Kimi K3 vs NVIDIA Nemotron 3 Super 120B
moonshotai/kimi-k3 · nvidia/nemotron-3-super-120b
As of November 3, 2026, NVIDIA Nemotron 3 Super 120B is the cheaper API on UberLLM: $0.0008 per million input tokens and $0.0062 per million output, versus $0.0017 / $0.0781 for Kimi K3, about 92% 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 NVIDIA Nemotron 3 Super 120B to cut cost; choose Kimi K3 when context size wins. Kimi K3 carries the larger context window (1,000,000 vs 256,000 tokens), which can matter for long-document work.
Kimi K3 vs NVIDIA Nemotron 3 Super 120B, side by side
| Spec | Kimi K3 | NVIDIA Nemotron 3 Super 120B |
|---|---|---|
| Price · input / 1M | $0.0017 | $0.0008 |
| Price · output / 1M | $0.0781 | $0.0062 |
| Context length | 1,000,000 | 256,000 |
| Max output tokens | 131,072 | 32,000 |
| Input modalities | text, image | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | — |
| Reasoning | Yes | — |
| % off list | 99.3% off | 99.7% off |
| First token, median (7 days) | 3.3 s (1,160 requests) | — |
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?
Kimi K3 vs NVIDIA Nemotron 3 Super 120B — FAQ
Is Kimi K3 or NVIDIA Nemotron 3 Super 120B cheaper?
NVIDIA Nemotron 3 Super 120B is cheaper on a blended token mix, by about 92%. 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 Kimi K3 and NVIDIA Nemotron 3 Super 120B?
Kimi K3: $0.0017 in / $0.0781 out per 1M tokens. NVIDIA Nemotron 3 Super 120B: $0.0008 in / $0.0062 out per 1M tokens. That's roughly a 92% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Kimi K3 and NVIDIA Nemotron 3 Super 120B 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.