Nebius
Nebius serves 13 open models from 8 labs on OpenRouter, in 13 offers. Of the 12 models it shares with other providers, it has the lowest blended price on 0. It is the only provider for 1 model. Its median blended price is $0.525 (₹50) per million tokens, blended 3:1 input to output. Its most common precision is 4-bit (9 of 13 offers).
Company and policies
- Headquarters listed by OpenRouter
- Netherlands
- Datacenter countries listed by OpenRouter
- Not listed
Privacy policyTerms of serviceProvider on OpenRouter
Provider-level locations do not guarantee where a particular request is processed. Check the provider's terms for data handling. Directory source, checked 14 Nov 2026.
Precision and price rank
| Offers | 4-bit | 8-bit | Total |
|---|---|---|---|
| Offers | 9 | 4 | 13 |
| Rank | Models |
|---|---|
| Lowest or tied | 0 |
| 2nd | 0 |
| 3rd | 1 |
| 4th or lower | 11 |
Every model Nebius serves 13
USD and INR per million tokens| Precision | Lab | Pricing | ||||||
|---|---|---|---|---|---|---|---|---|
| $1.98₹187 | $1.32₹124 | $3.96₹373 | 15 of 20 | 1,048,576 | FP8 | DeepSeek | All providers | |
| $0.525₹50 | $0.30₹28 | $1.20₹113 | 35 of 38 | 1,048,576 | FP8 | DeepSeek | All providers | |
| $0.15₹14 | $0.10₹9.43 | $0.30₹28 | 3 of 4 | 110,000 | FP8 | All providers | ||
| $2.15₹203 | $1.40₹132 | $4.40₹415 | 20 of 24 | 1,048,576 | FP4 | Z.ai (Zhipu) | All providers | |
| $2.15₹203 | $1.40₹132 | $4.40₹415 | 31 of 37 | 1,048,576 | FP4 | Z.ai (Zhipu) | All providers | |
| $0.2375₹22 | $0.15₹14 | $0.50₹47 | 31 of 37 | 1,048,576 | FP4 | Z.ai (Zhipu) | All providers | |
| $0.2625₹25 | $0.15₹14 | $0.60₹57 | 16 of 22 | 131,072 | FP4 | OpenAI | All providers | |
| $6.00₹566 | $3.00₹283 | $15.00₹1,414 | 16 of 20 | 1,048,576 | FP4 | Moonshot AI | All providers | |
| $4.00₹377 | $2.00₹189 | $10.00₹943 | 13 of 18 | 1,048,576 | FP4 | Moonshot AI | All providers | |
| $0.2625₹25 | $0.15₹14 | $0.60₹57 | 8 of 11 | 1,048,576 | FP4 | MiniMax | All providers | |
| $0.105₹9.90 | $0.06₹5.66 | $0.24₹23 | 1 of 1Only provider | 262,144 | FP8 | NVIDIA | All providers | |
| $0.45₹42 | $0.30₹28 | $0.90₹85 | 10 of 10 | 1,048,576 | FP4 | NVIDIA | All providers | |
| $1.0875₹103 | $0.45₹42 | $3.00₹283 | 19 of 23 | 1,000,000 | FP4 | Alibaba Qwen | All providers |
Where Nebius is cheapest
0 of 12 models shared with other providersNebius does not have the lowest blended price on any model that other providers also serve.
Only provider for 1 model: NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. With no other provider to compare, these are not counted as cheapest.
Nebius questions
Which open models does Nebius serve?
Nebius serves 13 open models from 8 labs on OpenRouter. The most downloaded on Hugging Face are Qwen3.8-27B, GLM-5.3-Flash and gpt-oss-120b. Prices were fetched 14 Nov 2026.
Is Nebius the cheapest provider for any open model?
No. Its best position is 3rd of 4 providers, for gemma-3-27b-it at $0.15 (₹14) per million tokens, blended 3:1 input to output. It is also the only provider for 1 model, which we do not count as cheapest.
What precision does Nebius serve models at?
Of its 13 offers, Nebius lists 4-bit for 9 and 8-bit for 4. Prices are in US dollars; we show rupees at ₹94.29 per $1.
About this data
Every number on this page comes from the endpoints OpenRouter lists for each model, fetched 14 Nov 2026. INR is shown beside USD at ₹94.29 per $1. Prices change, so check the provider before you build on a number.