Aggregator

Fireworks AI

/fireworks-ai · Redwood City, USA · est. 2022

Key facts

  • Fireworks AI is a aggregator headquartered in Redwood City, USA, founded 2022.
  • Exposes an OpenAI-compatible API, so existing OpenAI SDK code can target it by changing the base URL.
  • Blended reference price is $0.90 per 1M tokens (in $0.90 / out $0.90).
  • Reference latency 300 ms TTFT at 145 tok/s throughput, with 99.7% reference uptime.
  • Editorial reputation index 85/100 from 388 weighted signals; 90-day trend improving.

Specification

Category
Aggregator
Headquarters
Redwood City, USA
Founded
2022
Model access
Open weights
Flagship / served
FireAttention-served open models
Reference open model
Llama 3.3 70B
OpenAI-compatible API
Yes
Blended $/1M
$0.90 medium

Strengths & trade-offs

Strength

Low-latency serving stack and strong function-calling support.

Trade-off

Smaller catalog than the largest aggregators.


Profile reviewed 2026-07-10. Confidence for this listing:high — Figure confirmed against the provider's public pricing/docs page on the last_reviewed date.Not affiliated with Fireworks AI. ← Back to directory