OpenAI compatible API. Attested gateway. Public status.

Tinfoil

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

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`tinfoil`

Confidential

All providers

Provider	Tinfoil
Models	5 public models
Prepaid routes	5
BYOK routes	5
Zero data retention	yes
Confidential compute	yes
Provider E2EE	yes
Policy note	Tracked as a confidential inference provider with attested provider compute and no prompt/output logging claims. Policy source

Measured performance

320 samples

Continuously sampled across Tinfoil'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	1199 ms
Throughput	—
Uptime	92.50%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
meta-llama/llama-3.3-70b-instruct	915 ms	811 ms	—	100.00%	—	59
openai/gpt-oss-120b	1188 ms	1102 ms	—	100.00%	—	58
deepseek/deepseek-v4-pro	1199 ms	1122 ms	—	100.00%	—	70
moonshotai/kimi-k2.6	1399 ms	1368 ms	—	100.00%	—	60
z-ai/glm-5.1	3665 ms	3601 ms	—	67.12%	—	73

Full provider & model leaderboard.

Provider models

Models served by Tinfoil.

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

Model	Context	Endpoints	Prompt	Completion	Routes
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro benchmarks performance api	1,048,576	2	$1.65/1M	$5.775/1M	prepaid BYOK
`meta-llama/llama-3.3-70b-instruct` Meta: Llama 3.3 70B Instruct benchmarks performance api	131,072	2	$1.925/1M	$3.025/1M	prepaid BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks performance api	262,144	2	$1.65/1M	$5.775/1M	prepaid BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b benchmarks performance api	131,072	2	$0.825/1M	$1.375/1M	prepaid BYOK
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks performance api	202,752	2	$1.65/1M	$5.775/1M	prepaid BYOK