ToAPIs · Rate Limits
Toapis Rate Limits
Toapis Rate Limits is the machine-readable rate-limit profile for ToAPIs on the APIs.io network, in the API Commons Rate Limits shape.
It captures 6 rate-limit definitions.
Limit state is signalled in the Retry-After, X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset response headers.
Tagged areas include AI API, LLM/AI gateway, model aggregation, OpenAI-Compatible, and Model Routing.
6 Limits
Retry-AfterX-RateLimit-LimitX-RateLimit-RemainingX-RateLimit-Reset
Transcribed from the provider's documentation on 2026-09-07 — docs.toapis.com/docs/cn/api-reference/rate-limits/async-t....
View Source
AI APILLM/AI gatewaymodel aggregationOpenAI-CompatibleModel Routingprovider failoverText GenerationImage GenerationVideo GenerationDeveloper ToolsA2A
Limits
per-user async task submission (group default)
300 RPM
per-user async task submission (group vip)
1000 RPM
per-user async task submission (group svip)
2000 RPM
per-user async task status query (group default)
3000 RPM
per-user async task status query (group vip)
10000 RPM
per-user async task status query (group svip)
30000 RPM
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.