Phala
Explore Phala models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Phalaphala
ZDR
These privacy labels describe Phala, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | Phala |
|---|---|
| Routing status | Active |
| Provider website | https://phala.network/ |
| Models | 5 public models |
| Credits routes | 5 |
| Zero data retention | yes All routes |
| Verified confidential inference | Not verified |
| 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
26 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 | 3329 ms |
|---|---|
| Effective throughput | 46 tok/s n=3 |
| Uptime | 57.69% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| moonshotai/kimi-k3 | 2545 ms | 33 tok/s n=1 | 100.00% | — | 8 |
| z-ai/glm-5.1 | 3329 ms | — | 50.00% | — | 2 |
| z-ai/glm-5.2 | 4342 ms | 46 tok/s n=2 | 85.71% | — | 7 |
| z-ai/glm-5.3 | — | — | 0.00% | — | 6 |
| z-ai/glm-5.3-flash | — | — | 0.00% | — | 3 |
Phala performance history · Full provider & model leaderboard.
Models served by Phala.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 121#27 | 1,048,576 | $3.165/1M | $0.3165/1M | $15.825/1M |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 113#49 | 202,752 | $1.27655/1M | $0.633/1M | $4.431/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#28 | 1,048,576 | $1.3293/1M | $0.2321/1M | $3.165/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 123#18 | 1,048,576 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 116#40 | 1,048,576 | $0.15825/1M | $0.03165/1M | $0.5275/1M |
Questions
Does Phala have zero data retention?
TrustedRouter records Phala 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 Phala end-to-end encrypted?
TrustedRouter does not currently mark Phala as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Phala models are available through TrustedRouter?
This page currently lists 5 public Phala models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.