Fireworks AI pricing
Fireworks AI publishes 9 plans and has a free tier, with self-serve signup, so an agent can start without talking to sales.
Last checked 2026-08-23. Always verify on the vendor's own page before you commit spend.
| Plan | Price | Included |
|---|---|---|
| Serverless Inference | Pay per token | High rate limits, postpaid billing, $1 in free credits to start |
| Embeddings - up to 150M | $0.008 / 1M input tokens | - |
| Embeddings - 150M-350M | $0.016 / 1M input tokens | - |
| Embeddings - Qwen3 8B | $0.1 / 1M input tokens | - |
| Training - Models up to 16B | LoRA SFT: $0.50, LoRA DPO: $1.00, Full Param SFT: $1.00, Full Param DPO: $2.00 per 1M training tokens | - |
| Training - Models 16.1B-80B | LoRA SFT: $3.00, LoRA DPO: $6.00, Full Param SFT: $6.00, Full Param DPO: $12.00 per 1M training tokens | - |
| Training - Models 80B-300B | LoRA SFT: $6.00, LoRA DPO: $12.00, Full Param SFT: $12.00, Full Param DPO: $24.00 per 1M training tokens | - |
| Training - Models >300B | LoRA SFT: $10.00, LoRA DPO: $20.00, Full Param SFT: $20.00, Full Param DPO: $40.00 per 1M training tokens | - |
| On Demand Deployments | Pay per GPU second | Faster speeds, higher rate limits, lower costs at scale |
Also: Fireworks AI agent-readiness profile · Fireworks AI alternatives
An agent can fetch this as data: GET /v1/pricing?domain=fireworks.ai