--- title: "Get chat completion." method: GET path: "/v1/chat/completions/{completion_id}" tags: ["Inference"] --- # Get chat completion. `GET /v1/chat/completions/{completion_id}` Describe a chat completion by its ID. ## Path parameters - `completion_id` string, required — ID of the chat completion. ## Response `200` A OpenAICompletionWithInputMessages. - OpenAICompletionWithInputMessages — Chat completion response extended with the original input messages. - `id` string, required — The ID of the chat completion. - `choices` OpenAIChoice[], required — List of choices. - `message` OpenAIChatCompletionResponseMessage, required — An assistant message returned in a chat completion response. - `role` 'assistant' — The role of the message author, always 'assistant' in responses. - `content` string, nullable — The content of the message. - `tool_calls` union[] — The tool calls generated by the model. - union - ChatCompletionMessageToolCall — Tool call specification for OpenAI-compatible chat completion responses. - `id` string, required — Unique identifier for the tool call. - `type` 'function', required — Must be 'function' to identify this as a function call. - `function` object, required — Function call details. - … - ChatCompletionMessageCustomToolCall — A call to a custom tool created by the model. - `id` string, required — The ID of the tool call. - `type` 'custom', required — The type of the tool. Always 'custom'. - `custom` object, required — The custom tool that the model called. - … - `refusal` string, nullable — The refusal message generated by the model. - `function_call` object — Deprecated: the name and arguments of a function that should be called. - `name` string, required — Name of the function to call. - `arguments` string, required — Arguments to pass to the function as a JSON string. - `annotations` object[] — Annotations for the message, when applicable. - `audio` object, nullable — Audio response data when using audio output modality. - `finish_reason` 'stop' | 'length' | 'tool_calls' | 'content_filter' | 'function_call', required — The reason the model stopped generating. - `index` integer, required — The index of the choice. - `logprobs` object, nullable — The log probabilities for the tokens in the message. - `content` OpenAITokenLogProb[], nullable — The log probabilities for the tokens in the message. - `token` string, required — The token. - `bytes` integer[], nullable — The bytes for the token. - `logprob` number, required — The log probability of the token. - `top_logprobs` OpenAITopLogProb[], nullable — The top log probabilities for the token. - `token` string, required — The token. - `bytes` integer[], nullable — The bytes for the token. - `logprob` number, required — The log probability of the token. - `refusal` OpenAITokenLogProb[], nullable — The log probabilities for the refusal tokens. - `token` string, required — The token. - `bytes` integer[], nullable — The bytes for the token. - `logprob` number, required — The log probability of the token. - `top_logprobs` OpenAITopLogProb[], nullable — The top log probabilities for the token. - `token` string, required — The token. - `bytes` integer[], nullable — The bytes for the token. - `logprob` number, required — The log probability of the token. - `object` 'chat.completion' — The object type. - `created` integer, required — The Unix timestamp in seconds when the chat completion was created. - `model` string, required — The model that was used to generate the chat completion. - `service_tier` string, nullable — The service tier that was used for this response. - `system_fingerprint` string — System fingerprint for this completion. - `usage` OpenAIChatCompletionUsage — Usage information for OpenAI chat completion. - `prompt_tokens` integer — Number of tokens in the prompt. - `completion_tokens` integer — Number of tokens in the completion. - `total_tokens` integer — Total tokens used (prompt + completion). - `prompt_tokens_details` OpenAIChatCompletionUsagePromptTokensDetails — Token details for prompt tokens in OpenAI chat completion usage. - `cached_tokens` integer — Number of tokens retrieved from cache. - `completion_tokens_details` OpenAIChatCompletionUsageCompletionTokensDetails — Token details for output tokens in OpenAI chat completion usage. - `reasoning_tokens` integer — Number of tokens used for reasoning (o1/o3 models). - `input_messages` union[], required — The input messages used to generate this completion. - union - OpenAIUserMessageParamOutput — A message from the user in an OpenAI-compatible chat completion request. - `role` 'user' — Must be 'user' to identify this as a user message. - `content` union, required — The content of the message, which can include text and other media. - string - union[] - union - … - `name` string, nullable — The name of the user message participant. - OpenAISystemMessageParam — A system message providing instructions or context to the model. - `role` 'system' — Must be 'system' to identify this as a system message. - `content` union, required — The content of the 'system prompt'. If multiple system messages are provided, they are concatenated. - string - OpenAIChatCompletionContentPartTextParam[] - `type` 'text' — Must be 'text' to identify this as text content. - `text` string, required — The text content of the message. - `name` string, nullable — The name of the system message participant. - OpenAIAssistantMessageParamOutput — A message containing the model's (assistant) response in an OpenAI-compatible chat completion request. - `role` 'assistant' — Must be 'assistant' to identify this as the model's response. - `content` union — The content of the model's response. - string - OpenAIChatCompletionContentPartTextParam[] - `type` 'text' — Must be 'text' to identify this as text content. - `text` string, required — The text content of the message. - `name` string, nullable — The name of the assistant message participant. - `tool_calls` ChatCompletionMessageToolCall[], nullable — List of tool calls. Each tool call is an OpenAIChatCompletionToolCall object. - `id` string, required — Unique identifier for the tool call. - `type` 'function', required — Must be 'function' to identify this as a function call. - `function` object, required — Function call details. - `name` string, required — Name of the function to call. - `arguments` string, required — Arguments to pass to the function as a JSON string. - OpenAIToolMessageParam — A message representing the result of a tool invocation in an OpenAI-compatible chat completion request. - `role` 'tool' — Must be 'tool' to identify this as a tool response. - `tool_call_id` string, required — Unique identifier for the tool call this response is for. - `content` union, required — The response content from the tool. - string - OpenAIChatCompletionContentPartTextParam[] - `type` 'text' — Must be 'text' to identify this as text content. - `text` string, required — The text content of the message. - OpenAIDeveloperMessageParam — A message from the developer in an OpenAI-compatible chat completion request. - `role` 'developer' — Must be 'developer' to identify this as a developer message. - `content` union, required — The content of the developer message. - string - OpenAIChatCompletionContentPartTextParam[] - `type` 'text' — Must be 'text' to identify this as text content. - `text` string, required — The text content of the message. - `name` string, nullable — The name of the developer message participant. ## Other responses - `400` — The request was invalid or malformed - `429` — The client has sent too many requests in a given amount of time - `500` — The server encountered an unexpected error - `default` — An error occurred --- [API](https://skmtc.net/ogx-ai/apis/ogx-specification-stable-experimental-apis.md) · [All operations](https://skmtc.net/ogx-ai/apis/ogx-specification-stable-experimental-apis/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/ogx-ai/ogx-specification-stable-experimental-apis/revisions/f3f783962256/schema)