DeepInfra vs Fireworks AI.
Prices checked
DeepInfra is cheaper on 28 of the 33 models both sell, the widest gap Mistral Small 3 at 5.8¢ against $0.90 per M tokens, checked .
Where to start
DeepInfraall 126 models Serves open-weight models on its own GPUs, often at fp8 or fp4, and publishes the precision per model.
Cheapest of the shared models
2.9¢/M tokens
Mistral Nemo
Fireworks AIall 53 models Serves open-weight models on its own GPUs; on-demand deployments are priced per GPU-hour.
Cheapest of the shared models
8.8¢/M tokens
Nemotron 3.5 Lightning
Side by side
| Fact | DeepInfra | Fireworks AI |
|---|---|---|
| Kind of provider | Host | Host |
| Models we track | 126 | 53 |
| Cheaper of the two | 28 of 33 | 3 of 33 |
| 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
33 models, most widely sold first. Per M tokens, blended 3 in : 1 out.
| Model | DeepInfra | Fireworks AI |
|---|---|---|
| GLM-5.3Z.ai · 1M context | $1.68 $0.90 in · $4 out | $2.15 $1.40 in · $4.40 out |
| GLM-5.3-FlashZ.ai · 1M context | $0.24 $0.15 in · $0.50 out | $0.24 $0.15 in · $0.50 out |
| DeepSeek V4.1 Flash 1017DeepSeek · 1M context | $0.30 $0.20 in · $0.60 out | $0.52 $0.30 in · $1.20 out |
| DeepSeek V4 Flash 0731DeepSeek · 1M context | 9¢ 6¢ in · $0.18 out | $0.18 $0.14 in · $0.28 out |
| Kimi K3Moonshot AI · 1M context | $5.70 $2.85 in · $14.25 out | $6 $3 in · $15 out |
| DeepSeek V4 ProDeepSeek · 1M context | $1.63 $1.30 in · $2.60 out | $1.98 $1.32 in · $3.96 out |
| gpt-oss-120bOpenAI · 131k context | 7¢ 3.7¢ in · $0.17 out | $0.26 $0.15 in · $0.60 out |
| MiniMax-M3MiniMax · 1M context | $0.49 $0.28 in · $1.10 out | $0.52 $0.30 in · $1.20 out |
| gpt-oss-20bOpenAI · 131k context | 5.8¢ 3¢ in · $0.14 out | $0.13 7¢ in · $0.30 out |
| R1 0528DeepSeek · 164k context | $0.91 $0.50 in · $2.15 out | $4.25 $3 in · $8 out |
| Qwen3 235B-A22BAlibaba Cloud · 131k context | $0.21 9¢ in · $0.55 out | $0.39 $0.22 in · $0.88 out |
| DeepSeek V3 0324DeepSeek · 164k context | $0.41 $0.24 in · $0.90 out | $0.90 $0.90 in · $0.90 out |
| Qwen3 30B A3BAlibaba Cloud · 262k context | $0.21 $0.12 in · $0.50 out | $0.26 $0.15 in · $0.60 out |
| Qwen3 32BAlibaba Cloud · 131k context | $0.13 8¢ in · $0.28 out | $0.90 $0.90 in · $0.90 out |
| Qwen3 Coder 480B A35BAlibaba Cloud · 262k context | $0.47 $0.30 in · $1 out | $0.79 $0.45 in · $1.80 out |
| Kimi K2 0905Moonshot AI · 262k context | $0.88 $0.50 in · $2 out | $1.08 $0.60 in · $2.50 out |
| Mistral NemoMistral AI · 131k context | 2.9¢ 2.9¢ in · 3¢ out | $0.20 $0.20 in · $0.20 out |
| InklingThinking Machines · 524k context | $1.73 $0.95 in · $4.05 out | $1.76 $1 in · $4.05 out |
| Qwen3 Next 80B A3B InstructAlibaba Cloud · 131k context | $0.34 9¢ in · $1.10 out | $0.90 $0.90 in · $0.90 out |
| Qwen3-VL 235B-A22BAlibaba Cloud · 131k context | $0.37 $0.20 in · $0.88 out | $0.39 $0.22 in · $0.88 out |
| Gemma 3 27BGoogle · 131k context | $0.10 8¢ in · $0.16 out | $0.90 $0.90 in · $0.90 out |
| DeepSeek V4 Flash Vision ExpDeepSeek · 1M context | $0.66 $0.44 in · $1.32 out | $0.33 $0.22 in · $0.66 out |
| Qwen3 14BAlibaba Cloud · 131k context | $0.15 $0.12 in · $0.24 out | $0.20 $0.20 in · $0.20 out |
| Qwen3-VL 30B-A3BAlibaba Cloud · 131k context | $0.26 $0.15 in · $0.60 out | $0.26 $0.15 in · $0.60 out |
| Muse Glimmer 30BMeta · 131k context | $0.52 $0.30 in · $1.20 out | $0.64 $0.35 in · $1.50 out |
| Nemotron 3.5 LightningNVIDIA · 262k context | 8.5¢ 6¢ in · $0.16 out | 8.8¢ 5¢ in · $0.20 out |
| Qwen3 235B A22B Thinking 2507Alibaba Cloud · 128k context | $0.95 $0.30 in · $2.90 out | $0.39 $0.22 in · $0.88 out |
| Qwen3-Next 80B-A3B (Thinking)Alibaba Cloud · 131k context | $0.45 $0.14 in · $1.40 out | $0.90 $0.90 in · $0.90 out |
| MythoMax 13BGryphe · 8k context | $0.40 $0.40 in · $0.40 out | $0.20 $0.20 in · $0.20 out |
| Mistral Small 3Mistral AI · 33k context | 5.8¢ 5¢ in · 8¢ out | $0.90 $0.90 in · $0.90 out |
| Qwq 32BAlibaba Cloud · 24k context | $0.21 $0.15 in · $0.40 out | $0.90 $0.90 in · $0.90 out |
| Deepseek R1 Distill Qwen 32BDeepSeek · 80k context | $0.27 $0.27 in · $0.27 out | $0.90 $0.90 in · $0.90 out |
| NVIDIA Nemotron Nano 9B v2NVIDIA · 131k context | 7¢ 4¢ in · $0.16 out | $0.20 $0.20 in · $0.20 out |
How we count
DeepInfra is cheaper on 28 of the 33 models both sell, Fireworks AI on 3, 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.
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 DeepInfra cheaper than Fireworks AI?
- On the 33 models both sell, DeepInfra is cheaper on 28, Fireworks AI on 3, and 2 cost the same at both. The widest gap is Mistral Small 3: 5.8¢ per million tokens against $0.90. Prices are per M tokens, blended 3 in : 1 out, and read on 31 Oct 2026.
- Which models do DeepInfra and Fireworks AI both sell?
- 33 of the models we track, led by GLM-5.3, GLM-5.3-Flash, DeepSeek V4.1 Flash 1017. DeepInfra sells 126 in all and Fireworks AI 53, 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 whether it trains on what you send it, and does not say how long it keeps requests. Fireworks AI 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. DeepInfra was last read 31 Oct 2026 and Fireworks AI 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.
Provider pages