Documentation Index
Fetch the complete documentation index at: https://docs.parallel.ai/llms.txt
Use this file to discover all available pages before exploring further.
For AI agents: a documentation index is available at https://docs.parallel.ai/llms.txt. The full text of all docs is at https://docs.parallel.ai/llms-full.txt. You may also fetch any page as Markdown by appending
The following table shows the default rate limits for each Parallel API product:
.md to its URL or sending Accept: text/markdown.| Product | Default Quota | What Counts as a Request |
|---|---|---|
| Search | 600 per min | Each POST to /v1/search |
| Extract | 600 per min | Each POST to /v1/extract |
| Tasks/TaskGroups | 2,000 per min | Each POST to /v1/tasks/runs or /v1beta/tasks/groups/{taskgroup_id}/runs (creating tasks) |
| Chat | 300 per min | Each POST to /v1beta/chat/completions |
| FindAll | 300 per hour | Each POST to /v1beta/findall/runs (creating a generator) |
| Monitor | 300 per min | Each POST to /v1alpha/monitors |
Rate limits apply to POST requests that create new resources. GET requests
(retrieving results, checking status) do not count against these limits. For
example, polling a task’s status with
GET /v1/tasks/runs/{run_id} does not
consume your Tasks rate limit—only creating new tasks does.