Granite-4.0-H-Micro vs Sarvam 105B vs Voxtral Mini 3B 2507
Too close to call on our weighted score (Granite-4.0-H-Micro 65, Sarvam 105B 65, Voxtral Mini 3B 2507 61). The right pick depends on what you value most.
IBMGranite-4.0-H-Micro
65/100- ECI—
- Price$0.017 / $0.112
- Context131K
Sarvam AI
Sarvam 105B
65/100- ECI—
- Price$0.047 / $0.186
- Context131K
Mistral AIVoxtral Mini 3B 2507
61/100- ECI—
- Price$0.04 / $0.04
- Context33K
Too close to call
It is close. Our weighted score puts them within a point (Granite-4.0-H-Micro 65/100, Sarvam 105B 65/100, Voxtral Mini 3B 2507 61/100), so choose by what matters most for your work: Voxtral Mini 3B 2507 on price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceVoxtral Mini 3B 2507Voxtral Mini 3B 2507 $0.04 · Granite-4.0-H-Micro $0.041 · Sarvam 105B $0.082 per 1M tokens (3:1 blend)
- Longest contextGranite-4.0-H-Micro and Sarvam 105BGranite-4.0-H-Micro 131,072 · Sarvam 105B 131,072 · Voxtral Mini 3B 2507 32,768 tokens
- Widest inputsVoxtral Mini 3B 2507Granite-4.0-H-Micro: Text · Sarvam 105B: Text · Voxtral Mini 3B 2507: Text, Audio
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Granite-4.0-H-Micro | Sarvam 105B | Voxtral Mini 3B 2507 |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 35 | 35 | 35 |
| Context window | 20% | 24 | 24 | 0 |
| Overall | 100% | 65/100 | 65/100 | 61/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Granite-4.0-H-MicroIBM | Sarvam 105BSarvam AI | Voxtral Mini 3B 2507Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.017 (best) | $0.047 | $0.04 |
| Output | $0.112 | $0.186 | $0.04 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.041 | $0.082 | $0.04 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 2 providers | Median of 2 providers |
| Limits | |||
| Context window | 131,072 tokens (best) | 131,072 tokens (best) | 32,768 tokens |
| Max output | 131,072 tokens (best) | 131,072 tokens (best) | 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 | No | Yes · low · medium · high | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache 2.0 |
| API model ID | — | sarvam-105b | — |
| API providers | 1 | 3 (best) | 2 |
| Released | Oct 2, 2025 | Sep 1, 2025 | 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.
- Granite-4.0-H-Micro$0.394
- Sarvam 105B$0.842
- Voxtral Mini 3B 2507$0.48
Which should you choose?
Which is better: Granite-4.0-H-Micro, Sarvam 105B or Voxtral Mini 3B 2507?
It is close. Our weighted score puts them within a point (Granite-4.0-H-Micro 65/100, Sarvam 105B 65/100, Voxtral Mini 3B 2507 61/100), so choose by what matters most for your work: Voxtral Mini 3B 2507 on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Granite-4.0-H-Micro, Sarvam 105B or Voxtral Mini 3B 2507?
Voxtral Mini 3B 2507 is cheaper at $0.04 input / $0.04 output per million tokens (median across 2 API providers). Granite-4.0-H-Micro costs $0.017 input / $0.112 output per million tokens (median across 1 API provider); Sarvam 105B costs $0.047 input / $0.186 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 Voxtral Mini 3B 2507 versus $0.041 for Granite-4.0-H-Micro (1× as much) and $0.082 for Sarvam 105B (2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Granite-4.0-H-Micro has not been scored yet, Sarvam 105B 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 Granite-4.0-H-Micro, Sarvam 105B 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?
Granite-4.0-H-Micro and Sarvam 105B have the largest context windows (131,072 and 131,072 tokens), against 32,768 for Voxtral Mini 3B 2507. Maximum output per response: Granite-4.0-H-Micro up to 131,072, Sarvam 105B up to 131,072, Voxtral Mini 3B 2507 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Micro accepts text; Sarvam 105B 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 (Apache 2.0), so you can self-host them.
Which is newer?
Granite-4.0-H-Micro is the newest, released Oct 2, 2025. Sarvam 105B came out Sep 1, 2025; 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.
