Sarvam 30B vs Tiny Aya Global vs Voxtral Mini 3B 2507
Sarvam 30B comes out ahead, 31 to 21 and 15 on our weighted score.
- Our pick
Sarvam AI
Sarvam 30B
31/100- ECI—
- Price$0.02 / $0.10
- Context128K
CohereTiny Aya Global
15/100- ECI—
- Price—
- Context8K
Mistral AIVoxtral Mini 3B 2507
21/100- ECI—
- Price$0.04 / $0.04
- Context33K
Sarvam 30B is our pick
Sarvam 30B is the better all-round choice, scoring 31/100 against Voxtral Mini 3B 2507 (21) and Tiny Aya Global (15). It leads on 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
- Lowest priceSarvam 30B and Voxtral Mini 3B 2507Sarvam 30B $0.04 · Voxtral Mini 3B 2507 $0.04 per 1M tokens (3:1 blend) · Tiny Aya Global unpriced
- Longest contextSarvam 30BSarvam 30B 128,000 · Voxtral Mini 3B 2507 32,768 · Tiny Aya Global 8,000 tokens
- Widest inputsVoxtral Mini 3B 2507Sarvam 30B: Text · Tiny Aya Global: Text · Voxtral Mini 3B 2507: Text, Audio
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Sarvam 30B | Tiny Aya Global | Voxtral Mini 3B 2507 |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 25 | 35 |
| Context window | 40% | 24 | 0 | 0 |
| Overall | 100% | 31/100 | 15/100 | 21/100 |
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 | Tiny Aya GlobalCohere | Voxtral Mini 3B 2507Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.02 (best) | — | $0.04 |
| Output | $0.10 | — | $0.04 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.04 | — | $0.04 |
| Long-context rate | Same rate | — | Same rate |
| Price source | Median of 1 providers | — | Median of 2 providers |
| Limits | |||
| Context window | 128,000 tokens (best) | 8,000 tokens | 32,768 tokens |
| Max output | 128,000 tokens (best) | 8,000 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | No |
| Reasoning | Yes · low · medium · high | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenCC-BY-NC-4.0 | OpenApache 2.0 |
| API model ID | sarvam-30b | tiny-aya-global | — |
| API providers | 2 (best) | 1 | 2 (best) |
| Released | Feb 18, 2026 | Feb 17, 2026 | Jul 15, 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$0.40
- Tiny Aya Global—
- Voxtral Mini 3B 2507$0.48
Which should you choose?
Which is better: Sarvam 30B, Tiny Aya Global or Voxtral Mini 3B 2507?
Sarvam 30B is the better all-round choice, scoring 31/100 against Voxtral Mini 3B 2507 (21) and Tiny Aya Global (15). It leads on 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, Tiny Aya Global or Voxtral Mini 3B 2507?
Sarvam 30B is cheaper at $0.02 input / $0.10 output per million tokens (median across 1 API provider). Voxtral Mini 3B 2507 costs $0.04 input / $0.04 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.04 per million tokens for Sarvam 30B versus $0.04 for Voxtral Mini 3B 2507 (1× as much). Tiny Aya Global has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Sarvam 30B has not been scored yet, Tiny Aya Global has not been scored yet and Voxtral Mini 3B 2507 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Sarvam 30B, Tiny Aya Global and Voxtral Mini 3B 2507 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Sarvam 30B has the largest context window at 128,000 tokens, against 32,768 for Voxtral Mini 3B 2507 and 8,000 for Tiny Aya Global. Maximum output per response: Sarvam 30B up to 128,000, Tiny Aya Global up to 8,000, Voxtral Mini 3B 2507 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Sarvam 30B accepts text; Tiny Aya Global accepts text; Voxtral Mini 3B 2507 accepts text and audio. Voxtral Mini 3B 2507 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (CC-BY-NC-4.0 and Apache 2.0), so you can self-host them.
Which is newer?
Sarvam 30B is the newest, released Feb 18, 2026. Tiny Aya Global came out Feb 17, 2026; Voxtral Mini 3B 2507 came out Jul 15, 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 Oct 4, 2026.
