eleven-multilingual-v2

eleven-multilingual-v2 is a advanced-tier language model from ElevenLabs. eleven-multilingual-v2 is a proprietary model available exclusively through ElevenLabs's API. The ElevenLabs TTS family is ElevenLabs's model series for this capability tier.

eleven-multilingual-v2 is priced at $0.3 per 1K chars. This is a speech-to-text model billed per 1K chars rather than per token — token input/output pricing does not apply.

Its 0-token context window is standard for this tier — adequate for most chat and completion tasks, but may require chunking for long-document workloads. Median latency (P50 time-to-first-token) is approximately 800ms — better suited to batch or async workloads where latency is less critical.

eleven-multilingual-v2 is best suited to tts, voice, multilingual. Supported capabilities include streaming token output for real-time UIs. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how eleven-multilingual-v2 compares to similar models across these dimensions.

eleven-multilingual-v2 sits in the advanced tier — strong general-purpose models balancing capability and cost, suitable for most production applications. Unlike open-weights alternatives, eleven-multilingual-v2 is only available via ElevenLabs's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing eleven-multilingual-v2 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (0/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.