Nebius AI Studio
Price history
Blended ($/Mtok, 75% input / 25% output) price over time for every model this host serves. Click a legend entry to hide or show its line.
Hosted offerings
| Model | Variant | Input $/Mtok | Output $/Mtok | Confidence |
|---|---|---|---|---|
| Qwen/Qwen2.5-Coder-7B | – | $0.010000 | $0.030000 | medium |
| Qwen3-Embedding-8B | – | $0.010000 | $0.000000 | medium |
| meta-llama/Llama-Guard-3-8B | – | $0.020000 | $0.060000 | medium |
| meta-llama/Meta-Llama-3.1-8B-Instruct | – | $0.020000 | $0.060000 | medium |
| Qwen/Qwen2-VL-7B-Instruct | – | $0.020000 | $0.060000 | medium |
| mistralai/Mistral-Nemo-Instruct-2407 | – | $0.040000 | $0.120000 | medium |
| NVIDIA: Nemotron 3 Nano 30B A3B | fp8 | $0.060000 | $0.240000 | high |
| Qwen/Qwen2.5-32B-Instruct | – | $0.060000 | $0.200000 | medium |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | – | $0.060000 | $0.240000 | medium |
| nvidia/Nemotron-3-Nano-Omni | – | $0.060000 | $0.240000 | medium |
| nvidia/Nemotron-3_5-Lightning | – | $0.060000 | $0.240000 | medium |
| NVIDIA: Nemotron 3.5 Lightning (free) | – | $0.060000 | $0.240000 | medium |
| Qwen: Qwen3 14B | – | $0.080000 | $0.240000 | medium |
| Qwen/Qwen3-4B | – | $0.080000 | $0.240000 | medium |
| Qwen: Qwen3 30B A3B Instruct 2507 | fp8 | $0.100000 | $0.300000 | high |
| Google: Gemma 3 27B | fp8 | $0.100000 | $0.300000 | high |
| Google: Gemma 3 27B | – | $0.100000 | $0.300000 | medium |
| Llama 3.3 Nemotron Super 49B v1.5 | – | $0.100000 | $0.400000 | medium |
| Qwen: Qwen3 32B | – | $0.100000 | $0.300000 | medium |
| Qwen: Qwen3 30B A3B | – | $0.100000 | $0.300000 | medium |
| nvidia/Cosmos3-Super-Reasoner | – | $0.100000 | $0.300000 | medium |
| Qwen: Qwen3 30B A3B Instruct 2507 | – | $0.100000 | $0.300000 | medium |
| Meta: Llama 3.3 70B Instruct | – | $0.130000 | $0.400000 | medium |
| meta-llama/Meta-Llama-3.1-70B-Instruct | – | $0.130000 | $0.400000 | medium |
| Qwen2.5-72B-Instruct | – | $0.130000 | $0.400000 | medium |
| Qwen/Qwen2-VL-72B-Instruct | – | $0.130000 | $0.400000 | medium |
| NousResearch/Hermes-4-70B | – | $0.130000 | $0.400000 | medium |
| deepseek-ai/DeepSeek-V4-Flash | – | $0.140000 | $0.280000 | medium |
| deepseek-ai/DeepSeek-V4-Flash-0731 | – | $0.140000 | $0.280000 | medium |
| DeepSeek: DeepSeek V4 Flash 0731 | – | $0.140000 | $0.280000 | medium |
| OpenAI: gpt-oss-120b | fp4 | $0.150000 | $0.600000 | high |
| Qwen/QwQ-32B | – | $0.150000 | $0.450000 | medium |
| OpenAI: gpt-oss-120b | – | $0.150000 | $0.600000 | medium |
| Qwen: Qwen3 Next 80B A3B Thinking | – | $0.150000 | $1.200000 | medium |
| zai-org/GLM-5.3-Flash | – | $0.150000 | $0.500000 | medium |
