Continue · Rate Limits

Continue Dev Rate Limits

Continue Hub IDE API (api.continue.dev) returns HTTP 429 on quota exhaustion. The free trial enforces per-user chat and autocomplete counts via /ide/free-trial-status. Inference rate limits ultimately depend on the LLM provider the user routes through — Anthropic, OpenAI, Mistral, OpenRouter, Ollama, or the Continue-managed proxy.

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

It captures 4 rate-limit definitions, measuring requests, chat-messages, autocomplete-requests, and requests / tokens.

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

Tagged areas include AI, Developer Tools, Rate Limits, Quotas, and Throttling.

4 Limits Throttle: 429
AIDeveloper ToolsRate LimitsQuotasThrottling

Limits

Hub IDE API per-user
requests
provider-enforced
api.continue.dev /ide/* endpoints return HTTP 429 when per-user quotas are exceeded. /ide/list-assistant-full-slugs in particular is currently flagged as always returning 429 in the spec.
Free Trial Chat per-user
chat-messages
chatLimit returned by /ide/free-trial-status
Per-user cap on chat messages allowed in Continue's managed free trial.
Free Trial Autocomplete per-user
autocomplete-requests
autocompleteLimit returned by /ide/free-trial-status
Per-user cap on autocomplete requests allowed in Continue's managed free trial.
BYO LLM Provider per-provider
requests / tokens
pass-through
When users bring their own LLM provider, rate limits and concurrency are governed by that provider, not Continue.

Policies

Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header on 429 responses from api.continue.dev.
Free-Trial Polling
IDE extensions and the CLI should poll /ide/free-trial-status to surface remaining chat and autocomplete quota to the user before the cap is hit.

Sources