Nebius Pricing
Nebius charges from $0.030 per 1 million output tokens, depending on the model. Qwen Qwen2.5 Coder 7B is the cheapest at $0.030/1M output and $0.010/1M input; its current flagship GLM-5.3 costs $4.40/1M output. The largest context window is 1.0M tokens (DeepSeek Ai DeepSeek V4 Flash). Prices are USD, current as of October 12, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.010/1M
Qwen Qwen2.5 Coder 7B
Cheapest output
$0.030/1M
Qwen Qwen2.5 Coder 7B
Longest context
1.0M
DeepSeek Ai DeepSeek V4 Flash
Models priced
76
Avg $1.88/1M output
Pricing by model
All prices in USD per 1 million tokens. All 76 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Qwen Qwen2.5 Coder 7B | $0.010 | $0.030 | 33K |
| Meta Llama Llama Guard 3 8B | $0.020 | $0.060 | 128K |
| Meta Llama Meta Llama 3.1 8B Instruct | $0.020 | $0.060 | 128K |
| Qwen Qwen2 VL 7B Instruct | $0.020 | $0.060 | 131K |
| Mistralai Mistral Nemo Instruct 2407 | $0.040 | $0.120 | 128K |
| Qwen Qwen2.5 32B Instruct | $0.060 | $0.200 | 128K |
| Nemotron 3.5 Lightning 30B A3B ReasoningToolsCache | $0.060 | $0.240 | 1.0M |
| Nvidia Nemotron 3 5 Lightning | $0.060 | $0.240 | 1.0M |
| Nvidia Nemotron 3 Nano Omni | $0.060 | $0.240 | 262K |
| Nvidia Nvidia Nemotron 3 Nano 30B A3b | $0.060 | $0.240 | 262K |
| Qwen Qwen3 14B | $0.080 | $0.240 | 33K |
| Qwen Qwen3 4B | $0.080 | $0.240 | 33K |
| DeepSeek Ai DeepSeek V4 Flash | $0.140 | $0.280 | 1.0M |
| DeepSeek Ai DeepSeek V4 Flash 0731 | $0.140 | $0.280 | 1.0M |
| DeepSeek V4 Flash 0731 ReasoningToolsCache | $0.140 | $0.280 | 1.0M |
| Gemma-3-27b-it VisionToolsCache | $0.100 | $0.300 | 110K |
| Google Gemma 3 27B It | $0.100 | $0.300 | 110K |
| Nvidia Cosmos3 Super Reasoner | $0.100 | $0.300 | 262K |
| Qwen Qwen3 30B A3b | $0.100 | $0.300 | 33K |
| Qwen Qwen3 30B A3b Instruct 2507 | $0.100 | $0.300 | 262K |
| Qwen Qwen3 32B | $0.100 | $0.300 | 41K |
| Qwen3-30B-A3B-Instruct-2507 ToolsCache | $0.100 | $0.300 | 262K |
| Meta Llama Llama 3.3 70B Instruct | $0.130 | $0.400 | 131K |
| Meta Llama Meta Llama 3.1 70B Instruct | $0.130 | $0.400 | 128K |
| Nousresearch Hermes 4 70B | $0.130 | $0.400 | 131K |
| Nvidia Llama 3.3 Nemotron Super 49B | $0.100 | $0.400 | 131K |
| Qwen Qwen2 VL 72B Instruct | $0.130 | $0.400 | 131K |
| Qwen Qwen2.5 72B Instruct | $0.130 | $0.400 | 128K |
| Qwen Qwq 32B | $0.150 | $0.450 | 33K |
| GLM-5.3-Flash ReasoningToolsCache | $0.150 | $0.500 | 1.0M |
| Zai Org Glm 5.3 Flash | $0.150 | $0.500 | 1.0M |
| gpt-oss-120b ReasoningToolsCache | $0.150 | $0.600 | 131K |
| OpenAI GPT Oss 120B | $0.150 | $0.600 | 131K |
| Qwen Qwen3 235B A22b | $0.200 | $0.600 | 262K |
| Qwen Qwen3 235B A22b Instruct 2507 | $0.200 | $0.600 | 262K |
| Qwen3 235B A22B Instruct 2507 Tools | $0.200 | $0.600 | 262K |
| DeepSeek Ai DeepSeek R1 Distill Llama 70B | $0.250 | $0.750 | 128K |
| Qwen Qwen2.5 VL 72B Instruct | $0.250 | $0.750 | 32K |
| Nemotron-3-Super-120B-A12B ReasoningTools | $0.300 | $0.900 | 262K |
| Nvidia Nemotron 3 Super 120B A12b | $0.300 | $0.900 | 262K |
| Openbmb Minicpm V 4 5 | $0.658 | $1.11 | 32K |
| DeepSeek Ai DeepSeek V4.1 Flash | $0.300 | $1.20 | 1.0M |
