> ## Documentation Index > Fetch the complete documentation index at: https://docs.aircaps.com/llms.txt > Use this file to discover all available pages before exploring further. # Limits > Usage limit, concurrency and rate limits. ## Usage limit Each account includes **5 hours of free usage**, shared by both models. * **A5S Async v1** counts the duration of each completed transcript. Failed jobs are not counted. * **A5S v2 Streaming** counts the audio you stream. * A file longer than your remaining usage fails with `usage_limit_reached` and is not counted. New requests at a used-up limit return `403 usage_limit_reached`. * See what's left in the console or with [`GET /v1/account`](/api-reference/account) (`usage_limit`). ## Defaults | Limit | Default | | - | - | | A5S Async v1 jobs processing at once | 5 (more are queued, first in first out) | | A5S Async v1 jobs waiting in the queue | 2,000 | | Transcript create requests | 600 per minute | | Maximum file duration / size | 10 hours / 5 GB | | Direct upload (`POST /v1/files`) | 1 GB (use an upload URL for larger files) | | Uploaded files kept | 24 hours | | Transcripts kept | 30 days (or until you delete them) | | A5S v2 Streaming sessions at once | 5 | | Streaming session length | 5 minutes | | Active API keys | 10 | Jobs beyond the processing limit wait as `queued`. Beyond the queue or request-rate limit you get `429` with a `Retry-After` header. ## Pricing and higher limits Limits are set per account. For pricing, higher usage limits or concurrency, access to a model, or a dedicated deployment, [talk to sales](https://research.aircaps.com/contact). research.aircaps.com/contact This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.