Generate a response

Model name

Text for the model to generate a response from

Used for fill-in-the-middle models, text that appears after the user prompt and before the model response

Structured output format for the model to generate a response from. Supports either the string "json" or a JSON schema object.

System prompt for the model to generate a response from

When true, returns a stream of partial responses

Controls a model's thinking output. Use /api/show to discover the supported values and default for the selected model. true requests thinking, false requests no thinking output, and null uses the model default. String values are model-defined; supported names must match /api/show exactly. Numbers are not supported.

When true, returns the raw response from the model without any prompt templating

Model keep-alive duration (for example 5m or 0 to unload immediately)

Whether to return log probabilities of the output tokens

Number of most likely tokens to return at each token position when logprobs are enabled

Model name

ISO 8601 timestamp of response creation

The model's generated text response

The model's generated thinking output

Indicates whether generation has finished

Reason the generation stopped

Time spent generating the response in nanoseconds

Time spent loading the model in nanoseconds

Number of input tokens in the prompt

Number of prompt tokens read from the cache

Time spent evaluating uncached prompt tokens in nanoseconds

Number of output tokens generated in the response

Time spent generating tokens in nanoseconds