On the Artificial Analysis Speech to Speech leaderboard, Eleven Realtime v1 Max sits near the top left corner, combining high accuracy with low latency. | Image: Elevenlabs
Source: the-decoder.com
What the models are for
Both models are available on ElevenAgents and through an OpenAI-compatible real-time API. Pricing combines minutes and tokens, with v1 Max costing more than v1 Mini. ElevenLabs publishes detailed rates on its pricing page.
The turn-taking feature is the more revealing part of the announcement. In voice interfaces, a system that mistakes an acknowledgment for a finished turn can interrupt; one that misses the end of a turn can leave an awkward pause. Mini is positioned as the lower-cost option, but the source does not say how often it gets that distinction right.
The unanswered question
I think the central comparison is not simply Mini against Max, but how much better Max performs on difficult conversations for its higher price. The announcement gives no benchmark, latency figures, or accuracy results, so buyers have little basis here for judging that trade-off. Until those details are available, the product split is clear, but the performance gap is not.
Source: the-decoder.com
Daily AI news
Every day we pick what actually matters in AI and explain it plainly — no hype, no filler. Subscribe if you want to follow where the industry is going.
Only what matters — every day
Follow on X