Voxtral Mini 3B 2507 vs DeepSeek OCR 2 vs Granite-4.0-H-Micro
Granite-4.0-H-Micro comes out ahead, 65 to 61 and 32 on our weighted score.
Mistral AIVoxtral Mini 3B 2507
61/100- ECI—
- Price$0.04 / $0.04
- Context33K
DeepSeekDeepSeek OCR 2
32/100- ECI—
- Price$0.89 / $1.47
- Context8K
- Our pick
IBMGranite-4.0-H-Micro
65/100- ECI—
- Price$0.017 / $0.112
- Context131K
Granite-4.0-H-Micro is our pick
Granite-4.0-H-Micro is the better all-round choice, scoring 65/100 against Voxtral Mini 3B 2507 (61) and DeepSeek OCR 2 (32). It leads on context window. 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 · DeepSeek OCR 2 $1.03 per 1M tokens (3:1 blend)
- Longest contextGranite-4.0-H-MicroGranite-4.0-H-Micro 131,072 · Voxtral Mini 3B 2507 32,768 · DeepSeek OCR 2 8,192 tokens
- Widest inputsVoxtral Mini 3B 2507 and DeepSeek OCR 2Voxtral Mini 3B 2507: Text, Audio · DeepSeek OCR 2: Text, Images · Granite-4.0-H-Micro: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Voxtral Mini 3B 2507 | DeepSeek OCR 2 | Granite-4.0-H-Micro |
|---|---|---|---|---|
| Price | 50% | 100 | 49 | 100 |
| Inputs & features | 30% | 35 | 25 | 35 |
| Context window | 20% | 0 | 0 | 24 |
| Overall | 100% | 61/100 | 32/100 | 65/100 |
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 | Voxtral Mini 3B 2507Mistral AI | DeepSeek OCR 2DeepSeek | Granite-4.0-H-MicroIBM |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.04 | $0.89 | $0.017 (best) |
| Output | $0.04 (best) | $1.47 | $0.112 |
| Cached input | — | — | — |
| Blended (3:1) | $0.04 (best) | $1.03 | $0.041 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 1 providers | Median of 1 providers |
| Limits | |||
| Context window | 32,768 tokens | 8,192 tokens | 131,072 tokens (best) |
| Max output | 32,768 tokens | 8,192 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | OpenApache 2.0 | Open | Open |
| API model ID | — | — | — |
| API providers | 2 (best) | 2 (best) | 1 |
| Released | Jul 15, 2025 | Jan 27, 2026 | Oct 2, 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.
- Voxtral Mini 3B 2507$0.48
- DeepSeek OCR 2$11.83
- Granite-4.0-H-Micro$0.394
Which should you choose?
Which is better: Voxtral Mini 3B 2507, DeepSeek OCR 2 or Granite-4.0-H-Micro?
Granite-4.0-H-Micro is the better all-round choice, scoring 65/100 against Voxtral Mini 3B 2507 (61) and DeepSeek OCR 2 (32). It leads on context window. 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, Voxtral Mini 3B 2507, DeepSeek OCR 2 or Granite-4.0-H-Micro?
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); DeepSeek OCR 2 costs $0.89 input / $1.47 output per million tokens (median across 1 API provider). 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 $1.03 for DeepSeek OCR 2 (26× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Voxtral Mini 3B 2507 has not been scored yet, DeepSeek OCR 2 has not been scored yet and Granite-4.0-H-Micro has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Voxtral Mini 3B 2507, DeepSeek OCR 2 and Granite-4.0-H-Micro yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that DeepSeek OCR 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Granite-4.0-H-Micro has the largest context window at 131,072 tokens, against 32,768 for Voxtral Mini 3B 2507 and 8,192 for DeepSeek OCR 2. Maximum output per response: Voxtral Mini 3B 2507 up to 32,768, DeepSeek OCR 2 up to 8,192, Granite-4.0-H-Micro up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Voxtral Mini 3B 2507 accepts text and audio; DeepSeek OCR 2 accepts text and images; Granite-4.0-H-Micro accepts text. 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?
DeepSeek OCR 2 is the newest, released Jan 27, 2026. Granite-4.0-H-Micro came out Oct 2, 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.
