Tinfoil
Explore Tinfoil models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Tinfoiltinfoil
Confidential
| Provider | Tinfoil |
|---|---|
| Routing status | Active |
| Provider website | https://tinfoil.sh/ |
| Models | 8 public models |
| Credits routes | 8 |
| Zero data retention | yes All routes |
| 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
83 samplesContinuously sampled across Tinfoil's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 2724 ms |
|---|---|
| Effective throughput | 63 tok/s n=2 |
| Uptime | 93.98% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash | 2724 ms | 58 tok/s n=1 | 90.20% | — | 51 |
| google/gemma-4-31b-it | 685 ms | 67 tok/s n=1 | 100.00% | — | 4 |
| meta-llama/llama-3.3-70b-instruct | 1609 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1653 ms | — | 100.00% | — | 6 |
| z-ai/glm-5.3 | 1753 ms | — | 100.00% | — | 8 |
| z-ai/glm-5.3-flash | 3012 ms | — | 100.00% | — | 9 |
| z-ai/glm-5.2 | 3720 ms | — | 100.00% | — | 3 |
Tinfoil performance history · Full provider & model leaderboard.
Models served by Tinfoil.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 113#46 | 1,024,000 | $0.3165/1M | $0.0633/1M | $0.7385/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#80 | 262,144 | $0.422/1M | Not published | $1.055/1M |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | $1.84625/1M | Not published | $2.90125/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 123#21 | 1,048,576 | $4.22/1M | $0.844/1M | $21.1/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#69 | 131,072 | $0.15825/1M | Not published | $0.633/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#27 | 1,048,576 | $1.5825/1M | $0.395625/1M | $5.53875/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 123#19 | 1,048,576 | $1.899/1M | $0.47475/1M | $6.06625/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 121#24 | 1,048,576 | $0.422/1M | $0.1055/1M | $1.31875/1M |
Questions
Does Tinfoil have zero data retention?
TrustedRouter records Tinfoil as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is Tinfoil end-to-end encrypted?
TrustedRouter records Tinfoil as supporting provider-side confidential compute and end-to-end encrypted inference. The route-specific model page shows whether that protection applies to a particular endpoint.
Which Tinfoil models are available through TrustedRouter?
This page currently lists 8 public Tinfoil models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.