Nebius pricing overview
TokenWatch tracks 12 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Nebius text-model pricing
Text offerings ranked by the Agentic workload mix. Change the calculator mix for a workload-specific result.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| nvidia | nebius | NVIDIA: Nemotron 3 Nano 30B A3B | $0.060 | $0.240 | $0.0060 | $0.0085 |
| qwen | nebius | Qwen: Qwen3 30B A3B Instruct 2507 | $0.100 | $0.300 | $0.010 | $0.014 |
| qwen | nebius | Qwen: Qwen3 32B | $0.100 | $0.300 | $0.010 | $0.014 |
| nebius | Google: Gemma 3 27B | $0.100 | $0.300 | $0.010 | $0.014 | |
| nous | nebius | Nous: Hermes 4 70B | $0.130 | $0.400 | $0.013 | $0.018 |
| meta | nebius | Meta: Llama 3.3 70B Instruct | $0.130 | $0.400 | $0.013 | $0.018 |
| openai | nebius | OpenAI: gpt-oss-120b | $0.150 | $0.600 | $0.015 | $0.021 |
| openai | nebius | OpenAI: gpt-oss-120b (batch) | $0.150 | $0.600 | $0.015 | $0.021 |
| qwen | nebius | Qwen: Qwen2.5 VL 72B Instruct | $0.250 | $0.750 | $0.025 | $0.034 |
| nous | nebius | Nous: Hermes 4 405B | $1.00 | $3.00 | $0.100 | $0.137 |
| qwen | nebius | Qwen: Qwen3 235B A22B Instruct 2507 | $0.200 | $0.600 | — | $0.202 |
| z-ai | nebius | Z.ai: GLM 5.1 | $1.40 | $4.40 | — | $1.41 |
Pricing refreshed 2026-08-31 from public provider APIs. Verify prices on the provider's official pricing page before committing spend.