MinerU2.5 2509 1.2B vs Voxtral Small 24B 2507 vs Granite-4.0-H-Micro
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Opendatalab
MinerU2.5 2509 1.2B
58/100- ECI—
- Price$0.024 / $0.071
- Context16K
Mistral AI
Voxtral Small 24B 2507
57/100- ECI—
- Price$0.10 / $0.40
- Context33K
IBM
Granite-4.0-H-Micro
64/100- ECI—
- Price$0.017 / $0.112
- Context131K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Micro 64/100, MinerU2.5 2509 1.2B 58/100, Voxtral Small 24B 2507 57/100) compare the available specifications and 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 priceMinerU2.5 2509 1.2BMinerU2.5 2509 1.2B $0.036 · Granite-4.0-H-Micro $0.041 · Voxtral Small 24B 2507 $0.175 per 1M tokens (3:1 blend)
- Longest contextGranite-4.0-H-MicroGranite-4.0-H-Micro 131,072 · Voxtral Small 24B 2507 32,768 · MinerU2.5 2509 1.2B 16,384 tokens
- Widest inputsMinerU2.5 2509 1.2B and Voxtral Small 24B 2507MinerU2.5 2509 1.2B: Text, Images · Voxtral Small 24B 2507: Text, Audio · Granite-4.0-H-Micro: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | MinerU2.5 2509 1.2B | Voxtral Small 24B 2507 | Granite-4.0-H-Micro |
|---|---|---|---|---|
| Price | 50% | 100 | 82 | 100 |
| Inputs & features | 30% | 25 | 45 | 25 |
| Context window | 20% | 0 | 11 | 32 |
| Specs & price only | 100% | 58/100 | 57/100 | 64/100 |
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 | MinerU2.5 2509 1.2BOpendatalab | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.024 | $0.10 | $0.017 (best) |
| Output | $0.071 (best) | $0.40 | $0.112 |
| Cached input | — | — | — |
| Blended (3:1) | $0.036 (best) | $0.175 | $0.041 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Mistral API | Median of 1 providers |
| Limits | |||
| Context window | 16,384 tokens | 32,768 tokens | 131,072 tokens (best) |
| Max output | — | 32,768 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | No | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenAGPL-3.0 | OpenApache 2.0 | Open |
| API model ID | — | voxtral-small-latest | — |
| API providers | 1 | 9 (best) | 1 |
| Released | Sep 17, 2025 | Jul 15, 2025 | 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.
- MinerU2.5 2509 1.2B$0.381
Voxtral Small 24B 2507$1.80
Granite-4.0-H-Micro$0.394
Which should you choose?
Which is better: MinerU2.5 2509 1.2B, Voxtral Small 24B 2507 or Granite-4.0-H-Micro?
There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Micro 64/100, MinerU2.5 2509 1.2B 58/100, Voxtral Small 24B 2507 57/100) compare the available specifications and 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, MinerU2.5 2509 1.2B, Voxtral Small 24B 2507 or Granite-4.0-H-Micro?
MinerU2.5 2509 1.2B is cheaper at $0.024 input / $0.071 output per million tokens (median across 1 API provider). Granite-4.0-H-Micro costs $0.017 input / $0.112 output per million tokens (median across 1 API provider); Voxtral Small 24B 2507 costs $0.10 input / $0.40 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.036 per million tokens for MinerU2.5 2509 1.2B versus $0.041 for Granite-4.0-H-Micro (1.1× as much) and $0.175 for Voxtral Small 24B 2507 (4.9× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MinerU2.5 2509 1.2B has not been scored yet, Voxtral Small 24B 2507 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 MinerU2.5 2509 1.2B, Voxtral Small 24B 2507 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 MinerU2.5 2509 1.2B 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 Small 24B 2507 and 16,384 for MinerU2.5 2509 1.2B. Maximum output per response: Voxtral Small 24B 2507 up to 32,768, Granite-4.0-H-Micro up to 131,072 tokens.
Which can read images, PDFs, audio or video?
MinerU2.5 2509 1.2B accepts text and images; Voxtral Small 24B 2507 accepts text and audio; Granite-4.0-H-Micro accepts text. MinerU2.5 2509 1.2B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (AGPL-3.0 and Apache 2.0), so you can self-host them.
Which is newer?
Granite-4.0-H-Micro is the newest, released Oct 2, 2025. MinerU2.5 2509 1.2B came out Sep 17, 2025; Voxtral Small 24B 2507 came out Jul 15, 2025.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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 18, 2026.