Chatbase · Rate Limits

Chatbase Rate Limits

Chatbase enforces account-level usage governance primarily through monthly message credits tied to the subscription plan (Free 50, Hobby 500, Standard 4,000, Pro 15,000, Enterprise custom). Every AI response consumes credits, and per-response cost depends on the chosen model. In addition, the REST API applies request rate limiting per API key; specific per-endpoint request-per-minute values are not published and are not reconciled in this artifact. Training-data size and number of agents are also capped per plan.

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

It captures 4 rate-limit definitions, measuring credits, requests, agents, and bytes.

The profile also includes 3 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, Chatbot, AI Agent, Customer Support, and Conversational AI.

4 Limits Throttle: 429
AIChatbotAI AgentCustomer SupportConversational AIRate LimitingQuotasThrottling

Limits

Monthly Message Credits account
credits
plan-based (Free 50 / Hobby 500 / Standard 4,000 / Pro 15,000 / Enterprise custom)
Each AI response consumes credits; per-response cost depends on the model.
API Requests Per Minute api_key
requests
see provider documentation
REST API requests are rate limited per API key; exact RPM not published.
AI Agents account
agents
plan-based (Free 1; more on paid plans; extra agents available as add-on)
Number of agents is capped per plan.
Training Data Size account
bytes
plan-based (Free 400 KB / Hobby 10 MB / Standard 20 MB / Pro 40 MB)
Total size of training sources per account is capped per plan.

Policies

Credit-Based Metering
Usage is governed by monthly message credits that reset each billing cycle; auto-recharge add-on credits can extend capacity.
Tiered Limits
Credit allotments, agent counts, training size, and feature access (including API access) increase with the subscription tier.
Backoff Strategy
Clients should implement exponential backoff with jitter on HTTP 429 responses and honor any Retry-After header.

Sources