Nebius Token Factory vs Novita.

model prices compared · prices as of · 21 models both sell

Novita is cheaper on 11 of the 21 models both sell, Nebius Token Factory on 6, and 4 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. The widest gap is DeepSeek V4 Flash 0731, $0.70 per million tokens at Nebius Token Factory against $2.46.

Novita is cheaper on 11 of the 21 models both sell, and the cheapest thing either one offers is Mistral Nemo at $0.24 per million tokens, read 16 Sept 2026.

Nebius Token Factoryall 31 models →

Serves open-weight models from its own datacenters in Europe.

cheapest here: Mistral Nemo at $0.24/M tokens

Serves open-weight models on its own GPUs; publishes list and promotional prices side by side.

cheapest here: Mistral Nemo at $0.29/M tokens

Kind of providerHostHost
Models we track3192
Cheaper of the two6 of 2111 of 21
Trains on your promptsdoes not saydoes not say
Keeps your requestsnot statednot stated
How you paynot statednot stated
Smallest top-upnot statednot stated
Free tiernone publishednone published
Where it runsnot statednot stated
Prices read16 Sept 202616 Sept 2026

Every model both sell, at each one's price

Most widely sold first. Each price is the cheapest that provider charges for the model under the standard blend, three parts input to one part output per million tokens. 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.

ModelNebius Token FactoryNovita
DeepSeek V4 Flash 0731DeepSeek · 1M context$0.70$0.14 / $0.28 in / out$2.46$0.41 / $1.23 in / out
GLM-5.2Z.ai · 1M context$8.60$1.40 / $4.40 in / out$3.99$0.65 / $2.04 in / out
DeepSeek V4 ProDeepSeek · 1M context$8.75$1.75 / $3.50 in / out$5.94$0.99 / $2.97 in / out
Kimi K2.6Moonshot AI · 262k context$6.85$0.95 / $4 in / out$5.80$0.80 / $3.40 in / out
Kimi K3Moonshot AI · 1M context$24$3 / $15 in / out$24$3 / $15 in / out
GLM-5.3-FlashZ.ai · 1M context$0.95$0.15 / $0.50 in / out$0.84$0.13 / $0.44 in / out
Kimi K2.7 CodeMoonshot AI · 262k context$6.85$0.95 / $4 in / out$6.58$0.91 / $3.84 in / out
gpt-oss-120bOpenAI · 131k context$1.05$0.15 / $0.60 in / out$0.40$0.05 / $0.25 in / out
GLM-5.1Z.ai · 200k context$8.60$1.40 / $4.40 in / out$8.54$1.38 / $4.40 in / out
MiniMax-M3MiniMax · 1M context$2.10$0.30 / $1.20 in / out$2.10$0.30 / $1.20 in / out
MiniMax-M2.5MiniMax · 205k context$2.10$0.30 / $1.20 in / out$2.10$0.30 / $1.20 in / out
Llama-3.3-70B-InstructMeta · 128k context$0.79$0.13 / $0.40 in / out$0.81$0.14 / $0.40 in / out
Qwen3.5 397B-A17BAlibaba Cloud · 262k context$5.40$0.60 / $3.60 in / out$5.40$0.60 / $3.60 in / out
Qwen3 235B-A22BAlibaba Cloud · 131k context$1.20$0.20 / $0.60 in / out$0.85$0.09 / $0.58 in / out
R1 0528DeepSeek · 164k context$4.80$0.80 / $2.40 in / out$4.60$0.70 / $2.50 in / out
Qwen3 30B A3B Instruct 2507Alibaba Cloud · 262k context$0.60$0.10 / $0.30 in / out$0.72$0.09 / $0.45 in / out
Mistral NemoMistral AI · 128k context$0.24$0.04 / $0.12 in / out$0.29$0.04 / $0.17 in / out
Gemma 3 27BGoogle · 131k context$0.60$0.10 / $0.30 in / out$0.56$0.12 / $0.20 in / out
Qwen3-Next 80B-A3B (Thinking)Alibaba Cloud · 131k context$1.65$0.15 / $1.20 in / out$1.95$0.15 / $1.50 in / out
R1 Distill Llama 70BDeepSeek · 8k context$1.50$0.25 / $0.75 in / out$3.20$0.80 / $0.80 in / out
Nemotron 3 Nano 30B A3BNVIDIA · 262k context$0.42$0.06 / $0.24 in / out$0.35$0.05 / $0.20 in / out

Frequently asked

Is Nebius Token Factory cheaper than Novita?
On the 21 models both sell, Nebius Token Factory is cheaper on 6, Novita on 11, and 4 cost the same at both. The widest gap is DeepSeek V4 Flash 0731: $0.70 per million tokens against $2.46. Prices are blended three parts input to one part output and read on 16 Sept 2026.
Which models do Nebius Token Factory and Novita both sell?
21 of the models we track, led by DeepSeek V4 Flash 0731, GLM-5.2, DeepSeek V4 Pro. Nebius Token Factory sells 31 in all and Novita 92, 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 train on what you send it, and not stated. Novita does not say, and not stated. 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 day. Nebius Token Factory was last read 16 Sept 2026 and Novita 16 Sept 2026; the whole index was refreshed 16 Sept 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.
Provider pageseverything Nebius Token Factory sellseverything Novita sellsMore matchupsDeepInfra vs Nebius Token FactoryDeepInfra vs Novita