Generate a chat message

{ "model": "<string>", "created_at": "2023-11-07T05:31:56Z", "message": { "role": "assistant", "content": "<string>", "thinking": "<string>", "tool_calls": [ { "function": { "name": "<string>", "description": "<string>", "arguments": {} } } ], "images": [ "<string>" ] }, "done": true, "done_reason": "<string>", "total_duration": 123, "load_duration": 123, "prompt_eval_count": 123, "prompt_eval_duration": 123, "eval_count": 123, "eval_duration": 123, "logprobs": [ { "token": "<string>", "logprob": 123, "bytes": [ 123 ], "top_logprobs": [ { "token": "<string>", "logprob": 123, "bytes": [ 123 ] } ] } ] }

Body

application/json

model

string

required

Model name

messages

object[]

required

Chat history as an array of message objects (each with a role and content)

Show child attributes

tools

object[]

Optional list of function tools the model may call during the chat

Show child attributes

format

Format to return a response in. Can be json or a JSON schema

Available options:

json

options

object

Runtime options that control text generation

Show child attributes

stream

boolean

default:true

think

When true, returns separate thinking output in addition to content. Can be a boolean (true/false) or a string ("high", "medium", "low", "max") for supported models, with "max" requesting the highest thinking level.

keep_alive

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

logprobs

boolean

Whether to return log probabilities of the output tokens

top_logprobs

integer

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

Response

Chat response

model

string

Model name used to generate this message

created_at

string<date-time>

Timestamp of response creation (ISO 8601)

message

object

Show child attributes

done

boolean

Indicates whether the chat response has finished

done_reason

string

Reason the response finished

total_duration

integer

Total time spent generating in nanoseconds

load_duration

integer

Time spent loading the model in nanoseconds

prompt_eval_count

integer

Number of tokens in the prompt

prompt_eval_duration

integer

Time spent evaluating the prompt in nanoseconds

eval_count

integer

Number of tokens generated in the response

eval_duration

integer

Time spent generating tokens in nanoseconds

logprobs

object[]

Log probability information for the generated tokens when logprobs are enabled

Show child attributes

API Reference

Endpoints

Generate a chat message

Body

Response