← All providers
open source-host

Fireworks

Low-latency OSS inference with function calling.

live
Uptime (30d)
99.92%
Median tps
245
Median TTFT
110 ms
Price index
0.55×
vs. market median
Overview
HQ
Redwood City, US
Founded
2022
Models
45
Modalities
text, vision, audio
Regions
us-east, us-west, asia-southeast
Strengths
low-latencyfunction-calling
Route via llmcloud
curl https://api.llmcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMCLOUD_KEY" \
  -H "X-Provider: fireworks" \
  -d '{
    "model": "auto:quality",
    "messages": [{"role":"user","content":"hi"}]
  }'