DeepInfra vs Nebius Token Factory.

model prices compared · prices as of · 26 models both sell

DeepInfra is cheaper on 21 of the 26 models both sell, Nebius Token Factory on 4, and 1 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 gpt-oss-120b, $0.28 per million tokens at DeepInfra against $1.05.

DeepInfra is cheaper on 21 of the 26 models both sell, and the cheapest thing either one offers is Mistral Nemo at $0.09 per million tokens, read 16 Sept 2026.

Serves open-weight models on its own GPUs, often at fp8 or fp4, and publishes the precision per model.

cheapest here: Mistral Nemo at $0.09/M tokens

Nebius Token Factoryall 31 models →

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

cheapest here: Mistral Nemo at $0.24/M tokens

Kind of providerHostHost
Models we track10631
Cheaper of the two21 of 264 of 26
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.

ModelDeepInfraNebius Token Factory
DeepSeek V4 Flash 0731DeepSeek · 1M context$0.45$0.09 / $0.18 in / out$0.70$0.14 / $0.28 in / out
GLM-5.2Z.ai · 1M context$4.65$0.75 / $2.40 in / out$8.60$1.40 / $4.40 in / out
DeepSeek V4 ProDeepSeek · 1M context$6.50$1.30 / $2.60 in / out$8.75$1.75 / $3.50 in / out
Kimi K2.6Moonshot AI · 262k context$5.75$0.75 / $3.50 in / out$6.85$0.95 / $4 in / out
Kimi K3Moonshot AI · 1M context$22.80$2.85 / $14.25 in / out$24$3 / $15 in / out
GLM-5.3-FlashZ.ai · 1M context$0.95$0.15 / $0.50 in / out$0.95$0.15 / $0.50 in / out
Kimi K2.7 CodeMoonshot AI · 262k context$5.44$0.68 / $3.40 in / out$6.85$0.95 / $4 in / out
gpt-oss-120bOpenAI · 131k context$0.28$0.04 / $0.17 in / out$1.05$0.15 / $0.60 in / out
GLM-5.1Z.ai · 200k context$6.65$1.05 / $3.50 in / out$8.60$1.40 / $4.40 in / out
MiniMax-M3MiniMax · 1M context$1.94$0.28 / $1.10 in / out$2.10$0.30 / $1.20 in / out
MiniMax-M2.5MiniMax · 205k context$1.60$0.15 / $1.15 in / out$2.10$0.30 / $1.20 in / out
Llama-3.3-70B-InstructMeta · 128k context$0.62$0.10 / $0.32 in / out$0.79$0.13 / $0.40 in / out
Qwen3.5 397B-A17BAlibaba Cloud · 262k context$4.35$0.45 / $3 in / out$5.40$0.60 / $3.60 in / out
Qwen3 235B-A22BAlibaba Cloud · 131k context$0.82$0.09 / $0.55 in / out$1.20$0.20 / $0.60 in / out
R1 0528DeepSeek · 164k context$3.65$0.50 / $2.15 in / out$4.80$0.80 / $2.40 in / out
Qwen3 30B A3B Instruct 2507Alibaba Cloud · 262k context$0.86$0.12 / $0.50 in / out$0.60$0.10 / $0.30 in / out
Mistral NemoMistral AI · 128k context$0.09$0.02 / $0.03 in / out$0.24$0.04 / $0.12 in / out
Gemma 3 27BGoogle · 131k context$0.40$0.08 / $0.16 in / out$0.60$0.10 / $0.30 in / out
Qwen3-Next 80B-A3B (Thinking)Alibaba Cloud · 131k context$1.82$0.14 / $1.40 in / out$1.65$0.15 / $1.20 in / out
Qwen3 14BAlibaba Cloud · 131k context$0.60$0.12 / $0.24 in / out$0.48$0.08 / $0.24 in / out
R1 Distill Llama 70BDeepSeek · 8k context$1.20$0.20 / $0.60 in / out$1.50$0.25 / $0.75 in / out
Nemotron 3 UltraNVIDIA · 262k context$3.70$0.50 / $2.20 in / out$6$1 / $3 in / out
Nemotron 3 SuperNVIDIA · 262k context$0.66$0.09 / $0.40 in / out$1.80$0.30 / $0.90 in / out
Nemotron 3 Nano 30B A3BNVIDIA · 262k context$0.35$0.05 / $0.20 in / out$0.42$0.06 / $0.24 in / out
Nemotron 3.5 LightningNVIDIA · 262k context$0.44$0.08 / $0.20 in / out$0.42$0.06 / $0.24 in / out
Hermes 3 405B InstructNous Research · 131k context$4$1 / $1 in / out$6$1 / $3 in / out

Frequently asked

Is DeepInfra cheaper than Nebius Token Factory?
On the 26 models both sell, DeepInfra is cheaper on 21, Nebius Token Factory on 4, and 1 cost the same at both. The widest gap is gpt-oss-120b: $0.28 per million tokens against $1.05. Prices are blended three parts input to one part output and read on 16 Sept 2026.
Which models do DeepInfra and Nebius Token Factory both sell?
26 of the models we track, led by DeepSeek V4 Flash 0731, GLM-5.2, DeepSeek V4 Pro. DeepInfra sells 106 in all and Nebius Token Factory 31, so most of each catalog has no counterpart at the other.
Does DeepInfra or Nebius Token Factory train on what you send it?
DeepInfra does not say train on what you send it, and not stated. Nebius Token Factory 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. DeepInfra was last read 16 Sept 2026 and Nebius Token Factory 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 DeepInfra sellseverything Nebius Token Factory sellsMore matchupsDeepInfra vs Fireworks AIDeepInfra vs GroqDeepInfra vs NovitaDeepInfra vs OpenRouterDeepInfra vs Together AINebius Token Factory vs Novita