All promotions
GuidesMCP

Friendli

Inference providerUS Westprices checked Oct 23, 06:00 UTC

Pricing page ↗

Friendli serves 7 models at a verified price. On the 7 it shares with other hosts, it is never the cheapest and charges a median 121% above it.

Models served77 with open weights
Cheapest input, per M$0.14Gemma 4 31B
Uptime, last 24 h100%average of its 7 OpenRouter endpoints
Sign-upno free credits stated
Newest first
ModelPrecisionContextToolsInputOutputCache
GLM-5.3-Flashnot read: host terms1M✓$0.15$0.50$0.03
GLM-5.3not read: host terms1M✓$1.26$3.96$0.23
GLM 5.2not read: host terms1M✓$1.40$4.40$0.26
GLM 5.1not read: host terms198K✓$1.40$4.40$0.26
Gemma 4 31Bnot read: host terms256K✓$0.14$0.40—
MiniMax M2.5not read: host terms200K✓$0.30$1.20$0.06
DeepSeek V3.2not read: host terms160K✓$0.50$1.50$0.25

7 of 7 models · prices per million tokens · precision and context: read at Friendli's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Friendli declares them to OpenRouter

ConditionWhat it saysSource
Sign-upCard requiredfriendli.ai
Free creditsNone stated—
Headquarters regionUS West—
Price listWhere its per-token prices are publishedfriendli.ai
API documentationIts own docsfriendli.ai
Status pageOutages and incidents, as Friendli reports themstatus.friendli.ai
Terms of serviceIts termsfriendli.ai

Links checked Oct 8.