Provider
Nebius
29 Models · 32 Prices · Cheapest on 11 · Uptime 98.8% · updated 2026-08-04 23:15 UTC
Trust signals · SLA · model-version transparency · pricing stability · quantization-degradation · incident response · data privacy — measured by TKX probe (activating).
About
Nebius is an AI inference provider that utilizes machine learning to serve 29 models via official/openrouter, focusing on delivering accurate and efficient predictions for various applications.
AI-generated summary from public information — is this yours? Claim & edit
Models served
| Model | $ in /1M | $ out /1M | Cheapest | Router / Source | Evidence |
|---|---|---|---|---|---|
| Qwen2.5-Coder-7B | $0.010 | $0.030 | ✓ | Pricebook (LiteLLM) | Official list |
| Llama-Guard-3-8B | $0.020 | $0.060 | ✓ | Pricebook (LiteLLM) | Official list |
| Meta-Llama-3.1-8B-Instruct | $0.020 | $0.060 | ✓ | Pricebook (LiteLLM) | Official list |
| Qwen2-VL-7B-Instruct | $0.020 | $0.060 | ✓ | Pricebook (LiteLLM) | Official list |
| Mistral-Nemo-Instruct-2407 | $0.040 | $0.120 | — | Pricebook (LiteLLM) | Official list |
| gemma-3-27b-it | $0.060 | $0.200 | ✓ | Pricebook (LiteLLM) | Official list |
| Qwen2.5-32B-Instruct | $0.060 | $0.200 | ✓ | Pricebook (LiteLLM) | Official list |
| Qwen3-14B | $0.080 | $0.240 | — | Pricebook (LiteLLM) | Official list |
| Qwen3-4B | $0.080 | $0.240 | ✓ | Pricebook (LiteLLM) | Official list |
| Qwen3 32B | $0.100 | $0.300 | — | OpenRouter | API-measured |
| Qwen3-30B-A3B | $0.100 | $0.300 | — | Pricebook (LiteLLM) | Official list |
| Llama-3.3-Nemotron-Super-49B-v1 | $0.100 | $0.400 | ✓ | Pricebook (LiteLLM) | Official list |
| Llama-3.3-70B-Instruct | $0.130 | $0.400 | — | Pricebook (LiteLLM) | Official list |
| Meta-Llama-3.1-70B-Instruct | $0.130 | $0.400 | — | Pricebook (LiteLLM) | Official list |
| Qwen2.5-72B-Instruct | $0.130 | $0.400 | — | Pricebook (LiteLLM) | Official list |
| Qwen2.5-VL-72B-Instruct | $0.130 | $0.400 | ✓ | Pricebook (LiteLLM) | Official list |
| Qwen2-VL-72B-Instruct | $0.130 | $0.400 | ✓ | Pricebook (LiteLLM) | Official list |
| QwQ-32B | $0.150 | $0.450 | — | Pricebook (LiteLLM) | Official list |
| gpt-oss-120b | $0.150 | $0.600 | — | OpenRouter | API-measured |
| Qwen3-235B-A22B | $0.200 | $0.600 | — | Pricebook (LiteLLM) | Official list |
| DeepSeek-R1-Distill-Llama-70B | $0.250 | $0.750 | — | Pricebook (LiteLLM) | Official list |
| DeepSeek-V3 | $0.500 | $1.50 | — | Pricebook (LiteLLM) | Official list |
| DeepSeek-V3-0324 | $0.500 | $1.50 | — | Pricebook (LiteLLM) | Official list |
| Llama-3.1-Nemotron-Ultra-253B-v1 | $0.600 | $1.80 | ✓ | Pricebook (LiteLLM) | Official list |
| DeepSeek-R1 | $0.800 | $2.40 | — | Pricebook (LiteLLM) | Official list |
| DeepSeek-R1-0528 | $0.800 | $2.40 | — | Pricebook (LiteLLM) | Official list |
| Meta-Llama-3.1-405B-Instruct | $1.00 | $3.00 | — | Pricebook (LiteLLM) | Official list |
| Hermes-3-Llama-3.1-405B | $1.00 | $3.00 | — | Pricebook (LiteLLM) | Official list |
| GLM 5.1 | $1.40 | $4.40 | — | OpenRouter | API-measured |