Parameters

CamelStep unifies parameters across providers where possible, but also supports provider-specific parameters for fine-grained control.

Common Parameters

model

stringRequired

ID of the model to use. e.g. "google/gemini-3.0-flash".

messages

arrayRequired

A list of messages comprising the conversation so far.

temperature

number

Sampling temperature between 0 and 2. Higher values like 0.8 make output more random.

max_tokens

integer

The maximum number of tokens to generate in the completion.

stream

boolean

If set to true, tokens will be sent as data-only Server-Sent Events.

Google Gemini

Official Docs

topP

number

The maximum cumulative probability of tokens to consider when sampling.

topK

integer

The maximum number of tokens to consider when sampling.

candidateCount

integer

Number of generated responses to return. Maps to "n" in OpenAI SDK.

Anthropic Claude

Official Docs

max_tokens

integerRequired

The maximum number of tokens to generate. Unlike other providers, this is often required.

system

string

A system prompt to provide context to the model. Can also be passed as a message with role "system".

stop_sequences

array

Custom text sequences that will cause the model to close generation.

OpenAI

Official Docs

frequency_penalty

number

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text.

presence_penalty

number

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.

logit_bias

map

Modify the likelihood of specified tokens appearing in the completion.

seed

integer

If specified, the system will make a best effort to sample deterministically.