Providers

Phala Confidential AI

Verified

Confidential model inference inside GPU trusted execution environments with verifiable attestation.

Start building View requests Official status

Models on Phala Confidential AI

Open in catalog

16 of 16

DeepSeek V3.2Chatdeepseek-v3.2164K contextWeights Routeemergency$0.56 / $0.84per M input / output

DeepSeek V4 FlashChatdeepseek-v4-flashReleased Apr 24, 20261M contextWeights Routeemergency$0.14 / $0.28per M input / output

DeepSeek V4 Flash 0731Chatdeepseek-v4-flash-07311M contextWeights Routeemergency$0.22 / $0.66per M input / output

Gemma 4 31BChatgemma-4-31b262K contextRouteemergency$0.18 / $0.50per M input / output

GLM 5.1Chatglm-5.1164K contextRouteemergency$1.40 / $4.40per M input / output

GLM 5.2Chatglm-5.2Released June 20261M contextWeights Routeemergency$1.40 / $4.40per M input / output

GLM 5.3Chatglm-5.3Released Aug 18, 20261M contextRouteemergency$1.40 / $4.40per M input / output

GLM 5.3 FlashChatglm-5.3-flashReleased Aug 26, 20261M contextRouteemergency$0.15 / $0.50per M input / output

GPT-OSS 120BChatgpt-oss-120bReleased Aug 5, 2025131K contextWeights Routeemergency$0.35 / $0.75per M input / output

Kimi K2.6Chatkimi-k2.6262K contextRouteemergency$0.95 / $4.00per M input / output

Kimi K3Chatkimi-k3Released Jul 16, 20261M contextRouteemergency$3.00 / $15.00per M input / output

Llama 3.3 70B Instruct TurboChatllama-3.3-70b131K contextRouteemergency$0.10 / $0.32per M input / output

Muse Glimmer 30BChatmuse-glimmer-30bReleased August 2026131K contextRouteemergency$0.35 / $1.50per M input / output

Qwen 3.5 397B A17BChatqwen-3.5-397b-a17b262K contextRouteemergency$0.55 / $3.50per M input / output

Qwen 3.6 35B A3BChatqwen-3.6-35b-a3b262K contextRouteemergency$0.10 / $0.95per M input / output

Qwen 3.8 27BChatqwen-3.8-27bReleased Aug 26, 20261M contextRouteemergency$0.45 / $3.20per M input / output

Direct routingCall Phala Confidential AI explicitly

phala· routing

# pin every request to Phala Confidential AI
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "routing": { "providers": { "only": ["phala"] } }
  }'