---
title: "Create Chat Completion"
method: POST
path: "/v1/chat/completions"
tags: ["AI"]
---

# Create Chat Completion

`POST /v1/chat/completions`

Creates a model response for the given chat conversation.

## Request body

- CreateChatCompletionRequest
  - `audio` ChatCompletionAudio
    - `format` 'wav' | 'aac' | 'mp3' | 'flac' | 'opus' | 'pcm16', required
    - `voice` union, required
      - 'alloy'
      - 'ash'
      - 'ballad'
      - 'coral'
      - 'echo'
      - 'fable'
      - 'nova'
      - 'onyx'
      - 'sage'
      - 'shimmer'
      - object
        - `other` string, required
  - `frequency_penalty` number, float, nullable — 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.
  - `function_call` union
    - 'none' — The model does not call a function, and responds to the end-user.
    - 'auto' — The model can pick between an end-user or calling a function.
    - object — Forces the model to call the specified function.
      - `Function` object, required — Forces the model to call the specified function.
        - `name` string, required
  - `functions` ChatCompletionFunctions[], nullable — Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for.
    - `description` string, nullable — 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` unknown, required
  - `logit_bias` object, nullable — 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. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
  - `logprobs` boolean, nullable — 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`.
  - `max_completion_tokens` integer, nullable — An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
  - `max_tokens` integer, nullable — The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API. This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with [o-series models](https://platform.openai.com/docs/guides/reasoning).
  - `messages` ChatCompletionRequestMessage[], required — A list of messages comprising the conversation so far. Depending on the [model](https://platform.openai.com/docs/models) you use, different message types (modalities) are supported, like [text](https://platform.openai.com/docs/guides/text-generation), [images](https://platform.openai.com/docs/guides/vision), and [audio](https://platform.openai.com/docs/guides/audio).
    - union
      - object
        - `content` union, required
          - string
          - ChatCompletionRequestDeveloperMessageContentPart[]
            - `text` string, required
            - `type` 'text', required
        - `name` string, nullable — An optional name for the participant. Provides the model information to differentiate between participants of the same role.
        - `role` 'developer', required
      - object
        - `content` union, required
          - string — The text contents of the system message.
          - ChatCompletionRequestSystemMessageContentPart[] — An array of content parts with a defined type. For system messages, only type `text` is supported.
            - `text` string, required
            - `type` 'text', required
        - `name` string, nullable — An optional name for the participant. Provides the model information to differentiate between participants of the same role.
        - `role` 'system', required
      - object
        - `content` union, required
          - string — The text contents of the message.
          - ChatCompletionRequestUserMessageContentPart[] — An array of content parts with a defined type. Supported options differ based on the [model](https://platform.openai.com/docs/models) being used to generate the response. Can contain text, image, or audio inputs.
            - union
              - …
        - `name` string, nullable — An optional name for the participant. Provides the model information to differentiate between participants of the same role.
        - `role` 'user', required
      - object
        - `audio` ChatCompletionRequestAssistantMessageAudio
          - `id` string, required — Unique identifier for a previous audio response from the model.
        - `content` union
          - string — The text contents of the message.
          - ChatCompletionRequestAssistantMessageContentPart[] — An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`.
            - union
              - …
        - `function_call` FunctionCall — The name and arguments of a function that should be called, as generated by the model.
          - `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.
          - `name` string, required — The name of the function to call.
        - `name` string, nullable — An optional name for the participant. Provides the model information to differentiate between participants of the same role.
        - `refusal` string, nullable — The refusal message by the assistant.
        - `tool_calls` ChatCompletionMessageToolCalls[], nullable
          - union
            - object
              - …
            - object
              - …
        - `role` 'assistant', required
      - object — Tool message
        - `content` union, required
          - string — The text contents of the tool message.
          - ChatCompletionRequestToolMessageContentPart[] — An array of content parts with a defined type. For tool messages, only type `text` is supported.
            - `text` string, required
            - `type` 'text', required
        - `tool_call_id` string, required
        - `role` 'tool', required
      - object
        - `content` string, nullable — The return value from the function call, to return to the model.
        - `name` string, required — The name of the function to call.
        - `role` 'function', required
  - `metadata` unknown
  - `modalities` ResponseModalities[], nullable — Output types that you would like the model to generate. Most models are capable of generating text, which is the default: `["text"]` The `gpt-4o-audio-preview` model can also be used to [generate audio](https://platform.openai.com/docs/guides/audio). To request that this model generate both text and audio responses, you can use: `["text", "audio"]`
  - `model` string, required — Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://platform.openai.com/docs/models) to browse and compare available models.
  - `n` integer, nullable — How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.
  - `parallel_tool_calls` boolean, nullable — Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling) during tool use.
