LLM Perks

Sarvam M

Free right now Small
Open weights

Sarvam M is a language model. It is currently free at 1 provider with up to 33K tokens of context. Its weights are open, so it can also run locally.

Context
33K tokens
Type
Text
License
Open weights

Where to use Sarvam M for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
Together AI
sarvamai/sarvam-m
33K Fair use (depends on server load) — Open

Quick start

curl https://api.together.xyz/v1/chat/completions \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sarvamai/sarvam-m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for Together AI. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
5.3
GPQA Diamond
41.6%
Humanity's Last Exam
3.1%
Terminal-Bench Hard
2.3%
τ²-Bench
0.0%
Long context (LCR)
0.0%

Source: Artificial Analysis · Sarvam M (Reasoning, based on Mistral Small 3.1)

FAQ

Is Sarvam M free?

Yes. As of September 26, 2026, Sarvam M is free at Together AI. Each provider has its own limits — see the table above.

What is the context window of Sarvam M?

The largest context among free routes is 32,768 tokens. Some providers cap it lower.

How do I call Sarvam M via API?

Use any OpenAI-compatible client with base URL https://api.together.xyz/v1, model ID sarvamai/sarvam-m, and a Together AI key.

How good is Sarvam M?

Artificial Analysis Intelligence Index: 5.3, GPQA Diamond: 42%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Sarvam M open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.