| GLM-5.3-Flash | – | $0.150000 | $0.500000 | medium |
| Qwen: Qwen3 235B A22B Instruct 2507 | fp8 | $0.200000 | $0.600000 | high |
| Qwen: Qwen3 235B A22B | – | $0.200000 | $0.600000 | medium |
| Qwen: Qwen3 235B A22B | – | $0.200000 | $0.600000 | medium |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | – | $0.250000 | $0.750000 | medium |
| Qwen: Qwen2.5 VL 72B Instruct | – | $0.250000 | $0.750000 | medium |
| deepseek-ai/DeepSeek-V4.1-Flash | – | $0.300000 | $1.200000 | medium |
| MiniMax-M2.5 | – | $0.300000 | $1.200000 | medium |
| MiniMax-M3 | – | $0.300000 | $1.200000 | medium |
| NVIDIA: Nemotron 3 Super (free) | – | $0.300000 | $0.900000 | medium |
| DeepSeek: DeepSeek V4.1 Flash | – | $0.300000 | $1.200000 | medium |
| Qwen: Qwen3.8 27B (free) | – | $0.450000 | $3.000000 | medium |
| DeepSeek-V3 | – | $0.500000 | $1.500000 | medium |
| deepseek-ai/DeepSeek-V3-0324 | – | $0.500000 | $1.500000 | medium |
| Llama 3.1 Nemotron Ultra 253B | – | $0.600000 | $1.800000 | medium |
| nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | – | $0.600000 | $1.800000 | medium |
| Qwen: Qwen3.5 397B A17B | – | $0.600000 | $3.600000 | medium |
| openbmb/MiniCPM-V-4_5 | – | $0.658000 | $1.110000 | medium |
| DeepSeek: R1 | – | $0.800000 | $2.400000 | medium |
| DeepSeek-R1-0528 | – | $0.800000 | $2.400000 | medium |
| MoonshotAI: Kimi K2.7 Code | fp4 | $0.950000 | $4.000000 | high |
| MoonshotAI: Kimi K2.6 | – | $0.950000 | $4.000000 | medium |
| MoonshotAI: Kimi K2.7 Code | – | $0.950000 | $4.000000 | medium |
| Kimi K2.7 Code | – | $0.950000 | $4.000000 | medium |
| Nous: Hermes 4 405B | fp8 | $1.000000 | $3.000000 | high |
| meta-llama/Meta-Llama-3.1-405B-Instruct | – | $1.000000 | $3.000000 | medium |
| Nous: Hermes 3 405B Instruct | – | $1.000000 | $3.000000 | medium |
| Nous: Hermes 4 405B | – | $1.000000 | $3.000000 | medium |
| NVIDIA: Nemotron 3 Ultra (free) | – | $1.000000 | $3.000000 | medium |
| deepseek-ai/DeepSeek-V4-Pro-0813 | – | $1.320000 | $3.960000 | medium |
| DeepSeek: DeepSeek V4 Pro 0813 | – | $1.320000 | $3.960000 | medium |
| Z.ai: GLM 5.3 | fp4 | $1.400000 | $4.400000 | high |
| Z.ai: GLM 5.1 | fp8 | $1.400000 | $4.400000 | high |
| GLM-5.1 | – | $1.400000 | $4.400000 | medium |
| zai-org/GLM-5.2 | – | $1.400000 | $4.400000 | medium |
| zai-org/GLM-5.3 | – | $1.400000 | $4.400000 | medium |
| GLM-5.2 | – | $1.400000 | $4.400000 | medium |
| GLM-5.3 | – | $1.400000 | $4.400000 | medium |
| deepseek-ai/DeepSeek-V4-Pro | – | $1.750000 | $3.500000 | medium |
| DeepSeek: DeepSeek V4 Pro 0423 | – | $1.750000 | $3.500000 | medium |
| MoonshotAI: Kimi K3 | – | $3.000000 | $15.000000 | medium |
| Kimi K3 | – | $3.000000 | $15.000000 | medium |