OpenAI compatible API. Attested gateway. Public status.

FriendliAI

FriendliAI models on TrustedRouter with prices, routes, policy notes, and source links.

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`friendli`

No provider claim

All providers

Provider	FriendliAI
Models	8 public models
Prepaid routes	8
BYOK routes	8
Zero data retention	not claimed
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	No provider-ZDR claim is tracked here. Friendli's legal/privacy terms are linked for users who need to review API data handling. Policy source

Measured performance

259 samples

Continuously sampled across FriendliAI's routed models — p50 TTFT, throughput, and success rate. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	1579 ms
Throughput	19 tok/s
Uptime	94.98%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
meta-llama/llama-3.1-8b-instruct	1146 ms	1145 ms	—	100.00%	—	3
minimax/minimax-m2.5	1282 ms	1281 ms	—	100.00%	—	8
qwen/qwen3-235b-a22b-2507	1579 ms	11105 ms	19 tok/s	99.50%	—	201
deepseek/deepseek-v3.2	1847 ms	1847 ms	—	100.00%	—	10
lgai-exaone/k-exaone-236b-a23b	3107 ms	3106 ms	—	100.00%	—	9
z-ai/glm-5.1	8914 ms	8912 ms	—	100.00%	—	13
z-ai/glm-5.2	9268 ms	9267 ms	—	100.00%	—	3
meta-llama/llama-3.3-70b-instruct	—	—	—	0.00%	—	12

Full provider & model leaderboard.

Provider models

Models served by FriendliAI.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Endpoints	Prompt	Completion	Routes
`deepseek/deepseek-v3.2` DeepSeek: DeepSeek V3.2 benchmarks performance api	IQ 101#47	163,840	2	$0.55/1M	$1.65/1M	prepaid BYOK
`lgai-exaone/k-exaone-236b-a23b` Friendli K-EXAONE 236B A23B benchmarks performance api	—	262,144	2	$0.22/1M	$0.88/1M	prepaid BYOK
`meta-llama/llama-3.1-8b-instruct` Meta: Llama 3.1 8B Instruct benchmarks performance api	—	131,072	2	$0.11/1M	$0.11/1M	prepaid BYOK
`meta-llama/llama-3.3-70b-instruct` Meta: Llama 3.3 70B Instruct benchmarks performance api	—	131,072	2	$0.66/1M	$0.66/1M	prepaid BYOK
`minimax/minimax-m2.5` MiniMax: MiniMax M2.5 benchmarks performance api	IQ 103#43	204,800	2	$0.33/1M	$1.32/1M	prepaid BYOK
`qwen/qwen3-235b-a22b-2507` Qwen: Qwen3 235B A22B Instruct 2507 benchmarks performance api	—	262,144	2	$0.22/1M	$0.88/1M	prepaid BYOK
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks performance api	IQ 113#19	202,752	2	$1.54/1M	$4.84/1M	prepaid BYOK
`z-ai/glm-5.2` GLM 5.2 benchmarks performance api	IQ 117#10	1,048,576	2	$1.54/1M	$4.84/1M	prepaid BYOK