Documentation

ModelRiver Documentation

A comprehensive guide to building AI-native infrastructure with ModelRiver. Explore all platform features, SDKs, and integration patterns.

AI Agent

$ Help me get set up with ModelRiver.

First, inspect this project to understand its stack, structure, and conventions.

Then:
1. Determine the appropriate ModelRiver integration for this project.
2. Install the required ModelRiver package or SDK.
3. Configure the ModelRiver client using environment variables.
4. Create a minimal working request that calls a ModelRiver workflow.
5. Explain any environment variables I need to set (API key, workflow name, etc.).
6. Follow the project's existing architecture and conventions.
7. Do not modify production configuration without asking me first.

Get started

Getting started

Step-by-step guidance to set up and connect your first project in minutes.

Chatbot tutorial

★ Recommended

Build a production-ready AI chatbot with real-time streaming, webhooks, and structured outputs.

Quick answers to commonly asked questions about platform features.

Ready-made ModelRiver workflows for common business tasks, with step-by-step integration guides.

Refund & Order Support Support Ticket Triage Lead Qualification & Follow-up Product Review Insights Content Moderation Classifier Billing & Invoice Assistant Feedback & NPS Response Job Application Screening Article → Social Content FAQ & Knowledge Assistant Booking & Appointment Intake Order Status & Tracking Assistant

Platform

Visual node-based orchestration for complex, multi-step AI pipelines.

Build a workflow Import & export Releases Customer data Test mode

Send requests to the unified ModelRiver endpoint, use OpenAI-compatible SDKs, handle streaming, and more.

Endpoints OpenAI compatibility Streaming Function calling Request types Response formats Error handling Authentication Migration

Backend pipeline

Build backend pipeline architectures with async endpoints, webhook callbacks, and real-time delivery to clients.

Multi-step Pipelines Backend Frameworks Serverless Databases

Manage your projects, monitor usage, and configure settings.

Manage authentication credentials for programmatic access.

Structured outputs

Define and enforce specific JSON schemas for AI responses.

Reduce latency and costs by caching frequent AI responses.

Real-time event subscriptions to trigger external automation.

Standard webhooks Backend pipeline Signature verification Delivery & retries

Monitor, debug, and analyze every AI request with comprehensive logging, timelines, and webhook tracking.

Debugging Spending limits Cost analytics Performance Provider reliability Billing Compliance Testing Timeline Use Cases Best Practices

Framework-specific libraries for React, Python, Node.js, and more.

React Vue Angular Svelte Vanilla JS

Terminal-based interface for managing resources and automated deployment.

Listen Forward Trigger WebSocket

Enterprise-grade RBAC, data encryption, and transparent audit logging.

Roles & project protection Provider credentials Data retention Input guardrails Compliance

Troubleshooting

Diagnostics and solutions for common challenges.

Quick fixes Debugging tips Contact support

Connect ModelRiver to LLM frameworks, agent systems, backend stacks, knowledge and memory, and automation tools.

LLM Frameworks Agent Frameworks Backend Frameworks Knowledge & Memory Observability Tools Automation

Solutions

High availability

Build production-grade AI applications with automatic model failover and redundancy.

Real-time streaming

Everything you need to know about implementing real-time AI streaming using WebSockets.

Type-safe AI outputs

Stop parsing text and start using JSON with validated Structured Outputs.

Resources

Terms of service