Wire-compatible OpenAI Chat Completions proxy

curl --request POST \
  --url https://api.antidote.example.com/api/runtime-security/proxy/openai/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '{}'

{}

Proxy

Wire-compatible OpenAI Chat Completions proxy

Body and response match POST https://api.openai.com/v1/chat/completions verbatim. Antidote scans both directions; the verdict either forwards (allow), mutates content in place (redact), or returns an OpenAI-shaped error (block).

Streaming: pass stream=true to receive Server-Sent Events. The firewall scans the assembled response on a 250 ms / 80-char cadence and emits finish_reason: content_filter mid-stream on a block verdict.

Headers: Authorization is reserved for OpenAI and forwarded upstream untouched. Authenticate to Antidote via X-API-Key.

POST

api

runtime-security

proxy

openai

chat

completions

Wire-compatible OpenAI Chat Completions proxy

curl --request POST \
  --url https://api.antidote.example.com/api/runtime-security/proxy/openai/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '{}'

{}

Authorizations

X-API-Key

string

header

required

Antidote workspace API key (ak_live_…). Use this header for the scan API and the OpenAI proxy routes. The required permission scope is runtime_security.scan for scan endpoints, runtime_security.view for read-only analytics, and runtime_security.manage for configuration changes.

Body

application/json

OpenAI Chat Completions request body. See https://platform.openai.com/docs/api-reference/chat/create for the full schema.

The body is of type object.

Response

On stream=false, an OpenAI Chat Completion response. On stream=true, an SSE stream (text/event-stream).

The response is of type object.

Scan an agent tool invocation before executing it Wire-compatible OpenAI legacy Completions proxy