All promotions
GuidesMCP

Fireworks AI

Inference providerUS Westprices checked Oct 23, 06:00 UTC

Pricing page ↗

Fireworks AI serves 10 models at a verified price. On the 10 it shares with other hosts, it is the cheapest on 1 and charges a median 146% above the cheapest.

Models served1010 with open weights
Cheapest input, per M$0.07gpt-oss-20b
Uptime, last 24 h97.9%average of its 7 OpenRouter endpoints
Sign-upno free credits stated
Newest first
ModelPrecisionContextToolsInputOutputCache
DeepSeek V4.1 Flash 1017not checked yet1M✓$0.30$1.20$0.006
Muse Spark Opencheapestnot checked yet1M✓$1.25$4.25$0.15
DeepSeek V4.1 Flashnot checked yet1M✓$0.30$1.20$0.006
GLM-5.3-Flashnot checked yet1M✓$0.15$0.50$0.03
DeepSeek V4 Flash Vision Expnot checked yet1M—$0.22$0.66$0.007
GLM-5.3not checked yet1M✓$1.40$4.40$0.26
Kimi K3not checked yet1M—$3.00$15.00$0.30
GLM 5.2not checked yet1M—$1.40$4.40$0.14
MiniMax-M3not checked yet500K—$0.30$1.20$0.06
gpt-oss-20bnot checked yet125K—$0.07$0.30$0.035

10 of 10 models · prices per million tokens · precision and context: read at Fireworks AI's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Fireworks AI declares them to OpenRouter

ConditionWhat it saysSource
Sign-upNot checked yetdocs.fireworks.ai
Free creditsNone stated—
Headquarters regionUS West—
Price listWhere its per-token prices are publisheddocs.fireworks.ai
API documentationIts own docsdocs.fireworks.ai
Status pageOutages and incidents, as Fireworks AI reports themstatus.fireworks.ai
Free credits$1 starter creditdocs.fireworks.ai

Links checked Oct 8.