Step 1. Get an API key on red-pill.ai
Step 2. Query (using phala/deepseek-r1-70b
as example here)
curl -X 'POST' \
'https://api.red-pill.ai/v1/chat/completions' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer <redpill-key>' \
-d '{
"messages": [
{
"content": "You are a helpful assistant.",
"role": "system"
},
{
"content": "What is your model name?",
"role": "user"
}
],
"stream": true,
"model": "phala/deepseek-r1-70b"
}'
Sample output:
data: {"id":"chatcmpl-4af943a924c8414facd482d159ba99e7","object":"chat.completion.chunk","created":1738970726,"model":"deepseek-r1-70b/deepseek-r1-70b","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"stop","stop_reason":128001}]}
data: [DONE]
Available verifiable inference models:
Step 3. Get both CPU and GPU Remote Attestation quotes
curl 'https://api.red-pill.ai/v1/attestation/report?model=phala/deepseek-r1-70b' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer <redpill-key>' | jq
Sample output:
{
"signing_address": "0x2371C9D132D257d62EB7131AacAeAd189Cff43Dd",
"intel_quote": "...",
"nvidia_payload": "..."
}
Step 4. Get the signed inference results. You can get CHAT_ID
from a query result. All the chats will be cached for 5 minutes for you to retrive the signatre.
CHAT_ID=chatcmpl-4af9...
curl "https://api.red-pill.ai/v1/signature/${CHAT_ID}?model=phala/deepseek-r1-70b&signing_algo=ecdsa" \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer <redpill-key>' | jq
Sample output:
{
"text": "e5542b0757e0b9d05bfa4a15da7bac97a03bd35d21b648ec492152708e795ff9:4687c2bfe9ea1b7dfded85de3e737a59de464b987ba43e9a2dd41be5f680d517",
"signature": "95afa6cd5ccf05d85628821d9cdbeaed4107d78ff4063362f152d936f5c3b9825d5a933aa4dd9589675ac2fcf6a4e2094b793c016c84261fe4f07dd7395bf65e1b",
"signing_algo": "ecdsa"
}