model'sarvam-105b' | 'sarvam-30b' required
Supported chat completion model IDs: sarvam-30b, sarvam-105b.
temperaturenumber double nullable
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_pnumber double nullable
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.
reasoning_effort'low' | 'medium' | 'high'
max_tokensinteger nullable
The maximum number of tokens that can be generated in the chat completion.
streamboolean nullable
If set to true, the model response data will be streamed to the client
as it is generated using server-sent events.
ninteger nullable
How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.
seedinteger nullable
This feature is in Beta.
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.
frequency_penaltynumber double nullable
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.
presence_penaltynumber double nullable
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.
wiki_groundingboolean nullable
If set to true, the model response will be wiki grounded.