Models
All TEE LLM Models
GPU TEE model endpoints with pricing, context windows, API calls, and verification details.
TEE models
25
providers
10
API
1
Showing 25 of 25 TEE models
inference.phala.com/v1/models
DeepSeek: DeepSeek V4.1 Flash 1017
Beta
1.0M context
$0.75/M input
$1.60/M output
$0.15/M cache read
Phala: Qwen3.8 27B Uncensored (Aggressive)
262K context
$0.30/M input
$1.50/M output
$0.05/M cache read
Z.ai: GLM 5.3 Flash
Beta
1.0M context
$0.15/M input
$0.50/M output
$0.03/M cache read
DeepSeek: DeepSeek V4 Flash 0731
1.0M context
$0.44/M input
$1.32/M output
$0.028/M cache read
Qwen: Qwen3.6 35B A3B
262K context
$0.20/M input
$1.27/M output
$0.056/M cache read
Phala: Gemma-4 26B-A4B Uncensored (Heretic)
262K context
$0.15/M input
$0.70/M output
$0.05/M cache read
Qwen: Qwen3.5 397B A17B
262K context
$0.55/M input
$3.50/M output
$0.225/M cache read
DeepSeek: DeepSeek V3.2
164K context
$1.00/M input
$1.00/M output
$0.50/M cache read
Qwen: Qwen3 VL 30B A3B Instruct
128K context
$0.20/M input
$0.70/M output
$0.03/M cache read
Prompt caching
Providers can reuse a repeated prompt prefix automatically. No extra request parameter is needed. Put stable system instructions and reference material first, then add the changing question at the end. Cache availability and minimum prefix length depend on the provider and model.
Cached input tokens use the listed cache-read rate. When a model has no cache-read rate, the normal input rate applies. Output tokens use the output rate. A listed rate does not guarantee a cache hit.
Check usage.prompt_tokens_details.cached_tokens in the response. Cached tokens are part of prompt_tokens, so subtract them before calculating uncached input cost. In this example, 1,792 input tokens are cached and 113 are uncached.
"usage": {
"prompt_tokens": 1905,
"prompt_tokens_details": { "cached_tokens": 1792 },
"completion_tokens": 64
}