GLM-4.5-Air vs Granite-4.0-H-Small vs Llama 3.3 Nemotron Super 49B v1.5
Granite-4.0-H-Small comes out ahead, 63 to 50 and 49 on our weighted score, and it is the cheaper option too.
Z.ai (Zhipu)GLM-4.5-Air
49/100- ECI—
- Price$0.20 / $1.10
- Context131K
- Our pick
IBMGranite-4.0-H-Small
63/100- ECI—
- Price$0.064 / $0.265
- Context131K
NVIDIALlama 3.3 Nemotron Super 49B v1.5
50/100- ECI—
- Price$0.40 / $0.40
- Context131K
Granite-4.0-H-Small is our pick
Granite-4.0-H-Small is the better all-round choice, scoring 63/100 against Llama 3.3 Nemotron Super 49B v1.5 (50) and GLM-4.5-Air (49). It leads 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 priceGranite-4.0-H-SmallGranite-4.0-H-Small $0.114 · Llama 3.3 Nemotron Super 49B v1.5 $0.40 · GLM-4.5-Air $0.425 per 1M tokens (3:1 blend)
- Longest contextAbout the sameGLM-4.5-Air 131,072 · Granite-4.0-H-Small 131,072 · Llama 3.3 Nemotron Super 49B v1.5 131,072 tokens
- Widest inputsSame inputsGLM-4.5-Air: Text · Granite-4.0-H-Small: Text · Llama 3.3 Nemotron Super 49B v1.5: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | GLM-4.5-Air | Granite-4.0-H-Small | Llama 3.3 Nemotron Super 49B v1.5 |
|---|---|---|---|---|
| Price | 50% | 68 | 95 | 69 |
| Inputs & features | 30% | 35 | 35 | 35 |
| Context window | 20% | 24 | 24 | 24 |
| Overall | 100% | 49/100 | 63/100 | 50/100 |
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 | GLM-4.5-AirZ.ai (Zhipu) | Granite-4.0-H-SmallIBM | Llama 3.3 Nemotron Super 49B v1.5NVIDIA |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.20 | $0.064 (best) | $0.40 |
| Output | $1.10 | $0.265 (best) | $0.40 |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.425 | $0.114 (best) | $0.40 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Official watsonx.ai API | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens | 131,072 tokens | 131,072 tokens |
| Max output | 98,304 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | glm-4.5-air | ibm/granite-4-h-small | nvidia/llama-3.3-nemotron-super-49b-v1.5 |
| API providers | 13 (best) | 1 | 2 |
| Released | Jul 28, 2025 | Oct 2, 2025 | Jul 25, 2025 |
| Knowledge cutoff | Apr 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GLM-4.5-Air$4.20
- Granite-4.0-H-Small$1.17
- Llama 3.3 Nemotron Super 49B v1.5$4.80
Which should you choose?
Which is better: GLM-4.5-Air, Granite-4.0-H-Small or Llama 3.3 Nemotron Super 49B v1.5?
Granite-4.0-H-Small is the better all-round choice, scoring 63/100 against Llama 3.3 Nemotron Super 49B v1.5 (50) and GLM-4.5-Air (49). It leads 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, GLM-4.5-Air, Granite-4.0-H-Small or Llama 3.3 Nemotron Super 49B v1.5?
Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Llama 3.3 Nemotron Super 49B v1.5 costs $0.40 input / $0.40 output per million tokens (median across 1 API provider; free on Nvidia); GLM-4.5-Air costs $0.20 input / $1.10 output per million tokens (official Z.AI 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 $0.40 for Llama 3.3 Nemotron Super 49B v1.5 (3.5× as much) and $0.425 for GLM-4.5-Air (3.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GLM-4.5-Air has not been scored yet, Granite-4.0-H-Small has not been scored yet and Llama 3.3 Nemotron Super 49B v1.5 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GLM-4.5-Air, Granite-4.0-H-Small and Llama 3.3 Nemotron Super 49B v1.5 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?
GLM-4.5-Air, Granite-4.0-H-Small and Llama 3.3 Nemotron Super 49B v1.5 share the same 131,072-token context window. Maximum output per response: GLM-4.5-Air up to 98,304, Granite-4.0-H-Small up to 131,072, Llama 3.3 Nemotron Super 49B v1.5 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
GLM-4.5-Air accepts text; Granite-4.0-H-Small accepts text; Llama 3.3 Nemotron Super 49B v1.5 accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Granite-4.0-H-Small is the newest, released Oct 2, 2025. GLM-4.5-Air came out Jul 28, 2025; Llama 3.3 Nemotron Super 49B v1.5 came out Jul 25, 2025. Knowledge cutoff: GLM-4.5-Air Apr 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.
