Octen · Rate Limits

Octen Ai Rate Limits

Octen Ai Rate Limits is the rate-limit profile for Octen on the APIs.io network — every limit transcribed verbatim from the provider’s own documentation on 2026-10-07.

It captures 17 rate-limit definitions, including Search QPS — Free — Free 10 ; Search QPS — Base — Base 20 ; Search QPS — Builder — Builder 50 .

An exhausted limit returns HTTP 429.

Tagged areas include Search, Web Search, AI, LLM, and Embeddings.

17 Limits Exhausted: HTTP 429
Transcribed from the provider's documentation on 2026-10-07 — docs.octen.ai/resources/rate-limits.md.
View Source
SearchWeb SearchAILLMEmbeddingsContent ExtractionModel GatewayMCPAgentsDeep ResearchCompany

Limits

Search QPS — Free per-accountFree
| Free | 10 |
/broad-search, /search, /news-search, /business-search
· per second
10
Search QPS — Base per-accountBase
| Base | 20 |
/broad-search, /search, /news-search, /business-search
· per second
20
Search QPS — Builder per-accountBuilder
| Builder | 50 |
/broad-search, /search, /news-search, /business-search
· per second
50
Search QPS — Pro per-accountPro
| Pro | 200 |
/broad-search, /search, /news-search, /business-search
· per second
200
Search QPS — Max per-accountMax
| Max | 500 |
/broad-search, /search, /news-search, /business-search
· per second
500
Image/Video/Answer QPS per-account
Image Search, Video Search, and Answer share a single QPS limit equal to your subscription tier's QPS, in a separate bucket from the search APIs above.
/image-search, /video-search, /answer
· per second
Embedding TPM — Free / Base per-accountFree / Base
| Free / Base | 1,000,000 | 200,000 |
/embedding
· per minute
1000000
VL Embedding 200,000 TPM on the same row
Embedding TPM — Builder per-accountBuilder
| Builder | 2,500,000 | 500,000 |
/embedding
· per minute
2500000
VL Embedding 500,000 TPM
Embedding TPM — Pro per-accountPro
| Pro | 10,000,000 | 2,000,000 |
/embedding
· per minute
10000000
VL Embedding 2,000,000 TPM
Embedding TPM — Max per-accountMax
| Max | 25,000,000 | 5,000,000 |
/embedding
· per minute
25000000
VL Embedding 5,000,000 TPM
Extract URLs/min — standard per-account
| `standard` | 2,000 |
/extract
· per minute
2000
Extract URLs/min — auto per-account
| `auto` | 500 |
/extract
· per minute
500
Extract URLs/min — advanced per-account
| `advanced` | 200 |
/extract
· per minute
200
Model Gateway RPM per-model
| RPM | 300 |
/v1/chat/completions
· per minute
300
Model Gateway TPM per-model
| TPM | 2,000,000 |
/v1/chat/completions
· per minute
2000000
Deep Research concurrency per-account
Only a single concurrent request is supported.
/v1/research
1
Per-key cap per-key
When creating an API key, you may configure an additional rate limit for that key.

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/octen-ai-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.