API Overview - RedPill AI

Base URL

https://api.redpill.ai/v1

For a base URL that serves confidential models only, on attested providers, use https://tee.redpill.ai/v1. It rejects standard models with 404 and forces attested serving. See the TEE-only endpoint.

Authentication

Send your API key as a bearer token:

Authorization: Bearer YOUR_API_KEY

See Authentication for key management.

Endpoints

Inference

Endpoint	Method	Description
`/v1/chat/completions`	POST	Create a chat completion.
`/v1/responses`	POST	Create a response (Responses API format).
`/v1/messages`	POST	Create a message (Anthropic Messages format).
`/v1/embeddings`	POST	Create text embeddings.
`/v1/models`	GET	List models with providers, context windows, and pricing.

Each model has an is_tee boolean: is_tee: true means it can be served confidentially, on a verified TEE provider. The receipt’s upstream.verified event confirms a specific response was. See Confidential models.

Verification

Endpoint	Method	Description
`/v1/aci/attestation`	GET	Fresh TEE attestation report, bound to a caller-supplied `nonce`.
`/v1/aci/receipts/{id}`	GET	Signed receipt for a response, by receipt id or chat id.
`/v1/aci/sessions/{id}`	GET	Attested-session record referenced by a receipt.
`/v1/aci/sessions`	GET	List a provider’s attested sessions (`?provider=&model=`).

To verify a response: fetch the attestation report with a fresh nonce, read the x-receipt-id header on your response, fetch its signed receipt, then check the receipt signature under the attested keyset and compare the request and response hashes. See Verify a response.

Legacy

Legacy endpoints kept for backward compatibility with earlier API clients. New integrations should use the canonical endpoints above.

Endpoint	Method	Canonical replacement
`/v1/completions`	POST	`/v1/chat/completions`
`/v1/signature/{id}`	GET	`/v1/aci/receipts/{id}`
`/v1/attestation/report`	GET	`/v1/aci/attestation`

Request format

POST requests use JSON:

curl https://api.redpill.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen/qwen3-30b-a3b-instruct-2507",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Response format

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "qwen/qwen3-30b-a3b-instruct-2507",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hello! How can I help you?" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 12, "total_tokens": 21 }
}

Response headers

Inference responses include verification headers:

Header	Description
`x-receipt-id`	Id of the signed receipt for the response.
`x-aci-identity`	The attested workload identity that served the request.
`x-aci-keyset-digest`	Digest of the workload’s published keyset.
`x-aci-version`	ACI version, for example `aci/1`.

To select a model, set the model field in the request body. For end-to-end encryption, send the X-E2EE-* request headers from the E2EE guide.

Errors

Errors return a JSON body with an appropriate HTTP status:

{
  "error": {
    "message": "Invalid API key",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Code	Meaning
200	Success
400	Bad request (invalid parameters)
401	Unauthorized (invalid API key)
403	Forbidden (insufficient credits)
404	Endpoint or model not found
429	Rate limit exceeded
500	Server error
503	Service unavailable

See Error handling. Rate limits depend on your account tier; check the dashboard.

Using existing client libraries

The API follows the OpenAI request and response format, so OpenAI client libraries work by pointing the base URL at the gateway and using your API key:

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.redpill.ai/v1")
resp = client.chat.completions.create(
    model="qwen/qwen3-30b-a3b-instruct-2507",
    messages=[{"role": "user", "content": "Hello"}],
)

See Integrations for SDKs and tools.

​Base URL

​Authentication

​Endpoints

​Inference

​Verification

​Legacy

​Request format

​Response format

​Response headers

​Errors

​Using existing client libraries