Langbase · Rate Limits

Langbase Rate Limits

Langbase enforces per-account rate limits that scale with subscription tier (Free, Pro, Enterprise). Limits are applied per API key across the platform primitives - Pipe / Agent runs, Memory retrieval and document uploads, Parser, Chunker, Embed, and Tools - and are commonly expressed as requests per minute. Generative endpoints stream via Server-Sent Events; exceeding limits returns HTTP 429. Specific per-endpoint numeric limits are not reconciled in this artifact.

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

It captures 6 rate-limit definitions, measuring requests, runs, and chunks.

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

Tagged areas include AI, Agents, RAG, LLM, and Serverless.

6 Limits Throttle: 429
AIAgentsRAGLLMServerlessRate LimitingQuotasThrottling

Limits

Requests Per Minute (RPM) account
requests
see provider documentation
Per-API-key RPM, varies by tier and endpoint.
Agent / Pipe Runs account
runs
see provider documentation
Run throughput scales with Free / Pro / Enterprise tier.
Memory Retrieval account
requests
see provider documentation
Retrieval (RAG) request rate; topK max 100 per request.
Document Upload / Parser account
requests
see provider documentation
Parser accepts documents up to 10 MB; upload rate varies by tier.
Embed account
chunks
100 chunks per request
Maximum 100 chunks per embed request, each up to 8192 characters.
Tools (Web Search / Crawl) account
requests
see provider documentation
Tool call rate varies by tier.

Policies

Tiered Limits
Limits raise as accounts move from Free to Pro to Enterprise agreements.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources