Vidu · Rate Limits

Vidu Ai Rate Limits

Vidu's API is an asynchronous, queue-based generation service. Throughput is governed less by classic requests-per-minute limits and more by the number of concurrent generation tasks an account may have in flight and by the account's prepaid credit balance, which caps total generation. Specific concurrency caps and any per-minute submission limits are set per account and are not published as fixed public numbers; they should be confirmed with Vidu on reconciliation. Off-peak mode intentionally trades a longer queue window for lower cost.

Vidu Ai Rate Limits is the machine-readable rate-limit profile for Vidu on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 3 rate-limit definitions, measuring tasks, credits, and requests.

The profile also includes 3 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include Video Generation, AI Video, Rate Limiting, Concurrency, and Quotas.

3 Limits Throttle: 429
Video GenerationAI VideoRate LimitingConcurrencyQuotas

Limits

Concurrent Generation Tasks account
tasks
see provider documentation
Number of in-flight generation tasks allowed per account; varies by account.
Credit Balance account
credits
prepaid balance
Total generation is bounded by the account's purchased credit balance.
Submission Rate account
requests
see provider documentation
Any per-minute task-submission ceiling is account-specific and not published as a fixed number.

Policies

Asynchronous Queue
Tasks are queued and processed asynchronously; poll /tasks/{id}/creations or use a callback_url rather than blocking.
Off-Peak Window
Off-peak mode accepts a longer (up to 48h) processing window in exchange for reduced credit cost.
Backoff Strategy
Clients should poll with a sensible interval and exponential backoff, and handle 429 with retry.

Sources