Fireworks AI pricing
Fireworks AI API Pricing Calculator
Serverless, batch, and priority deployments can have different rates.
Quick estimate
No API key needed. Pick a model, paste your question, choose the answer length, and get a close cost estimate.
$0.95/M input$4/M outputCache pricingBatchPriority
3. How long will the AI answer be?
Your estimate will appear here.
Paste a prompt, choose an answer length, and calculate.
Active model pricing
| Model | Input / 1M | Output / 1M | Cached / 1M | Notes |
|---|---|---|---|---|
| Kimi K2.7 Code | $0.95 | $4 | $0.19 | Code-focused serverless model. |
| DeepSeek V4 Flash | $0.14 | $0.28 | $0.028 | Low-cost Fireworks serverless model. |
| OpenAI GPT OSS 120B | $0.15 | $0.6 | $0.015 | Fireworks OSS hosted model. |
How do I estimate Fireworks AI API cost?
Choose a Fireworks AI model, paste prompt text, optionally paste output text, and use advanced controls for cache, tier, region, and tools.
Does Fireworks AI pricing include more than tokens?
Serverless, batch, and priority deployments can have different rates.