Granite-4.0-H-Small vs Nemotron Nano 9B v2 vs Apertus 8B
Too close to call on our weighted score (Nemotron Nano 9B v2 64, Granite-4.0-H-Small 63, Apertus 8B 56). The right pick depends on what you value most.
IBMGranite-4.0-H-Small
63/100- ECI—
- Price$0.064 / $0.265
- Context131K
NVIDIANemotron Nano 9B v2
64/100- ECI—
- Price$0.06 / $0.23
- Context131K
Swiss AI
Apertus 8B
56/100- ECI—
- Price$0.10 / $0.20
- Context66K
Too close to call
It is close. Our weighted score puts them within 1 points (Nemotron Nano 9B v2 64/100, Granite-4.0-H-Small 63/100, Apertus 8B 56/100), so choose by what matters most for your work: Nemotron Nano 9B v2 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 priceNemotron Nano 9B v2Nemotron Nano 9B v2 $0.102 · Granite-4.0-H-Small $0.114 · Apertus 8B $0.125 per 1M tokens (3:1 blend)
- Longest contextGranite-4.0-H-Small and Nemotron Nano 9B v2Granite-4.0-H-Small 131,072 · Nemotron Nano 9B v2 131,072 · Apertus 8B 65,536 tokens
- Widest inputsSame inputsGranite-4.0-H-Small: Text · Nemotron Nano 9B v2: Text · Apertus 8B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Granite-4.0-H-Small | Nemotron Nano 9B v2 | Apertus 8B |
|---|---|---|---|---|
| Price | 50% | 95 | 97 | 93 |
| Inputs & features | 30% | 35 | 35 | 25 |
| Context window | 20% | 24 | 24 | 12 |
| Overall | 100% | 63/100 | 64/100 | 56/100 |
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-SmallIBM | Nemotron Nano 9B v2NVIDIA | Apertus 8BSwiss AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.064 | $0.06 (best) | $0.10 |
| Output | $0.265 | $0.23 | $0.20 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.114 | $0.102 (best) | $0.125 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official watsonx.ai API | Median of 3 providers | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens (best) | 131,072 tokens (best) | 65,536 tokens |
| Max output | 131,072 tokens (best) | 131,072 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache-2.0 |
| API model ID | ibm/granite-4-h-small | nvidia/nvidia-nemotron-nano-9b-v2 | — |
| API providers | 1 | 4 (best) | 1 |
| Released | Oct 2, 2025 | Aug 18, 2025 | Sep 2, 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.
- Granite-4.0-H-Small$1.17
- Nemotron Nano 9B v2$1.06
- Apertus 8B$1.40
Which should you choose?
Which is better: Granite-4.0-H-Small, Nemotron Nano 9B v2 or Apertus 8B?
It is close. Our weighted score puts them within 1 points (Nemotron Nano 9B v2 64/100, Granite-4.0-H-Small 63/100, Apertus 8B 56/100), so choose by what matters most for your work: Nemotron Nano 9B v2 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-Small, Nemotron Nano 9B v2 or Apertus 8B?
Nemotron Nano 9B v2 is cheaper at $0.06 input / $0.23 output per million tokens (median across 3 API providers; free on Nvidia). Granite-4.0-H-Small costs $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). At a typical mix of three input tokens to one output token, that is $0.102 per million tokens for Nemotron Nano 9B v2 versus $0.114 for Granite-4.0-H-Small (1.1× as much) and $0.125 for Apertus 8B (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Granite-4.0-H-Small has not been scored yet, Nemotron Nano 9B v2 has not been scored yet and Apertus 8B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Granite-4.0-H-Small, Nemotron Nano 9B v2 and Apertus 8B 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 and Nemotron Nano 9B v2 have the largest context windows (131,072 and 131,072 tokens), against 65,536 for Apertus 8B. Maximum output per response: Granite-4.0-H-Small up to 131,072, Nemotron Nano 9B v2 up to 131,072, Apertus 8B up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Small accepts text; Nemotron Nano 9B v2 accepts text; Apertus 8B accepts text. They handle the same number of input types.
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-Small is the newest, released Oct 2, 2025. Apertus 8B came out Sep 2, 2025; Nemotron Nano 9B v2 came out Aug 18, 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.
