| id string A unique identifier for the chat completion. Each chunk has the same ID. |
| object string The object type, which is always chat.completion |
| created integer The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. |
| model string A string representing the version of the model being used. |
| system\_fingerprint null This field is not yet available. |
| choices list A list of chat completion choices. |
| choices\[].finish\_reason string 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. |
| choices\[].index integer The index of the choice in the list of choices. |
| choices\[].message object A chat completion message generated by the model. |
| choices\[].message.content string The contents of the message. |
| choices\[].message.reasoning string or null The visible reasoning text returned by models that expose it when reasoning is enabled. This field is omitted or null otherwise. |
| choices\[].message.role string The role of the author of this message. |
| choices\[].message.tool\_calls list A list of tools selected by model to call. |
| choices\[].message.tool\_calls\[].id string The ID of tool calls. |
| choices\[].message.tool\_calls\[].type string The type of tool. |
| choices\[].message.tool\_calls\[].function object A function object to call. |
| choices\[].message.tool\_calls\[].function.name string The name of function to call. |
| choices\[].message.tool\_calls\[].function.arguments string A JSON input to function. |
| choices\[].logprobs null This field is not yet available. |
| usage object Usage statistics for the completion request. |
| usage.completion\_tokens integer Number of tokens in the generated completion. |
| usage.completion\_tokens\_details object A breakdown of the tokens in the generated completion. |
| usage.completion\_tokens\_details.reasoning\_tokens integer Number of tokens the model used for reasoning. This can be 0 when reasoning is disabled. |
| usage.prompt\_tokens integer Number of tokens in the prompt. |
| usage.total\_tokens integer Total number of tokens used in the request (prompt + completion). |
| id string A unique identifier for the chat completion. Each chunk has the same ID. |
| object string The object type, which is always `chat.completion.chunk` |
| created integer The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. |
| model string A string representing the version of the model being used. |
| system\_fingerprint null This field is not yet available. |
| choices list A list of chat completion choices. |
| choices\[].finish\_reason string 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. |
| choices\[].index integer The index of the choice in the list of choices. |
| choices\[].delta object A chat completion message generated by the model. |
| choices\[].delta.content string The contents of the message. |
| choices\[].delta.reasoning string or null A partial segment of visible reasoning text returned by models that expose it. This field is omitted or null for chunks without reasoning text. |
| choices\[].delta.role string or null The role of the author of this message. |
| choices\[].delta.tool\_calls list A list of tools selected by model to call. |
| choices\[].delta.tool\_calls\[].id string The ID of tool calls. |
| choices\[].delta.tool\_calls\[].type string The type of tool. |
| choices\[].delta.tool\_calls\[].function object A function object to call. |
| choices\[].delta.tool\_calls\[].function.name string The name of function to call. |
| choices\[].delta.tool\_calls\[].function.arguments string A JSON input to function. |
| choices\[].logprobs null This field is not yet available. |