The Orchestrator › Models › ElevenLabs
ElevenLabs: Eleven Realtime v1 Mini
A speech-to-speech voice agent optimized for fast, natural conversation, with speech recognition, turn-taking, interruption handling, and voice generation tuned as one system. Supports more than 90 languages through an OpenAI-compatible Realtime WebSocket API. Billed for connected session duration plus input and output tokens.
Specifications
| Provider | ElevenLabs |
| Model ID | elevenlabs/eleven-realtime-v1-mini |
| Context window | — |
| Modalities | text + audio → text + audio |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2026-10-27 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | elevenlabs/eleven-realtime-v1-mini | $0.2 | $6.00 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.2 | $6.00 | — |
Capabilities
Audio input
Supported parameters
max_tokens, temperature, stop