Sarvam 30B vs Sarvam-M
Sarvam 30B comes out ahead, 31 to 6 on our weighted score.
- Our pick
Sarvam AI
Sarvam 30B
31/100- ECI—
- Price—
- Context128K
Sarvam AI
Sarvam-M
6/100- ECI—
- Price—
- Context33K
Add a model
Make it a three-way comparison.
Sarvam 30B is our pick
Sarvam 30B is the better all-round choice, scoring 31/100 against Sarvam-M (6). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Longest contextSarvam 30BSarvam 30B 128,000 · Sarvam-M 32,768 tokens
- Widest inputsSame inputsSarvam 30B: Text · Sarvam-M: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Sarvam 30B | Sarvam-M |
|---|---|---|---|
| Inputs & features | 60% | 35 | 10 |
| Context window | 40% | 24 | 0 |
| Overall | 100% | 31/100 | 6/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Sarvam 30BSarvam AI | Sarvam-MSarvam AI |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | — | — |
| Output | — | — |
| Cached input | — | — |
| Blended (3:1) | — | — |
| Long-context rate | — | — |
| Price source | — | — |
| Limits | ||
| Context window | 128,000 tokens (best) | 32,768 tokens |
| Max output | 128,000 tokens (best) | 32,768 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | Yeslow · medium · high | Yes |
| Tool calling | Yes | No |
| Structured output | No | No |
| Availability | ||
| Weights | Open | OpenApache 2.0 |
| API model ID | sarvam-30b | — |
| API providers | 1 | — |
| Released | Feb 18, 2026 | May 20, 2025 |
| Knowledge cutoff | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Sarvam 30B—
- Sarvam-M—
Which should you choose?
Which is better: Sarvam 30B or Sarvam-M?
Sarvam 30B is the better all-round choice, scoring 31/100 against Sarvam-M (6). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Sarvam 30B or Sarvam-M?
None of these models has a published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Sarvam 30B has not been scored yet and Sarvam-M has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Sarvam 30B and Sarvam-M yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Sarvam-M does not support tool calling, which most coding agents need.
Which has the bigger context window?
Sarvam 30B has the largest context window at 128,000 tokens, against 32,768 for Sarvam-M. Maximum output per response: Sarvam 30B up to 128,000, Sarvam-M up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Sarvam 30B accepts text; Sarvam-M accepts text. They handle the same number of input types.
Are any of these open source?
Yes, both publish their weights (Apache 2.0), so you can self-host them.
Which is newer?
Sarvam 30B is the newest, released Feb 18, 2026. Sarvam-M came out May 20, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
