LiteLLMModels

Sarvam M API Pricing

As of October 10, 2026, Sarvam M is free to use on Sarvam. It has an 8,192-token context window and returns up to 32,000 tokens per response.

Model ID sarvam/sarvam-mPrices updated Checked
Price
Free
Cache read
$0 / 1M tokens
Context window
8,192 tokens
Max output
32,000 tokens
Providers
1
Added to LiteLLM
July 2025

Sarvam M pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Sarvamsarvam/sarvam-m$0$0$0$08K

Other Sarvam M prices on Sarvam

Cache write, 1 hour$0 per 1M tokens

What Sarvam M costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Sarvam$0

Sarvam M features

Use Sarvam M with LiteLLM

Call Sarvam M through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="sarvam/sarvam-m",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: sarvam-m
    litellm_params:
      model: sarvam/sarvam-m
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "sarvam-m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Sarvam M FAQ

How much does Sarvam M cost?

Sarvam M is free to use on Sarvam.

What is the context window of Sarvam M?

Sarvam M has an 8,192-token context window and returns up to 32,000 tokens per response.

Which providers offer Sarvam M?

Sarvam M is available from Sarvam through LiteLLM, using the model name sarvam/sarvam-m.

How do I call Sarvam M with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="sarvam/sarvam-m", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Sarvam M support?

Sarvam M supports reasoning.

When did LiteLLM add Sarvam M?

Sarvam M was added to LiteLLM's model price file in July 2025.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.

LiteLLM docs: Sarvam.

Provider pages: Sarvam.