Nuclia · Rate Limits

Nuclia Rate Limits

Nuclia enforces plan-based quotas rather than published per-second request limits. The primary metered resource is the Nuclia token (consumed by processing, search, generative answers and stored indexed data), bounded by the monthly token allowance of the subscription plan. Indexed data is capped by the plan's GB / resource quota, and file size by a per-file maximum. Per-endpoint request throttling, when applied, returns HTTP 429. Specific numeric request-rate limits are not publicly reconciled in this artifact.

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

It captures 5 rate-limit definitions, measuring tokens, storage, knowledge_boxes, file_size, and requests.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, RAG, Search, Knowledge Base, and Unstructured Data.

5 Limits Throttle: 429
AIRAGSearchKnowledge BaseUnstructured DataRate LimitingQuotasThrottling

Limits

Monthly Token Allowance account
tokens
see plan (e.g. 10,000/month on Starter and Pro)
Tokens above the plan allowance are billed at $0.008 per token.
Indexed Data Quota account
storage
see plan (5GB/15,000 resources Starter, 25GB/80,000 resources Pro)
Each extra GB of indexed data is priced at 500 tokens/month.
Knowledge Boxes account
knowledge_boxes
see plan (1 Starter, 2 Pro, custom Enterprise)
Pro allows up to 8 Knowledge Boxes at $750/month extra each.
Max File Size request
file_size
see plan (750MB Starter, 1.5GB Pro, unlimited Enterprise)
Per-file ingestion limit; large files should use TUS resumable upload.
Request Throttling account
requests
see provider documentation
Per-endpoint request throttling may apply and returns HTTP 429.

Policies

Quota-Based Limits
Usage is bounded by plan token and storage quotas; overage is billed per token.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources

Work with this as data

Every rate limit here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for rate limits

4 MCP tools reach this
  • find_rate_limitsBrowse and filter every rate limit in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This rate limit 
curl "https://apis.io/api/v1/rate-limits/nuclia-rate-limits"
All rate limits 
curl "https://apis.io/api/v1/rate-limits?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.