Fireworks
US · serverless
Low-latency serverless inference with its own optimised runtime and on-demand GPU deployments.
- Category
- serverless
- Free tier
- Yes
- OpenAI API
- Compatible
- Adds on top
- None - sets its own prices
Margin over the underlying model price
What Fireworks charges
Live prices for widely-hosted open-weight models, sampled from the shared catalogue. Compare the same row against other hosts on each model page.
| Model | Input / 1M | Output / 1M | Context | Throughput |
|---|---|---|---|---|
| MiniMax M3.1 Flash | $0.150 | $0.600 | 1.0M | - |
| GLM 5.3 Flash | $0.150 | $0.500 | 1.0M | - |
| DeepSeek V4.1 Flash 1017 | $0.210 | $0.840 | 1.0M | - |
| DeepSeek V4.1 Flash | $0.210 | $0.840 | 1.0M | - |
| GLM 5.3 | $0.980 | $3.08 | 1.0M | - |
| Muse Spark Open | $1.25 | $4.25 | 1.0M | - |
Fireworks alternatives
Other services in the same category. These are genuine substitutes - services in a different category solve a different problem.
Frequently asked
Is Fireworks OpenAI-compatible?
Yes. Fireworks accepts the OpenAI chat-completions request shape, so most SDKs work by changing the base URL and API key.
Does Fireworks have a free tier?
Yes - Fireworks offers free usage, though limits and eligible models change frequently. Check the pricing page before relying on it.
How does Fireworks charge?
Per token, plus per-GPU-hour for dedicated Margin over the underlying model price: none - sets its own prices.