Fournisseur · 2026-05-12
nebius
| Modèle | Entrée / 1M | Sortie / 1M | Contexte | Fournisseurs | Tags |
|---|---|---|---|---|---|
| Hermes-4-70B | $0.130 | $0.400 | 128K | 1 | tools · json · reasoning · open-weights |
| INTELLECT-3 | $0.200 | $1.10 | 128K | 1 | tools · json · open-weights |
| Hermes-4-405B | $1.00 | $3.00 | 128K | 1 | tools · json · reasoning · open-weights |
| Gemma-2-2b-itdérivé | $0.020 | $0.060 | 8K | 1 | open-weights |
| Nemotron-3-Nano-Omnidérivé | $0.060 | $0.240 | 66K | 1 | tools · json · reasoning · open-weights |
| gpt-oss-120b-fastdérivé | $0.100 | $0.500 | 8K | 1 | tools · json · reasoning · open-weights |
| Qwen3-Next-80B-A3B-Thinking-fastdérivé | $0.150 | $1.20 | 8K | 1 | tools · json · reasoning · open-weights |
| MiniMax-M2.5-fastdérivé | $0.300 | $1.20 | 8K | 1 | tools · json · reasoning · open-weights |
| Llama-3.1-Nemotron-Ultra-253B-v1dérivé | $0.600 | $1.80 | 128K | 1 | tools · json · open-weights |
| DeepSeek-V3.2-fastdérivé | $0.400 | $2.00 | 8K | 1 | tools · json · reasoning · open-weights |
| Qwen3-235B-A22B-Thinking-2507-fastdérivé | $0.500 | $2.00 | 8K | 1 | tools · json · reasoning · open-weights |
| Kimi-K2.5-fastdérivé | $0.500 | $2.50 | 256K | 1 | tools · json · reasoning · vision · open-weights |
| Qwen3.5-397B-A17B-fastdérivé | $0.600 | $3.60 | 8K | 1 | tools · json · reasoning · open-weights |
Frequently asked questions
How many AI models does nebius offer?
We track 3 canonical nebius models plus 10 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.
Which nebius model is the cheapest?
Hermes-4-70B is currently the lowest-priced nebius model, at $0.130 per 1M input tokens and $0.400 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which nebius model has the largest context window?
Hermes-4-70B leads at 128K tokens. This is the total of prompt + completion.
Which nebius models support tool calling?
Multiple nebius models support tool calling, with Hermes-4-70B being a popular pick. The capability column in the table above marks every model with nebius tool-calling support.
What are the best alternatives to nebius?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this nebius pricing data?
Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top nebius models
- Hermes-4-70B$0.13 in / $0.40 out
- INTELLECT-3$0.20 in / $1.10 out
- Hermes-4-405B$1.00 in / $3.00 out
Browse by use case
Browse by capability
Dernière mise à jour :
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.