Nebius Token Factory vs Novita.
Prices checked
Novita is cheaper on 15 of the 28 models both sell, the widest gap DeepSeek V4 Flash 0731 at $0.18 against $0.61 per M tokens, checked .
Where to start
Nebius Token Factoryall 44 models Serves open-weight models from its own datacenters in Europe.
Cheapest of the shared models
3¢/M tokens
Llama 3.1 8B Instruct
Novitaall 101 models Serves open-weight models on its own GPUs; publishes list and promotional prices side by side.
Cheapest of the shared models
2.8¢/M tokens
Llama 3.1 8B Instruct
Side by side
| Fact | Nebius Token Factory | Novita |
|---|---|---|
| Kind of provider | Host | Host |
| Models we track | 44 | 101 |
| Cheaper of the two | 8 of 28 | 15 of 28 |
| Trains on your prompts | does not say | does not say |
| Keeps your requests | does not say | does not say |
| How you pay | does not say | does not say |
| Smallest top-up | does not say | does not say |
| Free tier | none listed | none listed |
| Where it runs | does not say | does not say |
Every model both sell
28 models, most widely sold first. Per M tokens, blended 3 in : 1 out.
| Model | Nebius Token Factory | Novita |
|---|---|---|
| GLM-5.3Z.ai · 1M context | $2.15 $1.40 in · $4.40 out | $0.97 $0.63 in · $1.98 out |
| GLM-5.3-FlashZ.ai · 1M context | $0.24 $0.15 in · $0.50 out | $0.13 8.4¢ in · $0.28 out |
| DeepSeek V4.1 Flash 1017DeepSeek · 1M context | $0.52 $0.30 in · $1.20 out | $0.34 $0.20 in · $0.78 out |
| DeepSeek V4 Flash 0731DeepSeek · 1M context | $0.18 $0.14 in · $0.28 out | $0.61 $0.41 in · $1.23 out |
| GLM-5.2Z.ai · 1M context | $2.15 $1.40 in · $4.40 out | $1 $0.65 in · $2.04 out |
| Kimi K3Moonshot AI · 1M context | $6 $3 in · $15 out | $6 $3 in · $15 out |
| DeepSeek V4 ProDeepSeek · 1M context | $1.98 $1.32 in · $3.96 out | $1.49 $0.99 in · $2.97 out |
| Kimi K2.6Moonshot AI · 262k context | $1.71 $0.95 in · $4 out | $1.45 $0.80 in · $3.40 out |
| Qwen3.8 27BAlibaba Cloud · 1M context | $1.09 $0.45 in · $3 out | $1.07 $0.42 in · $3 out |
| gpt-oss-120bOpenAI · 131k context | $0.26 $0.15 in · $0.60 out | $0.10 5¢ in · $0.25 out |
| MiniMax-M3MiniMax · 1M context | $0.52 $0.30 in · $1.20 out | $0.52 $0.30 in · $1.20 out |
| Kimi K2.7 CodeMoonshot AI · 262k context | $1.71 $0.95 in · $4 out | $1.64 $0.91 in · $3.84 out |
| GLM-5.1Z.ai · 200k context | $2.15 $1.40 in · $4.40 out | $2.13 $1.38 in · $4.40 out |
| Llama 3.3 70B InstructMeta · 131k context | $0.20 $0.13 in · $0.40 out | $0.20 $0.14 in · $0.40 out |
| MiniMax-M2.5MiniMax · 205k context | $0.52 $0.30 in · $1.20 out | $0.52 $0.30 in · $1.20 out |
| Qwen3.5 397B-A17BAlibaba Cloud · 262k context | $1.35 $0.60 in · $3.60 out | $1.35 $0.60 in · $3.60 out |
| MiniMax-M3.1-FlashMiniMax · 1M context | $0.26 $0.15 in · $0.60 out | $0.26 $0.15 in · $0.60 out |
| R1 0528DeepSeek · 164k context | $1.20 $0.80 in · $2.40 out | $1.15 $0.70 in · $2.50 out |
| Qwen3 235B-A22BAlibaba Cloud · 131k context | $0.30 $0.20 in · $0.60 out | $0.35 $0.20 in · $0.80 out |
| DeepSeek V3 0324DeepSeek · 164k context | $0.75 $0.50 in · $1.50 out | $0.63 $0.40 in · $1.30 out |
| Llama 3.1 8B InstructMeta · 131k context | 3¢ 2¢ in · 6¢ out | 2.8¢ 2¢ in · 5¢ out |
| Qwen3 30B A3BAlibaba Cloud · 262k context | $0.15 $0.10 in · $0.30 out | $0.18 9¢ in · $0.45 out |
| Mistral NemoMistral AI · 131k context | 6¢ 4¢ in · $0.12 out | 7.3¢ 4¢ in · $0.17 out |
| Gemma 3 27BGoogle · 131k context | $0.15 $0.10 in · $0.30 out | $0.14 $0.12 in · $0.20 out |
| Nemotron 3 Nano 30B A3BNVIDIA · 262k context | $0.10 6¢ in · $0.24 out | 8.8¢ 5¢ in · $0.20 out |
| Qwen2.5 72B InstructAlibaba Cloud · 33k context | $0.20 $0.13 in · $0.40 out | $0.39 $0.38 in · $0.40 out |
| Qwen3-Next 80B-A3B (Thinking)Alibaba Cloud · 131k context | $0.41 $0.15 in · $1.20 out | $0.49 $0.15 in · $1.50 out |
| Qwen2.5 VL 72B InstructAlibaba Cloud · 128k context | $0.38 $0.25 in · $0.75 out | $0.80 $0.80 in · $0.80 out |
How we count
Novita is cheaper on 15 of the 28 models both sell, Nebius Token Factory on 8, and 5 cost the same at both. Both are the same kind of provider, hosts running the same models, so the price is most of what separates them.
Each price is the cheapest that provider charges for the model, per M tokens, blended 3 in : 1 out. The smaller line under it is the price in and the price out.
A free tier is a limit rather than a price, and a price below the maker's own with nothing published to account for it is left out, so neither can be marked as the cheaper of the two.
Frequently asked
- Is Nebius Token Factory cheaper than Novita?
- On the 28 models both sell, Nebius Token Factory is cheaper on 8, Novita on 15, and 5 cost the same at both. The widest gap is DeepSeek V4 Flash 0731: $0.18 per million tokens against $0.61. Prices are per M tokens, blended 3 in : 1 out, and read on 31 Oct 2026.
- Which models do Nebius Token Factory and Novita both sell?
- 28 of the models we track, led by GLM-5.3, GLM-5.3-Flash, DeepSeek V4.1 Flash 1017. Nebius Token Factory sells 44 in all and Novita 101, so most of each catalog has no counterpart at the other.
- Does Nebius Token Factory or Novita train on what you send it?
- Nebius Token Factory does not say whether it trains on what you send it, and does not say how long it keeps requests. Novita does not say whether it trains on what you send it, and does not say how long it keeps requests. A provider that may train on prompts is often how a price below the maker's own is paid for.
- How current are these prices?
- Both catalogs are read every 3 days. Nebius Token Factory was last read 31 Oct 2026 and Novita 31 Oct 2026; the whole index was refreshed 31 Oct 2026. Prices exclude tax, and a price below the maker's own with nothing published to account for it is left out of this table entirely.
More comparisons