DeepInfra vs Fireworks AI.
model prices compared · prices as of · 31 models both sell
DeepInfra is cheaper on 27 of the 31 models both sell, Fireworks AI on 2, and 2 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 Mistral Small 3, $0.23 per million tokens at DeepInfra against $3.60.
DeepInfra is cheaper on 27 of the 31 models both sell, and the cheapest thing either one offers is Mistral Nemo at $0.09 per million tokens, read 16 Sept 2026.
DeepInfraall 106 models →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
Fireworks AIall 45 models →Serves open-weight models on its own GPUs; on-demand deployments are priced per GPU-hour.
cheapest here: gpt-oss-20b at $0.51/M tokens
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.
Frequently asked
- Is DeepInfra cheaper than Fireworks AI?
- On the 31 models both sell, DeepInfra is cheaper on 27, Fireworks AI on 2, and 2 cost the same at both. The widest gap is Mistral Small 3: $0.23 per million tokens against $3.60. Prices are blended three parts input to one part output and read on 16 Sept 2026.
- Which models do DeepInfra and Fireworks AI both sell?
- 31 of the models we track, led by DeepSeek V4 Flash 0731, GLM-5.2, DeepSeek V4 Pro. DeepInfra sells 106 in all and Fireworks AI 45, so most of each catalog has no counterpart at the other.
- Does DeepInfra or Fireworks AI train on what you send it?
- DeepInfra does not say train on what you send it, and not stated. Fireworks AI 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 Fireworks AI 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.