← All providers
Nebius Token Factory
31 models · routes through the OpenAI-Compatible adapter
API endpoint
https://api.tokenfactory.nebius.com/v1
Required environment variables
- NEBIUS_API_KEY
Models
| Model | Context | Input | Output | Capabilities |
|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Pro | 1000k | $1.75 / 1M | $3.50 / 1M | tools, reasoning, open-weights |
| nvidia/nemotron-3-super-120b-a12b | 256k | $0.30 / 1M | $0.90 / 1M | tools, reasoning, open-weights |
| zai-org/GLM-5 | 200k | $1.00 / 1M | $3.20 / 1M | tools, reasoning |
| NousResearch/Hermes-4-405B | 128k | $1.00 / 1M | $3.00 / 1M | tools, reasoning, open-weights |
| NousResearch/Hermes-4-70B | 128k | $0.13 / 1M | $0.40 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | 128k | $0.10 / 1M | $0.30 / 1M | tools, open-weights |
| Qwen/Qwen3-32B | 128k | $0.10 / 1M | $0.30 / 1M | tools, open-weights |
| Qwen/Qwen3-Next-80B-A3B-Thinking | 128k | $0.15 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| PrimeIntellect/INTELLECT-3 | 128k | $0.20 / 1M | $1.10 / 1M | tools, open-weights |
| deepseek-ai/DeepSeek-V3.2 | 163k | $0.30 / 1M | $0.45 / 1M | tools, reasoning, open-weights |
| google/gemma-3-27b-it | 110k | $0.10 / 1M | $0.30 / 1M | tools, open-weights, vision |
| openai/gpt-oss-120b | 128k | $0.15 / 1M | $0.60 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3-Embedding-8B | 33k | $0.01 / 1M | free | open-weights |
| moonshotai/Kimi-K2.5 | 256k | $0.50 / 1M | $2.50 / 1M | tools, reasoning, open-weights, vision |
| moonshotai/Kimi-K2.5-fast | 256k | $0.50 / 1M | $2.50 / 1M | tools, reasoning, open-weights, vision |
| meta-llama/Llama-3.3-70B-Instruct | 128k | $0.13 / 1M | $0.40 / 1M | tools, open-weights |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | 32k | $0.06 / 1M | $0.24 / 1M | tools, open-weights |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 262k | $0.20 / 1M | $0.60 / 1M | tools, reasoning |
| Qwen/Qwen3-235B-A22B-Thinking-2507-fast | 8k | $0.50 / 1M | $2.00 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3-Next-80B-A3B-Thinking-fast | 8k | $0.15 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.5-397B-A17B | 262k | $0.60 / 1M | $3.60 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen3.5-397B-A17B-fast | 8k | $0.60 / 1M | $3.60 / 1M | tools, reasoning, open-weights |
| openai/gpt-oss-120b-fast | 8k | $0.10 / 1M | $0.50 / 1M | tools, reasoning, open-weights |
| deepseek-ai/DeepSeek-V3.2-fast | 8k | $0.40 / 1M | $2.00 / 1M | tools, reasoning, open-weights |
| MiniMaxAI/MiniMax-M2.5 | 197k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| MiniMaxAI/MiniMax-M2.5-fast | 8k | $0.30 / 1M | $1.20 / 1M | tools, reasoning, open-weights |
| nvidia/Nemotron-3-Nano-Omni | 66k | $0.06 / 1M | $0.24 / 1M | tools, reasoning, open-weights |
| Qwen/Qwen2.5-VL-72B-Instruct | 128k | $0.25 / 1M | $0.75 / 1M | tools, open-weights, vision |
| nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | 128k | $0.60 / 1M | $1.80 / 1M | tools, open-weights |
| google/gemma-2-2b-it | 8k | $0.02 / 1M | $0.06 / 1M | open-weights |
| meta-llama/Meta-Llama-3.1-8B-Instruct | 128k | $0.02 / 1M | $0.06 / 1M | tools, open-weights |
Sourced from models.dev. Pricing reflects the catalog at the time this page was rendered.