specification: API Commons Rate Limits
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/RateLimits
provider: Langbase
providerId: langbase
created: '2026-07-01'
modified: '2026-07-01'
reconciled: false
tags:
- AI
- Agents
- RAG
- LLM
- Serverless
- Rate Limiting
- Quotas
- Throttling
description: >-
  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.
notes: >-
  Verify current per-tier and per-endpoint limits in the Langbase docs
  (Limits section) on reconciliation; limits change as accounts move between
  Free, Pro, and Enterprise tiers.
sources:
- https://langbase.com/docs/api-reference/limits
- https://langbase.com/pricing
responseCodes:
  throttled: 429
limits:
- name: Requests Per Minute (RPM)
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Per-API-key RPM, varies by tier and endpoint.
- name: Agent / Pipe Runs
  scope: account
  metric: runs
  limit: see provider documentation
  notes: Run throughput scales with Free / Pro / Enterprise tier.
- name: Memory Retrieval
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Retrieval (RAG) request rate; topK max 100 per request.
- name: Document Upload / Parser
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Parser accepts documents up to 10 MB; upload rate varies by tier.
- name: Embed
  scope: account
  metric: chunks
  limit: 100 chunks per request
  notes: Maximum 100 chunks per embed request, each up to 8192 characters.
- name: Tools (Web Search / Crawl)
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Tool call rate varies by tier.
policies:
- name: Tiered Limits
  description: Limits raise as accounts move from Free to Pro to Enterprise agreements.
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com