. The contents are not interpreted by the gateway, but must be echoed back verbatim on the next request that references this tool call. Currently used by Google Gemini extended-thinking models to carry the per-call `thought_signature`. Other providers may ignore the field.
          - `google` object — Google Gemini-specific extra content.
            - `thought_signature` string — Opaque signature returned with reasoning-enabled tool calls. Must be echoed back verbatim in the next request that includes this tool call, or Google will reject the request.
      - `tool_call_id` string
      - `reasoning_content` string — The reasoning content of the chunk message.
      - `reasoning` string — The reasoning of the chunk message. Same as reasoning_content.
    - `logprobs` object, nullable — Log probability information for the choice.
      - `content` ChatCompletionTokenLogprob[], required — A list of message content tokens with log probability information.
        - `token` string, required — The token.
        - `logprob` number, required — The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.
        - `bytes` integer[], required — A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.
        - `top_logprobs` object[], required — List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned.
          - `token` string, required — The token.
          - `logprob` number, required — The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.
          - `bytes` integer[], required — A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.
      - `refusal` ChatCompletionTokenLogprob[], required — A list of message refusal tokens with log probability information.
        - `token` string, required — The token.
        - `logprob` number, required — The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.
        - `bytes` integer[], required — A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.
        - `top_logprobs` object[], required — List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned.
          - `token` string, required — The token.
          - `logprob` number, required — The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.
          - `bytes` integer[], required — A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.
  - `created` integer, required — The Unix timestamp (in seconds) of when the chat completion was created.
  - `model` string, required — The model used for the chat completion.
  - `object` string, required — The object type, which is always `chat.completion`.
  - `usage` CompletionUsage — Usage statistics for the completion request.
    - `completion_tokens` integer, required — Number of tokens in the generated completion.
    - `prompt_tokens` integer, required — Number of tokens in the prompt.
    - `total_tokens` integer, required — Total number of tokens used in the request (prompt + completion).
    - `completion_tokens_details` object — Breakdown of tokens used in a completion.
      - `accepted_prediction_tokens` integer — When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
      - `audio_tokens` integer — Audio input tokens generated by the model.
      - `reasoning_tokens` integer — Tokens generated by the model for reasoning.
      - `rejected_prediction_tokens` integer — When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits.
    - `prompt_tokens_details` object — Breakdown of tokens used in the prompt.
      - `audio_tokens` integer — Audio input tokens present in the prompt.
      - `cached_tokens` integer — Cached tokens present in the prompt.

## Other responses

- `400` — Bad request
- `401` — Unauthorized
- `500` — Internal server error

## Changes

- **2026-07-20** `16a952d15e3c` — 4 info
  - added the optional property `oneOf[#/components/schemas/CreateChatCompletionStreamResponse]/usage/completion_tokens_details` to the response with the `200` status (media type: text/event-stream)
  - added the optional property `oneOf[#/components/schemas/CreateChatCompletionStreamResponse]/usage/prompt_tokens_details` to the response with the `200` status (media type: text/event-stream)
  - added the optional property `usage/completion_tokens_details` to the response with the `200` status (media type: application/json)
  - added the optional property `usage/prompt_tokens_details` to the response with the `200` status (media type: application/json)
- **2026-07-18** `b8f52abd9b46` — 1 info
  - added the new enum value `llamacpp` to the `query` request parameter `provider`
- **2026-07-08** `a52394ec1728` — 1 info
  - added the new enum value `zai` to the `query` request parameter `provider`
- **2026-07-05** `8826c77313d2` — 1 info
  - added the new enum value `nvidia` to the `query` request parameter `provider`
- **2026-06-18** `b3724a6ffd56` — 17 info
  - added the new optional request property `frequency_penalty`
  - added the new optional request property `logit_bias`
  - added the new optional request property `logprobs`
  - added the new optional request property `max_completion_tokens`
  - …13 more

[Full history](https://skmtc.dev/inference-gateway/apis/inference-gateway-api/changes/chat/completions/post.md)

---

[API](https://skmtc.dev/inference-gateway/apis/inference-gateway-api.md) · [All operations](https://skmtc.dev/inference-gateway/apis/inference-gateway-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/inference-gateway/inference-gateway-api/revisions/4419fdfdc00e/schema)