Chat

Chat Completions

Calls Sarvam LLM API to get the chat completion. Supported model(s): sarvam-m.

Headers

api-subscription-keystringRequired

Request

This endpoint expects an object.
messageslist of objectsRequired

A list of messages comprising the conversation so far.

modelenumRequired

Model ID used to generate the response, like sarvam-m.

Allowed values:
temperaturedoubleOptional>=0<=2Defaults to 0.2

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_pdoubleOptional>=0<=1Defaults 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.

reasoning_effortenumOptional
Allowed values:
max_tokensintegerOptional

The maximum number of tokens that can be generated in the chat completion.

streambooleanOptionalDefaults to false

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

stopstring or list of stringsOptional

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

nintegerOptional>=1<=128Defaults to 1

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.

seedintegerOptional>=-9223372036854776000<=9223372036854776000

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_penaltydoubleOptional>=-2<=2Defaults 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.

presence_penaltydoubleOptional>=-2<=2Defaults 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.

wiki_groundingbooleanOptionalDefaults to false

If this parameter is enabled, then the model uses a RAG based approach to retrieve relevant chunks from Wikipedia and uses them to answer the question. This is particularly useful for queries seeking factual information.

Response

Successful Response

idstring

A unique identifier for the chat completion.

choiceslist of objects

A list of chat completion choices. Can be more than one if n is greater than 1.

createdinteger

The Unix timestamp (in seconds) of when the chat completion was created.

modelstring

The model used for the chat completion.

object"chat.completion"

The object type, which is always chat.completion.

usageobjectOptional

Errors