Nebius API pricing
Hosted57 language models
As of Oct 14, 2026, Nebius lists 57 language models through its API. Its cheapest language model is Qwen2.5 Coder 7B Instruct at $0.01 input / $0.03 output per million tokens.
Language models (57)
Prices per million tokens.
nebius/deepseek-ai/DeepSeek-R1
- Input
- $0.80
- Output
- $2.40
- Context
- 128K
nebius/deepseek-ai/DeepSeek-R1-0528
- Input
- $0.80
- Output
- $2.40
- Context
- 164K
nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Input
- $0.25
- Output
- $0.75
- Context
- 128K
nebius/deepseek-ai/DeepSeek-V3
- Input
- $0.50
- Output
- $1.50
- Context
- 128K
nebius/deepseek-ai/DeepSeek-V3-0324
- Input
- $0.50
- Output
- $1.50
- Context
- 128K
nebius/deepseek-ai/DeepSeek-V4-Flash
- Input
- $0.14
- Output
- $0.28
- Context
- 1.05M
nebius/deepseek-ai/DeepSeek-V4-Flash-0731
- Input
- $0.14
- Output
- $0.28
- Context
- 1.02M
nebius/deepseek-ai/DeepSeek-V4-Pro
- Input
- $1.75
- Output
- $3.50
- Context
- 1.05M
nebius/deepseek-ai/DeepSeek-V4-Pro-0813
- Input
- $1.32
- Output
- $3.96
- Context
- 979K
nebius/deepseek-ai/DeepSeek-V4.1-Flash
- Input
- $0.30
- Output
- $1.20
- Context
- 1.05M
nebius/google/gemma-3-27b-it
- Input
- $0.10
- Output
- $0.30
- Context
- 110K
nebius/zai-org/GLM-5.1
- Input
- $1.40
- Output
- $4.40
- Context
- 203K
nebius/zai-org/GLM-5.2
- Input
- $1.40
- Output
- $4.40
- Context
- 1.05M
nebius/zai-org/GLM-5.3
- Input
- $1.40
- Output
- $4.40
- Context
- 1.02M
nebius/zai-org/GLM-5.3-Flash
- Input
- $0.15
- Output
- $0.50
- Context
- 1.02M
nebius/openai/gpt-oss-120b
- Input
- $0.15
- Output
- $0.60
- Context
- 131K
nebius/NousResearch/Hermes-3-Llama-3.1-405B
- Input
- $1.00
- Output
- $3.00
- Context
- 128K
nebius/moonshotai/Kimi-K2.6
- Input
- $0.95
- Output
- $4.00
- Context
- 262K
nebius/moonshotai/Kimi-K2.7-Code
- Input
- $0.95
- Output
- $4.00
- Context
- 262K
nebius/moonshotai/Kimi-K3
- Input
- $3.00
- Output
- $15.00
- Context
- 1.02M
nebius/meta-llama/Llama-3.3-70B-Instruct
- Input
- $0.13
- Output
- $0.40
- Context
- 131K
nebius/meta-llama/Llama-Guard-3-8B
- Input
- $0.02
- Output
- $0.06
- Context
- 128K
nebius/meta-llama/Meta-Llama-3.1-8B-Instruct
- Input
- $0.02
- Output
- $0.06
- Context
- 128K
nebius/meta-llama/Meta-Llama-3.1-70B-Instruct
- Input
- $0.13
- Output
- $0.40
- Context
- 128K
nebius/MiniMaxAI/MiniMax-M2.5
- Input
- $0.30
- Output
- $1.20
- Context
- 197K
nebius/MiniMaxAI/MiniMax-M3
- Input
- $0.30
- Output
- $1.20
- Context
- 1.05M
nebius/mistralai/Mistral-Nemo-Instruct-2407
- Input
- $0.04
- Output
- $0.12
- Context
- 128K
nebius/nvidia/Nemotron-3-Ultra-550b-a55b
- Input
- $1.00
- Output
- $3.00
- Context
- 1.05M
nebius/Qwen/Qwen3-32B
- Input
- $0.10
- Output
- $0.30
- Context
- 41K
nebius/Qwen/Qwen3.8-27B
- Input
- $0.45
- Output
- $3.00
- Context
