Nebius API pricing
17 models · USD per 1M tokens · verified 2026-10-23
Nebius serves 17 of the models we track, 17 of them open-weights. The cheapest is Qwen3-30B-A3B-Instruct-2507 at $0.10 input and $0.30 output per million tokens. For 3 of these models, Nebius is the cheapest tracked host.
// models on Nebius
| model | lab | in $/1M | out $/1M | ctx | vs best price |
|---|---|---|---|---|---|
| Qwen3-30B-A3B-Instruct-2507 BEST | Alibaba (Qwen) | $0.10 | $0.30 | 262.1K | best |
| Gemma 3 27B IT | $0.10 | $0.30 | 131.1K | +50% | |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.14 | $0.28 | 1.05M | +94.4% |
| GLM-5.3-FlashX BEST | Z.AI (Zhipu) | $0.15 | $0.50 | 1M | −59.7% |
| GPT OSS 120B | OpenAI | $0.15 | $0.60 | 131.1K | +273.4% |
| Qwen3 235B-A22B Instruct 2507 | Alibaba (Qwen) | $0.20 | $0.60 | 262.1K | +46.3% |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | 1.05M | +75% |
| MiniMax-M3 | MiniMax | $0.30 | $1.20 | 1M | best |
| Qwen3.8 27B | Alibaba (Qwen) | $0.45 | $3.00 | 262.1K | +40.3% |
| Qwen3.5 397B-A17B | Alibaba (Qwen) | $0.60 | $3.60 | 262.1K | best |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $0.95 | $4.00 | 262.1K | −50% |
| DeepSeek V4 Pro (0813) | DeepSeek | $1.32 | $3.96 | 1.05M | +100% |
| Muse Spark Open BEST | Meta | $1.25 | $4.25 | 1.05M | best |
| GLM-5.2 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| GLM-5.3 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| DeepSeek V4 Pro | DeepSeek | $1.75 | $3.50 | 1.05M | +34.6% |
| Kimi K3 | Moonshot AI | $3.00 | $15.00 | 1.05M | best |
// how to read this page
Prices are Nebius's base-tier list prices per million tokens. "vs best price" compares Nebius's blended price (3 × input + output) / 4 with the lowest price we track for the same model, whether it comes from the lab's own API or another host. Open each model for its full price history and every host that serves it.