  - `prediction` PredictionContent — The type of the predicted content you want to provide. This type is currently always `content`.
    - `content` union, required — The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly.
      - string — The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes.
      - ChatCompletionRequestMessageContentPartText[] — An array of content parts with a defined type. Supported options differ based on the [model](https://platform.openai.com/docs/models) being used to generate the response. Can contain text inputs.
        - `text` string, required
    - `type` 'content', required
  - `presence_penalty` number, float, nullable — 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.
  - `prompt_cache_key` string, nullable — Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
  - `reasoning_effort` 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh'
  - `response_format` union
    - object — The type of response format being defined: `text`
      - `type` 'text', required
    - object — The type of response format being defined: `json_object`
      - `type` 'json_object', required
    - object — The type of response format being defined: `json_schema`
      - `json_schema` ResponseFormatJsonSchema, required
        - `description` string, nullable — 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` unknown
        - `strict` boolean, nullable — 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`. To learn more, read the [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
      - `type` 'json_schema', required
  - `safety_identifier` string, nullable — A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
  - `seed` integer, nullable — This feature is in Beta. 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.
  - `service_tier` 'auto' | 'default' | 'flex' | 'scale' | 'priority'
  - `stop` union
    - string
    - string[]
  - `store` boolean, nullable — Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. Supports text and image inputs. Note: image inputs over 8MB will be dropped.
  - `stream` boolean, nullable — 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). See the [Streaming section below](https://platform.openai.com/docs/api-reference/chat/streaming) for more information, along with the [streaming responses](https://platform.openai.com/docs/guides/streaming-responses) guide for more information on how to handle the streaming events.
  - `stream_options` ChatCompletionStreamOptions — Options for streaming response. Only set this when you set `stream: true`.
    - `include_obfuscation` boolean, nullable — When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an `obfuscation` field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set `include_obfuscation` to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.
    - `include_usage` boolean, nullable — 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. **NOTE:** If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request.
  - `temperature` number, float, nullable — 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. We generally recommend altering this or `top_p` but not both.
  - `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.
    - object
      - `allowed_tools` ChatCompletionAllowedTools[], required
        - `mode` 'auto' | 'required', required
        - `tools` unknown[], required — A list of tool definitions that the model should be allowed to call. For the Chat Completions API, the list of tool definitions might look like: ```json [ { "type": "function", "function": { "name": "get_weather" } }, { "type": "function", "function": { "name": "get_time" } } ] ```
          - unknown
      - `type` 'allowed_tools', required
    - object — Specifies a tool the model should use. Use to force the model to call a specific function.
      - `function` FunctionName, required
        - `name` string, required — The name of the function to call.
      - `type` 'function', required
    - object
      - `custom` CustomName, required
        - `name` string, required — The name of the custom tool to call.
      - `type` 'custom', required
  - `tools` ChatCompletionTools[], nullable — A list of tools the model may call. You can provide either [custom tools](https://platform.openai.com/docs/guides/function-calling#custom-tools) or [function tools](https://platform.openai.com/docs/guides/function-calling).
    - union
      - object — A function tool that can be used to generate a response.
        - `function` FunctionObject, required
          - `description` string, nullable — 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` unknown
          - `strict` boolean, nullable — 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](https://platform.openai.com/docs/guides/function-calling).
        - `type` 'function', required
      - object — A custom tool that processes input using a specified format.
        - `custom` CustomToolProperties, required
          - `description` string, nullable — Optional description of the custom tool, used to provide more context.
          - `format` union, required
            - object — Unconstrained free-form text.
              - …
            - object — A grammar defined by the user.
              - …
          - `name` string, required — The name of the custom tool, used to identify it in tool calls.
        - `type` 'custom', required
  - `top_logprobs` integer, nullable — 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.
  - `top_p` number, float, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
  - `user` string, nullable — This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
  - `verbosity` 'low' | 'medium' | 'high' — o-series reasoning settings.
  - `web_search_options` WebSearchOptions — Options for the web search tool.
    - `search_context_size` 'low' | 'medium' | 'high' — The amount of context window space to use for the search.
    - `user_location` WebSearchUserLocation
      - `approximate` WebSearchLocation, required — Approximate location parameters for the search.
        - `city` string, nullable — Free text input for the city of the user, e.g. `San Francisco`.
        - `country` string, nullable — The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`.
        - `region` string, nullable — Free text input for the region of the user, e.g. `California`.
        - `timezone` string, nullable — The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`.
      - `type` 'approximate', required

