GPT-Live vs Vogent API

GPT-Live

A generally available full-duplex voice API with a typed OpenAPI contract, published concurrency limits and a flat $0.05 a minute for the voice session. Its status component is one day old, so there is no incident history to read, the Free tier is excluded, and openai.com refused our reader, so the terms and privacy policy were not read.

Vogent API

IVR detection and navigation models for outbound calls. No public changelog and no release found since January 2026.

GPT-Live

1. Create sessions on a server with the project API key. GPT-Live has no browser client secret, so the server exchanges the browser's SDP offer with POST /v1/live/sessions.
2. Choose delegation.type at creation. Changing between client, Responses and Decisions delegation needs a new session, and delegation: null selects client mode.
3. After session.started, listen for error with code responses_validation_failed. Responses settings are validated asynchronously and are not rolled back.
4. Do not retry an outbound SIP POST /v1/live/sessions after a timeout. Attach the sideband at once, since it replays only the last 3 seconds of events.
5. Keep the transport open until session.closed to read the final usage.seconds. A WebRTC session bills 15 seconds at creation, credited once it runs.

Vogent API

1. Send an idempotencyKey on POST /dials, a reused key returns 409
2. Create a call with callAgentId, plus toNumber and fromNumberId for phone calls
3. Tell the model when to emit <|transfer|>, since transfers fire on that tag
4. Verify webhooks with the HMAC in X-Elto-Signature
5. Expect new dials to fail at the workspace's concurrent dial limit until calls end