RS
Ringside
GuideDocsTutorialsRAGBrainsUse casesExamplesMigrationsPricingSign inSign up
Documentation homeSwagger UI
Get started
  • What is Ringside
  • Architecture
  • Key concepts
  • Quickstart
  • Authentication
  • SDKs and tools
Concepts
  • The customer and spend model
  • Model references and resolution
  • Metering and billing
  • Rate limiting and quotas
  • Idempotency and reliability
  • Prompt caching
  • Retrieval-augmented generation
  • GraphRAG
  • Brains: managed memory
  • Brains and RAG
  • Brain Packs and mounts
  • Sealed RAG and encryption
  • Webhooks and events
  • Batch processing
  • Assistants, threads and runs
How-to guides
  • Create and manage customers
  • Provision accounts for your customers
  • Meter and bill with Stripe
  • Embed a browser chatbot
  • Build RAG over documents
  • Secure RAG for regulated data
  • Add model fallback
  • Enforce structured output
  • Receive and verify webhooks
  • Migrate from OpenAI
  • Add agent memory with Brains
  • Share knowledge across tenants with Packs
Best practices
  • Security
  • Error handling and resilience
  • Cost control
  • Observability
  • Going to production
Reference
  • Error catalog
  • Limits and quotas
  • Model catalog
  • Brains API
  • Brain Packs API
  • Accounts API
  • Regions and data residency
  • Glossary
  • Changelog and versioning
API reference
  • Chat Completions
  • Embeddings
  • Moderations
  • Rerank
  • Conversations
  • Assistants
  • Threads
  • Runs
  • Webhooks
  • Customers
  • Files
  • Batches
  • Client Tokens
  • Vector Stores
Prefer Swagger UI? Click hereThe same API in the classic OpenAPI explorer.
HomeGet startedConceptsHow-to guidesBest practicesReference
// Concepts

Concepts

The ideas behind the API. Read these to build a correct mental model before wiring code.

The customer and spend model

Budgets, prepaid wallets, markup and margin.

Model references and resolution

fc:, match:, slot:, dyn: and region routing.

Metering and billing

How cost becomes a charge on your wallet.

Rate limiting and quotas

The four enforcement layers and their headers.

Idempotency and reliability

Safe retries, fallback cascades, delivery guarantees.

Prompt caching

Reuse stable prefixes and cut input cost.

Retrieval-augmented generation

Vector stores, embeddings and file_search.

GraphRAG

Knowledge-graph retrieval over your documents.

Brains: managed memory

Long-term agent memory that learns, ranks and forgets on a curve.

Brains and RAG

One searchable corpus, migrating an existing store, read-only recall.

Brain Packs and mounts

Share one base layer of knowledge under many private, per-tenant brains.

Sealed RAG and encryption

Encryption at rest, BYOK and the threat model.

Webhooks and events

The event taxonomy, signing and delivery.

Batch processing

Asynchronous bulk jobs at half price.

Assistants, threads and runs

The stateful agent execution model.

Ringside
  • Docs
  • Quickstart
  • Pricing
  • Migrations
Resources
  • Examples
  • Use cases
  • Tutorials
  • Status (TODO)
  • Changelog (TODO)
Other products
  • Fight Club
  • Knockout
Legal
  • Terms (TODO)
  • Privacy (TODO)
Ringside · Fight Club Platform