OpenAI compatible API. Attested gateway. Public status.
Phala
Phala models on TrustedRouter with prices, routes, policy notes, and source links.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
phala
Confidential
| Provider | Phala |
|---|---|
| Models | 18 public models |
| Prepaid routes | 18 |
| BYOK routes | 18 |
| Zero data retention | yes |
| Confidential compute | yes |
| Provider E2EE | yes |
| Policy note | Tracked as a confidential AI provider with provider-side attestation and encrypted prompt transport. Policy source |
Measured performance
320 samplesContinuously sampled across Phala'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 | 1393 ms |
|---|---|
| Throughput | — |
| Uptime | 0.31% |
| Model | p50 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-20b | 1393 ms | 1391 ms | — | 7.69% | — | 13 |
| moonshotai/kimi-k2.5 | — | — | — | 0.00% | — | 15 |
| deepseek/deepseek-chat-v3.1 | — | — | — | 0.00% | — | 23 |
| qwen/qwen3.5-27b | — | — | — | 0.00% | — | 14 |
| z-ai/glm-5 | — | — | — | 0.00% | — | 23 |
| z-ai/glm-5.1 | — | — | — | 0.00% | — | 26 |
| google/gemma-3-27b-it | — | — | — | 0.00% | — | 20 |
| deepseek/deepseek-v3.2 | — | — | — | 0.00% | — | 14 |
| minimax/minimax-m2.5 | — | — | — | 0.00% | — | 12 |
| qwen/qwen3-vl-30b-a3b-instruct | — | — | — | 0.00% | — | 16 |
| qwen/qwen2.5-vl-72b-instruct | — | — | — | 0.00% | — | 22 |
| qwen/qwen-2.5-7b-instruct | — | — | — | 0.00% | — | 16 |
| qwen/qwen3-30b-a3b-instruct-2507 | — | — | — | 0.00% | — | 18 |
| z-ai/glm-4.7-flash | — | — | — | 0.00% | — | 19 |
| z-ai/glm-4.7 | — | — | — | 0.00% | — | 20 |
| moonshotai/kimi-k2.6 | — | — | — | 0.00% | — | 14 |
| qwen/qwen3.5-397b-a17b | — | — | — | 0.00% | — | 18 |
| openai/gpt-oss-120b | — | — | — | 0.00% | — | 17 |
Provider models
Models served by Phala.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|
deepseek/deepseek-chat-v3.1DeepSeek: DeepSeek V3.1 |
163,840 | 2 | $1.155/1M | $3.41/1M | prepaid BYOK |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
163,840 | 2 | $0.352/1M | $0.528/1M | prepaid BYOK |
google/gemma-3-27b-itGoogle: Gemma 3 27B |
131,072 | 2 | $0.121/1M | $0.44/1M | prepaid BYOK |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
204,800 | 2 | $0.22/1M | $1.518/1M | prepaid BYOK |
moonshotai/kimi-k2.5MoonshotAI: Kimi K2.5 |
262,144 | 2 | $0.66/1M | $3.3/1M | prepaid BYOK |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
262,144 | 2 | $1.199/1M | $5.06/1M | prepaid BYOK |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
131,072 | 2 | $0.165/1M | $0.66/1M | prepaid BYOK |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
131,072 | 2 | $0.044/1M | $0.165/1M | prepaid BYOK |
qwen/qwen-2.5-7b-instructQwen: Qwen2.5 7B Instruct |
131,072 | 2 | $0.044/1M | $0.11/1M | prepaid BYOK |
qwen/qwen2.5-vl-72b-instructQwen: Qwen2.5 VL 72B Instruct |
131,072 | 2 | $0.22/1M | $0.77/1M | prepaid BYOK |
qwen/qwen3-30b-a3b-instruct-2507Qwen: Qwen3 30B A3B Instruct 2507 |
131,072 | 2 | $0.165/1M | $0.605/1M | prepaid BYOK |
qwen/qwen3-vl-30b-a3b-instructQwen: Qwen3 VL 30B A3B Instruct |
262,144 | 2 | $0.22/1M | $0.77/1M | prepaid BYOK |
qwen/qwen3.5-27bQwen: Qwen3.5-27B |
262,144 | 2 | $0.33/1M | $2.64/1M | prepaid BYOK |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
262,144 | 2 | $0.605/1M | $3.85/1M | prepaid BYOK |
z-ai/glm-4.7Z.ai: GLM 4.7 |
202,752 | 2 | $0.935/1M | $3.63/1M | prepaid BYOK |
z-ai/glm-4.7-flashZ.ai: GLM 4.7 Flash |
202,752 | 2 | $0.11/1M | $0.473/1M | prepaid BYOK |
z-ai/glm-5Z.ai: GLM 5 |
204,800 | 2 | $1.32/1M | $3.85/1M | prepaid BYOK |
z-ai/glm-5.1Z.ai: GLM 5.1 |
202,752 | 2 | $1.331/1M | $4.62/1M | prepaid BYOK |