OpenAI compatible API · Attested · Public status
Phala
Explore Phala models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Phalaphala
No logs
| Provider | Phala |
|---|---|
| Provider website | https://phala.network/ |
| Models | 2 public models |
| Prepaid routes | 2 |
| BYOK routes | 2 |
| Zero data retention | yes |
| Confidential compute | yes |
| Provider E2EE | no |
| Policy note | Phala publishes TDX/GPU attestation and signed request receipts, but TrustedRouter does not yet verify the complete receipt chain on every routed request. The route is therefore not classified as provider E2EE and is excluded from trustedrouter/e2e. Policy source |
Measured performance
50 samplesContinuously sampled across Phala'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 | 4046 ms |
|---|---|
| Effective throughput | 23 tok/s n=2 |
| Uptime | 96.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| z-ai/glm-5.2 | 2185 ms | 2184 ms | 32 tok/s n=1 | 100.00% | — | 19 |
| moonshotai/kimi-k3 | 4046 ms | 4046 ms | 13 tok/s n=1 | 93.55% | — | 31 |
Phala performance history · Full provider & model leaderboard.
Provider models
Models served by Phala.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 123#14 | 1,048,576 | 2 | $3.15/1M | $15.75/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#16 | 1,048,576 | 2 | $1.47/1M | $4.62/1M | prepaid BYOK |