Sarvam-M vs Tiny Aya Earth
Tiny Aya Earth comes out ahead, 15 to 6 on our weighted score.
Sarvam AI
Sarvam-M
6/100- ECI—
- Price—
- Context33K
- Our pick
CohereTiny Aya Earth
15/100- ECI—
- Price—
- Context8K
Add a model
Make it a three-way comparison.
Tiny Aya Earth is our pick
Tiny Aya Earth is the better all-round choice, scoring 15/100 against Sarvam-M (6). It leads on inputs & features. 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-MSarvam-M 32,768 · Tiny Aya Earth 8,000 tokens
- Widest inputsSame inputsSarvam-M: Text · Tiny Aya Earth: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Sarvam-M | Tiny Aya Earth |
|---|---|---|---|
| Inputs & features | 60% | 10 | 25 |
| Context window | 40% | 0 | 0 |
| Overall | 100% | 6/100 | 15/100 |
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-MSarvam AI | Tiny Aya EarthCohere |
|---|---|---|
| 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 | 32,768 tokens (best) | 8,000 tokens |
| Max output | 32,768 tokens (best) | 8,000 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | Yes | No |
| Tool calling | No | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | OpenApache 2.0 | OpenCC-BY-NC-4.0 |
| API model ID | — | tiny-aya-earth |
| API providers | — | 1 |
| Released | May 20, 2025 | Feb 17, 2026 |
| 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-M—
- Tiny Aya Earth—
Which should you choose?
Which is better: Sarvam-M or Tiny Aya Earth?
Tiny Aya Earth is the better all-round choice, scoring 15/100 against Sarvam-M (6). It leads on inputs & features. 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-M or Tiny Aya Earth?
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-M has not been scored yet and Tiny Aya Earth has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Sarvam-M and Tiny Aya Earth 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-M has the largest context window at 32,768 tokens, against 8,000 for Tiny Aya Earth. Maximum output per response: Sarvam-M up to 32,768, Tiny Aya Earth up to 8,000 tokens.
Which can read images, PDFs, audio or video?
Sarvam-M accepts text; Tiny Aya Earth accepts text. They handle the same number of input types.
Are any of these open source?
Yes, both publish their weights (Apache 2.0 and CC-BY-NC-4.0), so you can self-host them.
Which is newer?
Tiny Aya Earth is the newest, released Feb 17, 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.
