Granite-4.0-H-Micro vs DeepSeek OCR 2 vs Voxtral Mini 3B 2507
Granite-4.0-H-Micro comes out ahead, 65 to 61 and 32 on our weighted score.
- Our pick
IBMGranite-4.0-H-Micro
65/100- ECI—
- Price$0.017 / $0.112
- Context131K
DeepSeekDeepSeek OCR 2
32/100- ECI—
- Price$0.89 / $1.47
- Context8K
Mistral AIVoxtral Mini 3B 2507
61/100- ECI—
- Price$0.04 / $0.04
- Context33K
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 inputsDeepSeek OCR 2 and Voxtral Mini 3B 2507Granite-4.0-H-Micro: Text · DeepSeek OCR 2: Text, Images · 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 | DeepSeek OCR 2 | Voxtral Mini 3B 2507 |
|---|---|---|---|---|
| Price | 50% | 100 | 49 | 100 |
| Inputs & features | 30% | 35 | 25 | 35 |
| Context window | 20% | 24 | 0 | 0 |
| Overall | 100% | 65/100 | 32/100 | 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 | DeepSeek OCR 2DeepSeek | Voxtral Mini 3B 2507Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.017 (best) | $0.89 | $0.04 |
| Output | $0.112 | $1.47 | $0.04 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.041 | $1.03 | $0.04 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Median of 2 providers |
| Limits | |||
| Context window | 131,072 tokens (best) | 8,192 tokens | 32,768 tokens |
| Max output | 131,072 tokens (best) | 8,192 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | No | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache 2.0 |
| API model ID | — | — | — |
| API providers | 1 | 2 (best) | 2 (best) |
| Released | Oct 2, 2025 | Jan 27, 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.
- Granite-4.0-H-Micro$0.394
- DeepSeek OCR 2$11.83
- Voxtral Mini 3B 2507$0.48
Which should you choose?
Which is better: Granite-4.0-H-Micro, DeepSeek OCR 2 or Voxtral Mini 3B 2507?
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, Granite-4.0-H-Micro, DeepSeek OCR 2 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); 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. Granite-4.0-H-Micro has not been scored yet, DeepSeek OCR 2 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, DeepSeek OCR 2 and Voxtral Mini 3B 2507 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: Granite-4.0-H-Micro up to 131,072, DeepSeek OCR 2 up to 8,192, Voxtral Mini 3B 2507 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Micro accepts text; DeepSeek OCR 2 accepts text and images; Voxtral Mini 3B 2507 accepts text and audio. DeepSeek OCR 2 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.
