fireworks-ai
Fireworks AI
7 models on Fireworks AI, with the price per million tokens and who ends up holding your prompt.
- Company based in
- 🇺🇸 United States
- How it serves
- Runs 6 models itself · 1 model unconfirmed
- Training on your prompts
- off by default
- Data policy source
- fireworks.ai
- Policy checked
- 2026-10-20
Models
| Model | Input $/M | Output $/M | Blended* | Holds your prompt | Training |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.52 | runs it 🇺🇸 United States | off by default |
| DeepSeek V4.1 Flash 1017 | $0.30 | $1.20 | $0.52 | runs it 🇺🇸 United States | off by default |
| Ember-1 | $3.00 | $15.00 | $6.00 | runs it 🇺🇸 United States | off by default |
| GLM-5.3 | $1.40 | $4.40 | $2.15 | runs it 🇺🇸 United States | off by default |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.24 | runs it 🇺🇸 United States | off by default |
| MiniMax M3.1 Flash | $0.15 | $0.60 | $0.26 | unverified | |
| Muse Spark Open | $1.25 | $4.25 | $2.00 | runs it 🇺🇸 United States | off by default |
Blended is our calculation: (3 × input + output) ÷ 4, US dollars per million tokens — most calls read far more than they write. Tiers that are cheaper because they train on your data are not used for the “from” price.