## Response `200`

Chat completion generated successfully

- CreateChatCompletionResponse — Represents a chat completion response returned by model, based on the provided input.
  - `choices` ChatChoice[], 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'
    - `index` integer, required — The index of the choice in the list of choices.
    - `logprobs` ChatChoiceLogprobs
      - `content` ChatCompletionTokenLogprob[], nullable — A list of message content tokens with log probability information.
        - `bytes` integer[], nullable — 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.
        - `logprob` number, float, 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.
        - `token` string, required — The token.
        - `top_logprobs` TopLogprobs[], 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.
          - `bytes` integer[], nullable — 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.
          - `logprob` number, float, required — The log probability of this token.
          - `token` string, required — The token.
      - `refusal` ChatCompletionTokenLogprob[], nullable
        - `bytes` integer[], nullable — 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.
        - `logprob` number, float, 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.
        - `token` string, required — The token.
        - `top_logprobs` TopLogprobs[], 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.
          - `bytes` integer[], nullable — 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.
          - `logprob` number, float, required — The log probability of this token.
          - `token` string, required — The token.
    - `message` ChatCompletionResponseMessage, required — A chat completion message generated by the model.
      - `annotations` ChatCompletionResponseMessageAnnotation[], nullable
        - `type` 'url_citation', required
        - `url_citation` UrlCitation, required
          - `end_index` integer, required — The index of the last character of the URL citation in the message.
          - `start_index` integer, required — The index of the first character of the URL citation in the message.
          - `title` string, required — The title of the web resource.
          - `url` string, required — The URL of the web resource.
      - `audio` ChatCompletionResponseMessageAudio
        - `data` string, required — Base64 encoded audio bytes generated by the model, in the format specified in the request.
        - `expires_at` integer, required — The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations.
        - `id` string, required — Unique identifier for this audio response.
        - `transcript` string, required — Transcript of the audio generated by the model.
      - `content` string, nullable — The contents of the message.
      - `function_call` FunctionCall — The name and arguments of a function that should be called, as generated by the model.
        - `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.
        - `name` string, required — The name of the function to call.
      - `reasoning_content` string, nullable — Reasoning / chain-of-thought content (e.g. extracted from a `<think>` block), kept separate from the user-facing `content`. Populated by reasoning models such as GLM, DeepSeek-R1, and QwQ.
      - `refusal` string, nullable — The refusal message generated by the model.
      - `role` 'user' | 'assistant' | 'system' | 'developer', required — Role of messages in the API.
      - `tool_calls` ChatCompletionMessageToolCalls[], nullable — The tool calls generated by the model, such as function calls.
        - union
          - object
            - `function` FunctionCall, required — The name and arguments of a function that should be called, as generated by the model.
              - …
            - `id` string, required — The ID of the tool call.
            - `type` 'function', required
          - object
            - `custom_tool` CustomTool, required
              - …
            - `id` string, required — The ID of the tool call.
            - `type` 'custom', required
  - `created` integer, required — The Unix timestamp (in seconds) of when the chat completion was created.
  - `id` string, required — A unique identifier for the chat completion.
  - `model` string, required — The model used for the chat completion.
  - `object` string, required — The object type, which is always `chat.completion`.
  - `service_tier` 'auto' | 'default' | 'flex' | 'scale' | 'priority'
  - `system_fingerprint` string, nullable — This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.
  - `usage` CompletionUsage — Usage statistics for the completion request.
    - `completion_tokens` integer, required — Number of tokens in the generated completion.
    - `completion_tokens_details` CompletionTokensDetails — Breakdown of tokens used in a completion.
      - `accepted_prediction_tokens` integer, nullable
      - `audio_tokens` integer, nullable — Audio input tokens generated by the model.
      - `reasoning_tokens` integer, nullable — Tokens generated by the model for reasoning.
      - `rejected_prediction_tokens` integer, nullable — 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` integer, required — Number of tokens in the prompt.
    - `prompt_tokens_details` PromptTokensDetails — Breakdown of tokens used in a completion.
      - `audio_tokens` integer, nullable — Audio input tokens present in the prompt.
      - `cached_tokens` integer, nullable — Cached tokens present in the prompt.
    - `total_tokens` integer, required — Total number of tokens used in the request (prompt + completion).

## Other responses

- `404` — The specified model was not found
- `500` — An internal server error occurred while processing the chat completion

## Changes

- **2026-06-23** `b901b202d046` — 1 info
  - added the optional property `choices/items/message/reasoning_content` to the response with the `200` status
- **2026-02-06** `c4d7063e0abe` — 1 breaking, 2 warning, 2 info
  - the `metadata/oneOf[#/components/schemas/Metadata]/` request property type/format changed from `object`/`` to ``/``
  - removed the request property `metadata/oneOf[#/components/schemas/Metadata]/supports_responses_api`
  - added the new `developer` enum value to the `choices/items/message/role` response property for the response status `200`
  - removed the `function` enum value from the `choices/items/message/role` response property for the response status `200`
  - …1 more
- **2025-12-30** `13efaee3e410` — 21 breaking, 2 warning, 21 info
  - removed the enum value `alloy` of the request property `audio/oneOf[#/components/schemas/ChatCompletionAudio]/voice`
  - removed the enum value `ash` of the request property `audio/oneOf[#/components/schemas/ChatCompletionAudio]/voice`
  - removed the enum value `ballad` of the request property `audio/oneOf[#/components/schemas/ChatCompletionAudio]/voice`
  - removed the enum value `coral` of the request property `audio/oneOf[#/components/schemas/ChatCompletionAudio]/voice`
  - …40 more
- …earlier changes not shown

[Full history](https://skmtc.dev/spiceai/apis/runtime/changes/v1/chat/completions/post.md)

---

[API](https://skmtc.dev/spiceai/apis/runtime.md) · [All operations](https://skmtc.dev/spiceai/apis/runtime/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/spiceai/runtime/revisions/fb597a4eaa56/schema)