Can My Agent Uselookup · compare · cite

Aug 28, 2026 · Catalog foundation is up

Product feature · operations

Rate limits and quotasMeasured product property

Record documented product usage limits and reset periods.

Terminology basis: Measured product property. Cursor — Usage and limits

Rate limits and quotas: 5 supported, 0 partial, 0 unsupported, 26 unreviewed across 31 cataloged products.

Markdown · JSON

Explore this familyMore in Pricing, usage, and limits3 capabilities

Current evidence by product

Can my agent use Rate limits and quotas?

Read across for the answer. 5 of 31 current product columns have reviewed evidence; unreviewed does not mean unsupported.

Known issues (0)Report an issue
  • Supported5
  • Partial0
  • Unsupported0
  • Unknown26
  • Not applicable0

Web

9 products

Desktop

13 products

CLI

9 products

Unknown means no public evidence has been reviewed for that product and capability. It does not mean unsupported.

How statuses are assigned

Definition and scope

What this capability means

This row records rate and quota boundaries around the harness: requests, tokens, agent runs, active sandboxes, sub-agent concurrency, tool calls, connectors, uploads, media minutes, storage, and background compute. Each number needs a plan, model, user or organization scope, and reset window.

Evidence should state whether pools are shared, whether limits are fixed or dynamic, what meters or headers reveal, retry and backoff guidance, priority tiers, overage behavior, and whether work queues, degrades, or fails at the boundary. “Reasonable use” without an inspectable limit is partial disclosure.

Traceable compatibility

Assertion ledger

Documentation evidence only. No runtime conformance test is implied.

ChatGPTweb · current
Supported
Target
2026-08-28 ChatGPT Work usage-limit documentation observation · hosted-observation
Environment
hosted-default
Observed
2026-08-28
  • planlocal messages and cloud chats share a five-hour allowance; additional weekly limits may apply, and Enterprise or Edu flexible pricing can scale through credits
  • runtimedocumented plan and model tables are estimated ranges because task size, context, reasoning, tools, retrieval, caching, and local versus cloud execution change consumption
  • policyan active turn may finish at the boundary subject to fair use; eligible plans can buy credits, switch models, or use separately billed API-key sessions
Evidence
ChatGPTdesktop · current
Supported
Target
2026-08-28 ChatGPT desktop usage-limit documentation observation · hosted-observation
Environment
local-default
Observed
2026-08-28
  • planlocal desktop tasks share the five-hour ChatGPT Work and Codex allowance with cloud chats; additional weekly limits may apply
  • runtimeChatGPT Voice on desktop has a separate plan-dependent rolling five-hour allowance, while tasks started through Voice still consume the shared Codex task budget
  • policythe published local-message and voice-minute ranges are estimates rather than fixed per-message guarantees
Evidence
Codex CLIcli · current
Supported
Target
2026-08-28 Codex CLI usage-limit documentation observation · hosted-observation
Environment
local-default
Observed
2026-08-28
  • planChatGPT-authenticated local messages share a five-hour allowance with cloud chats and may have additional weekly limits; model-specific estimated ranges are published by plan
  • runtime/status exposes remaining limits during the session; an active turn may finish at the boundary subject to fair use
  • authAPI-key sessions are billed independently at API rates and are not part of the ChatGPT-plan allowance
Evidence
Cursordesktop · current
Supported
Target
2026-08-28 Cursor documentation observation · hosted-observation
Environment
local-default
Observed
2026-08-28
  • planusage is split into two monthly pools; remaining allowance, on-demand charges, and reset date are visible in the Spending dashboard
  • runtimeunused usage does not roll over; at the boundary the editor offers on-demand usage or a plan upgrade
  • policynumeric included allowances and the complete request, token, upload, tool, and agent-concurrency envelope are not established by the reviewed page
Evidence
Copilot CLIcli · current
Supported
Target
2026-08-28 GitHub Copilot CLI documentation observation · hosted-observation
Environment
local-default
Observed
2026-08-28
  • planconcurrent subagents are limited to 2 on Free or Education, 4 on Pro or Pro+, 8 on Max, 16 on Business, and 32 on Enterprise or usage-based billing
  • runtimeconcurrency is counted across the full session tree; new child requests are rejected until an active child completes; maximum documented concurrency is 32
  • policythis cell establishes subagent limits only, not the full request, token, premium-request, tool, or upload quota envelope
Evidence
  1. 1. Evidence checked 2026-08-28: Cursor documents two monthly usage pools, real-time remaining allowance, a billing-cycle reset with no rollover, editor notification at the boundary, and optional on-demand usage. The numeric included allowance varies by plan and is not stated on the reviewed page.
  2. 2. Evidence checked 2026-08-28: GitHub Copilot CLI documents plan-based concurrent-subagent limits of 2, 4, 8, 16, or 32, a global session-tree maximum of 32, and rejection of new child requests until capacity becomes available. These are subagent quotas, not the complete request, token, tool, or premium-request envelope.
  3. 3. Evidence checked 2026-08-28: OpenAI publishes plan- and model-specific estimated local-message ranges per five-hour window for ChatGPT Work and Codex, documents that local and cloud tasks share the window, notes additional weekly limits, and describes credit-based continuation. The ranges vary with task complexity and are not hard per-message guarantees.