Nebius
Inference providerdocs.nebius.com ↗
Models on Nebius · prices & measurements for models served by Nebius’s APIUSD / MTOK · VERIFIED 4 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
 Qwen3 30B A3B Instruct 2507Qwen | $0.10 | $0.30 | 262K | fp8 | 0.51s° | 139° tok/s | — | $0.048 elsewhere |
| Qwen3 32BQwen | $0.10 | $0.30 | 41K | fp8 | 1.6s° | 23° tok/s | — | $0.08 elsewhere |
 Gemma 3 27BGoogle | $0.10 | $0.30 | 110K | fp8 | 1.3s° | 45° tok/s | 4/5 | $0.08 elsewhere |
| NRHermes 4 70BNous Research | $0.13 | $0.40 | 131K | fp8 | 0.9s° | 109° tok/s | — | only provider |
 Llama 3.3 70B InstructMeta | $0.13 | $0.40 | 131K | fp8 | 15s° | 3° tok/s | 5/5 | $0.10 elsewhere |
| Qwen3 Next 80B A3B ThinkingQwenBEST PRICE | $0.15 | $1.20 | 128K | fp8 | 1.3s° | 103° tok/s | — | cheapest here |
 gpt-oss-120bOpenAI | $0.15 | $0.60 | 131K | fp4 | 0.75s° | 286° tok/s | — | $0.03 elsewhere |
| Qwen3 235B A22B Instruct 2507Qwen | $0.20 | $0.60 | 262K | fp8 | 1.1s° | 77° tok/s | 5/5 | $0.087 elsewhere |
| Qwen2.5 VL 72B InstructQwenBEST PRICE | $0.25 | $0.75 | 32K | fp8 | 2.4s° | 36° tok/s | — | cheapest here |
| NRHermes 4 405BNous Research | $1.00 | $3.00 | 131K | fp8 | 1.8s° | 29° tok/s | — | only provider |
 GLM 5.1Z.ai | $1.40 | $4.40 | 203K | fp8 | 1.8s° | 31° tok/s | — | $0.91 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) for Nebius’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page