whisper

For whisper, set the max_tokens or max_completion_tokens parameter to control spending per call. Start with a budget aligned to your typical response length and increase only when longer outputs are genuinely needed. Monitor token usage in the API response headers to tune your budget over time.

Whisper supports transcription and translation across 50+ languages. Test with your specific language to confirm accuracy.

Check the current pricing page. Whisper is priced per minute of audio duration, billed to the nearest second.

whisper is listed with catalog status stable. The recorded release date is 2022-09-21. Check the model page for deprecation notices before you build a long-lived integration on it.

Yes. whisper is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to whisper. Keep your current request and response handling.

whisper has no token-based output limit; transcription output is bounded by the audio file size (up to 25 MB).

whisper rate limits vary by your MixRoute subscription plan. Check your plan details in the console for requests per minute (RPM) and tokens per minute (TPM) limits. Run a small load test before production to confirm your effective quota.