GPT-4o Mini Realtime by OpenAI is a lightweight speech-to-speech model for low-latency voice conversations, with tool use and voice activity detection.
Available on
Pricing from$0.60/ 1M input$2.40/ 1M output
Privacy
- ZDR
- Training
- No
- Region
- US
Run Continue on GPT-4o Mini Realtime
Continue is an open-source AI code assistant that lives inside VS Code and JetBrains, giving you chat, inline edits, autocomplete and custom assistants against whichever models you configure. Add an Opper entry to ~/.continue/config.yaml with the openai provider and our base URL, and every role you assign it runs on any of 700+ models, with a choice of EU or US inference on one key.
Run
Continueonin
ContinueoninConnect Continue to GPT-4o Mini Realtime
Set up with agents
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Where you can run it
GPT-4o Mini Realtime runs on the routes below. Route only to EU providers when your data has to stay in Europe.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| OpenAI | US | No | $0.60 | $2.40 |
The model
More apps on Opper
Cursor
Point Cursor's OpenAI base URL at Opper to run it on any of 700+ models.
Editors
OpenAI-compatible
Cline
Cline's OpenAI-Compatible provider points straight at Opper's gateway.
Editors
OpenAI-compatible
Kilo Code
Kilo Code's OpenAI-Compatible provider connects to Opper's gateway in two fields.
Editors
OpenAI-compatible