Apertus 8B vs Granite-4.0-H-Small vs Voxtral Small 24B 2507
Granite-4.0-H-Small comes out ahead, 63 to 56 and 55 on our weighted score, and it is the cheaper option too.
Swiss AI
Apertus 8B
56/100- ECI—
- Price$0.10 / $0.20
- Context66K
- Our pick
IBMGranite-4.0-H-Small
63/100- ECI—
- Price$0.064 / $0.265
- Context131K
Mistral AIVoxtral Small 24B 2507
55/100- ECI—
- Price$0.10 / $0.30
- Context33K
Granite-4.0-H-Small is our pick
Granite-4.0-H-Small is the better all-round choice, scoring 63/100 against Apertus 8B (56) and Voxtral Small 24B 2507 (55). It leads on price and 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 priceGranite-4.0-H-SmallGranite-4.0-H-Small $0.114 · Apertus 8B $0.125 · Voxtral Small 24B 2507 $0.15 per 1M tokens (3:1 blend)
- Longest contextGranite-4.0-H-SmallGranite-4.0-H-Small 131,072 · Apertus 8B 65,536 · Voxtral Small 24B 2507 32,768 tokens
- Widest inputsVoxtral Small 24B 2507Apertus 8B: Text · Granite-4.0-H-Small: Text · Voxtral Small 24B 2507: Text, Audio
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Apertus 8B | Granite-4.0-H-Small | Voxtral Small 24B 2507 |
|---|---|---|---|---|
| Price | 50% | 93 | 95 | 89 |
| Inputs & features | 30% | 25 | 35 | 35 |
| Context window | 20% | 12 | 24 | 0 |
| Overall | 100% | 56/100 | 63/100 | 55/100 |
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 | Apertus 8BSwiss AI | Granite-4.0-H-SmallIBM | Voxtral Small 24B 2507Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.10 | $0.064 (best) | $0.10 |
| Output | $0.20 (best) | $0.265 | $0.30 |
| Cached input | — | — | — |
| Blended (3:1) | $0.125 | $0.114 (best) | $0.15 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official watsonx.ai API | Official Mistral API |
| Limits | |||
| Context window | 65,536 tokens | 131,072 tokens (best) | 32,768 tokens |
| Max output | 8,192 tokens | 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 | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | OpenApache 2.0 |
| API model ID | — | ibm/granite-4-h-small | voxtral-small-latest |
| API providers | 1 | 1 | 7 (best) |
| Released | Sep 2, 2025 | Oct 2, 2025 | Jul 15, 2025 |
| Knowledge cutoff | Sep 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Apertus 8B$1.40
- Granite-4.0-H-Small$1.17
- Voxtral Small 24B 2507$1.60
Which should you choose?
Which is better: Apertus 8B, Granite-4.0-H-Small or Voxtral Small 24B 2507?
Granite-4.0-H-Small is the better all-round choice, scoring 63/100 against Apertus 8B (56) and Voxtral Small 24B 2507 (55). It leads on price and 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, Apertus 8B, Granite-4.0-H-Small or Voxtral Small 24B 2507?
Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Apertus 8B costs $0.10 input / $0.20 output per million tokens (median across 1 API provider); Voxtral Small 24B 2507 costs $0.10 input / $0.30 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.114 per million tokens for Granite-4.0-H-Small versus $0.125 for Apertus 8B (1.1× as much) and $0.15 for Voxtral Small 24B 2507 (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Apertus 8B has not been scored yet, Granite-4.0-H-Small has not been scored yet and Voxtral Small 24B 2507 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Apertus 8B, Granite-4.0-H-Small and Voxtral Small 24B 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-Small has the largest context window at 131,072 tokens, against 65,536 for Apertus 8B and 32,768 for Voxtral Small 24B 2507. Maximum output per response: Apertus 8B up to 8,192, Granite-4.0-H-Small up to 131,072, Voxtral Small 24B 2507 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Apertus 8B accepts text; Granite-4.0-H-Small accepts text; Voxtral Small 24B 2507 accepts text and audio. Voxtral Small 24B 2507 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0 and Apache 2.0), so you can self-host them.
Which is newer?
Granite-4.0-H-Small is the newest, released Oct 2, 2025. Apertus 8B came out Sep 2, 2025; Voxtral Small 24B 2507 came out Jul 15, 2025. Knowledge cutoff: Apertus 8B Sep 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.
