POST /chat/completions

post

https://api.fireworks.ai/inference/v1/chat/completions

Creates a model response for the given chat conversation.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Body Params

model

string

required

The name of the model to use.

messages

array of objects

required

length ≥ 1

A list of messages comprising the conversation so far.

messages*

role

string

enum

required

The role of the messages author. One of system, user, or assistant.

Allowed:

content

required

name

string

The name of the author of this message. May contain a-z, A-Z, 0-9, and underscores, with a maximum length of 64 characters.

tools

array of objects

A list of tools the model may call. Currently, only functions are supported as a tool.
Use this to provide a list of functions the model may generate JSON inputs for.
See the guide for more information and the list of supported models: https://readme.fireworks.ai/docs/function-calling#supported-models

tools

max_tokens

integer

Defaults to 200

The maximum number of tokens to generate in the completion.

If the token count of your prompt (previous messages) plus max_tokens exceed the model's context length, the behavior is depends on context_length_exceeded_behavior. By default, max_tokens will be lowered to fit in the context window instead of returning an error.

prompt_truncate_len

integer | null

Defaults to 1500

The size to which to truncate chat prompts. Earlier user/assistant messages will be evicted to fit the prompt into this length.

This should usually be set to a number << the max context size of the model, to allow enough remaining tokens for generating a response.

If omitted, you may receive "prompt too long" errors in your responses as conversations grow. Note that even with this set, you may still receive "prompt too long" errors if individual messages are too long for the model context window.

temperature

number | null

0 to 2

Defaults to 1

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.

top_p

number | null

0 to 1

Defaults to 1

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.

top_k

integer | null

1 to 128

Top-k sampling is another sampling method where the k most probable next tokens are filtered and the probability mass is redistributed among only those k next tokens. The value of k controls the number of candidates for the next token at each step during text generation.

frequency_penalty

number | null

-2 to 2

Defaults to 0

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.

Reasonable value is around 0.1 to 1 if the aim is to just reduce repetitive samples somewhat. If the aim is to strongly suppress repetition, then one can increase the coefficients up to 2, but this can noticeably degrade the quality of samples. Negative values can be used to increase the likelihood of repetition.

See also presence_penalty for penalizing tokens that have at least one appearance at a fixed rate.

presence_penalty

number | null

-2 to 2

Defaults to 0

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.

See also frequence_penalty for penalizing tokens at an increasing rate depending on how often they appear.

integer | null

1 to 128

Defaults to 1

How many completions to generate for each prompt.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

stop

Up to 4 sequences where the API will stop generating further tokens. The returned text will contain the stop sequence.

response_format

object | null

Allows to force the model to produce specific output format.

Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.

Optional JSON schema can be provided as response_format = {"type": "json_object", "schema": <json_schema>}.

Important: when using JSON mode, it's crucial to also instruct the model to produce JSON via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length. In this case the return value might not be a valid JSON.

stream

boolean | null

Defaults to false

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events
as they become available, with the stream terminated by a data: [DONE] message.

context_length_exceeded_behavior

string

enum

What to do if the token count of prompt plus max_tokens exceeds the model's context window.

Passing truncate limits the max_tokens to at most context_window_length - prompt_length. This is the default.

Passing error would trigger a request error.

The default of 'truncate' is selected as it allows to ask for high max_tokens value while respecting the context window length without having to do client-side prompt tokenization.

Note, that it differs from OpenAI's behavior that matches that of error.

Allowed:

user

string | null

A unique identifier representing your end-user, which can help monitor and detect abuse

200OK