| DeepSeek V4.1 Flash VisionReasoningToolsCache | $0.300 | $1.20 | 1.0M |
| MiniMax-M3 ReasoningTools | $0.300 | $1.20 | 1.0M |
| Minimaxai Minimax M2.5 | $0.300 | $1.20 | 197K |
| Minimaxai Minimax M3 | $0.300 | $1.20 | 1.0M |
| Qwen Qwen3 Next 80B A3b Thinking | $0.150 | $1.20 | 128K |
| DeepSeek Ai DeepSeek V3 | $0.500 | $1.50 | 128K |
| DeepSeek Ai DeepSeek V3 0324 | $0.500 | $1.50 | 128K |
| Nvidia Llama 3 1 Nemotron Ultra 253B | $0.600 | $1.80 | 131K |
| DeepSeek Ai DeepSeek R1 | $0.800 | $2.40 | 128K |
| DeepSeek Ai DeepSeek R1 0528 | $0.800 | $2.40 | 164K |
| Hermes-4-405B ReasoningToolsCache | $1.00 | $3.00 | 131K |
| Meta Llama Meta Llama 3.1 405B Instruct | $1.00 | $3.00 | 128K |
| Nemotron 3 Ultra 550B A55B ReasoningToolsCache | $1.00 | $3.00 | 1.0M |
| Nousresearch Hermes 3 Llama 3.1 405B | $1.00 | $3.00 | 128K |
| Nousresearch Hermes 4 405B | $1.00 | $3.00 | 131K |
| Nvidia Nemotron 3 Ultra 550B A55b | $1.00 | $3.00 | 1.0M |
| Qwen Qwen3.8 27B | $0.450 | $3.00 | 262K |
| Qwen3.8 27B ReasoningToolsCache | $0.450 | $3.00 | 262K |
| DeepSeek Ai DeepSeek V4 Pro | $1.75 | $3.50 | 1.0M |
| DeepSeek V4 Pro ReasoningToolsCache | $1.75 | $3.50 | 1.0M |
| Qwen Qwen3.5 397B A17b | $0.600 | $3.60 | 262K |
| Qwen3.5-397B-A17B ReasoningToolsCache | $0.600 | $3.60 | 262K |
| DeepSeek Ai DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 979K |
| DeepSeek V4 Pro 0813 ReasoningToolsCache | $1.32 | $3.96 | 979K |
| Kimi K2.7 Code ReasoningTools | $0.950 | $4.00 | 262K |
| Moonshotai Kimi K2.6 | $0.950 | $4.00 | 262K |
| Moonshotai Kimi K2.7 Code | $0.950 | $4.00 | 262K |
| GLM-5.2 ReasoningTools | $1.40 | $4.40 | 1.0M |
| GLM-5.3 ReasoningToolsCache | $1.40 | $4.40 | 1.0M |
| Zai Org Glm 5.1 | $1.40 | $4.40 | 203K |
| Zai Org Glm 5.2 | $1.40 | $4.40 | 1.0M |
| Zai Org Glm 5.3 | $1.40 | $4.40 | 1.0M |
| Kimi K3 ReasoningToolsCache | $3.00 | $15.00 | 1.0M |
| Moonshotai Kimi K3 | $3.00 | $15.00 | 1.0M |
Frequently asked questions
How much does Nebius cost per 1M tokens?
Nebius pricing starts at $0.030 per 1 million output tokens (Qwen Qwen2.5 Coder 7B) across 76 models, with its current flagship GLM-5.3 at $4.40. Older premium models in the catalog list higher. Rates current as of October 12, 2026.
What is the cheapest Nebius model?
Qwen Qwen2.5 Coder 7B is the cheapest Nebius model on both axes — $0.010 per 1M input tokens and $0.030 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.
What is the largest Nebius context window?
DeepSeek Ai DeepSeek V4 Flash has the largest context window in the Nebius catalog at 1.0M input tokens, with up to 1.0M output tokens per response.
Does Nebius support prompt caching?
Yes. Gemma-3-27b-it reads cached input at $0.010 per 1M tokens, against $0.100 per 1M uncached. Caching pays off when a long system prompt or document is reused across many requests.
Which Nebius models support reasoning or vision?
The Nebius catalog includes 17 reasoning models, 2 vision models, 20 with tool calling. Reasoning models bill their internal thinking as output tokens, so they cost more per visible response than the headline rate suggests.
How do I calculate my actual Nebius bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator