NVIDIA Nemotron 3 Super 120B vs GLM 4.5 Air
nvidia/nemotron-3-super-120b · z-ai/glm-4.5-air
As of November 3, 2026, GLM 4.5 Air is the cheaper API on UberLLM: $0.0001 per million input tokens and $0.0008 per million output, versus $0.0008 / $0.0062 for NVIDIA Nemotron 3 Super 120B, about 86% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose GLM 4.5 Air to cut cost; choose NVIDIA Nemotron 3 Super 120B when context size wins. NVIDIA Nemotron 3 Super 120B carries the larger context window (256,000 vs 128,000 tokens), which can matter for long-document work.
NVIDIA Nemotron 3 Super 120B vs GLM 4.5 Air, side by side
| Spec | NVIDIA Nemotron 3 Super 120B | GLM 4.5 Air |
|---|---|---|
| Price · input / 1M | $0.0008 | $0.0001 |
| Price · output / 1M | $0.0062 | $0.0008 |
| Context length | 256,000 | 128,000 |
| Max output tokens | 32,000 | 32,768 |
| Input modalities | text | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Reasoning | — | Yes |
| % off list | 99.7% off | 99.9% off |
Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 3, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
NVIDIA Nemotron 3 Super 120B vs GLM 4.5 Air — FAQ
Is NVIDIA Nemotron 3 Super 120B or GLM 4.5 Air cheaper?
GLM 4.5 Air is cheaper on a blended token mix, by about 86%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between NVIDIA Nemotron 3 Super 120B and GLM 4.5 Air?
NVIDIA Nemotron 3 Super 120B: $0.0008 in / $0.0062 out per 1M tokens. GLM 4.5 Air: $0.0001 in / $0.0008 out per 1M tokens. That's roughly a 86% blended difference. Prices are live; UberLLM adds no fee.
Can I use both NVIDIA Nemotron 3 Super 120B and GLM 4.5 Air with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.