- 262K
nebius/Qwen/Qwen2.5-32B-Instruct
- Input
- $0.06
- Output
- $0.20
- Context
- 128K
nebius/Qwen/Qwen2.5-72B-Instruct
- Input
- $0.13
- Output
- $0.40
- Context
- 128K
nebius/Qwen/Qwen2.5-Coder-7B
- Input
- $0.01
- Output
- $0.03
- Context
- 33K
nebius/Qwen/Qwen2.5-VL-72B-Instruct
- Input
- $0.25
- Output
- $0.75
- Context
- 32K
nebius/Qwen/Qwen3-14B
- Input
- $0.08
- Output
- $0.24
- Context
- 33K
nebius/Qwen/Qwen3-30B-A3B
- Input
- $0.10
- Output
- $0.30
- Context
- 33K
nebius/Qwen/Qwen3-30B-A3B-Instruct-2507
- Input
- $0.10
- Output
- $0.30
- Context
- 262K
nebius/Qwen/Qwen3-235B-A22B
- Input
- $0.20
- Output
- $0.60
- Context
- 262K
nebius/Qwen/Qwen3-235B-A22B-Instruct-2507
- Input
- $0.20
- Output
- $0.60
- Context
- 262K
nebius/Qwen/Qwen3-Next-80B-A3B-Thinking
- Input
- $0.15
- Output
- $1.20
- Context
- 128K
nebius/Qwen/Qwen3.5-397B-A17B
- Input
- $0.60
- Output
- $3.60
- Context
- 262K
nebius/Qwen/QwQ-32B
- Input
- $0.15
- Output
- $0.45
- Context
- 33K
Cosmos3 Super Reasoner
nebius/nvidia/Cosmos3-Super-Reasoner
- Input
- $0.10
- Output
- $0.30
- Context
- 262K
Hermes 4 70B
nebius/NousResearch/Hermes-4-70B
- Input
- $0.13
- Output
- $0.40
- Context
- 131K
Hermes 4 405B
nebius/NousResearch/Hermes-4-405B
- Input
- $1.00
- Output
- $3.00
- Context
- 131K
Llama 3.1 Nemotron Ultra 253B V1
nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1
- Input
- $0.60
- Output
- $1.80
- Context
- 128K
Llama 3.1 Nemotron Ultra 253B V1
nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
- Input
- $0.60
- Output
- $1.80
- Context
- 131K
Llama 3.3 Nemotron Super 49B V1
nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1
- Input
- $0.10
- Output
- $0.40
- Context
- 131K
Meta Llama 3.1 405B Instruct
nebius/meta-llama/Meta-Llama-3.1-405B-Instruct
- Input
- $1.00
- Output
- $3.00
- Context
- 128K
Minicpm V 4.5
nebius/openbmb/MiniCPM-V-4_5
- Input
- $0.658
- Output
- $1.11
- Context
- 32K
Nemotron 3 Nano Omni
nebius/nvidia/Nemotron-3-Nano-Omni
- Input
- $0.06
- Output
- $0.24
- Context
- 262K
Nemotron 3 Super 120B A12B
nebius/nvidia/nemotron-3-super-120b-a12b
- Input
- $0.30
- Output
- $0.90
- Context
- 262K
Nemotron 3.5 Lightning
nebius/nvidia/Nemotron-3_5-Lightning
- Input
- $0.06
- Output
- $0.24
- Context
- 1.05M
Nvidia Nemotron 3 Nano 30B A3B
nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
- Input
- $0.06
- Output
- $0.24
- Context
- 262K
Qwen2 VL 7B Instruct
nebius/Qwen/Qwen2-VL-7B-Instruct
- Input
- $0.02
- Output
- $0.06
- Context
- 131K
Qwen2 VL 72B Instruct
nebius/Qwen/Qwen2-VL-72B-Instruct
- Input
- $0.13
- Output
- $0.40
- Context
- 131K
Qwen3 4B
nebius/Qwen/Qwen3-4B
- Input
- $0.08
- Output
- $0.24
- Context
- 33K
Prices in USD from LiteLLM and models.dev, checked daily; confirm on Nebius's pricing page before you rely on a number.