NEW AI backend pipelines

Build AI-powered tools for your business. You stay in control of your data.

Build customer support, CRM assistants, and document processing. Connect once to every major AI model while your backend controls what AI sees.

Start free See how it works

Start free · No credit card required

13 AI providers 98 models 12 ready-made templates Switch providers anytime
console.northstar.ai/projects/…/workflows
Backend code Frontend code View integration examples for your workflows

Workflows

Configure AI workflows with provider, model, and response options

Create workflow
mr_chatbot_workflow Live

Customer support chatbot with structured replies and failover.

Test Copy
Primary model
gpt-4o-mini
Budget No budget
Backup models if primary fails
Backup 1
claude-haiku-4-5-20251001
Budget No budget
15m window chatbot_structure
get_book_suggestion Live

Translate this Sanskrit medical text into Sumerian cuneiform notation. Preserve the original meaning with extreme precision.

Test Copy
Primary model
gpt-3.5-turbo
Budget $1.00/day
0% of budget used
$0.00 / $1.00 per day · $1.00 remaining
Backup models if primary fails
Backup 1
claude-3-haiku-20240307
Budget $1.00/day
0% of budget used
$0.00 / $1.00 per day · $1.00 remaining
15m window chatbot_structure Backend pipeline · 3 steps
summarize_ticket Live

Summarize support tickets into actionable next steps.

Test Copy
Primary model
gemini-2.5-flash
Budget No budget
Backup models if primary fails
Backup 1
gpt-4o-mini
Budget No budget
ticket_summary
content_moderator Live

Classify user content and route low-confidence cases.

Test Copy
Primary model
grok-4.3
Budget $1.00/day
12% of budget used
$0.12 / $1.00 per day · $0.88 remaining
Backup models if primary fails
Backup 1
claude-haiku-4-5
Budget No budget
15m window moderation_schema

Provider credentials

Add your API keys for OpenAI, Anthropic, and other providers

+ Custom provider
Anthropic
Claude 4.5 Sonnet, Claude 4.5 Opus, Haiku 4.5
Connected
Update
OpenAI
GPT-5, GPT-5 pro, GPT-5 mini
Connected
Update
Cohere
Command-A-03-2025, Command R, Embed
Not configured
Add API Key
DeepSeek
DeepSeek-V3 (Chat) and DeepSeek-R1 (Reasoner)
Not configured
Add API Key
Google
Gemini 2.5 Flash, Gemini 2.5 Pro, 2.5 Flash-Lite
Not configured
Add API Key
Groq
Ultra-fast LPU inference - Llama 3.1/3.3, GPT OSS
Not configured
Add API Key
Mistral AI
Mistral Large 24.11, Small 3.2, Codestral
Not configured
Add API Key
Qwen
Qwen-Max, Qwen-Plus, Qwen-Turbo, Qwen-Long (Alibaba Cloud)
Not configured
Add API Key
xAI
Grok 4, Grok-4-fast-reasoning
Not configured
Add API Key

Test workflow

Run a workflow with sample JSON input. Test requests do not appear in the request log.

Start new test Send request
Async mode (background job)

Process AI requests in the background with real-time updates via WebSocket. Works even if you refresh the page!

Workflow
my_workflow
LIVE Production settings
Choose how this playground request runs before you send it.
Edit workflow
Run with model

Pin one model for this test, or use Auto to follow your configured order.

Auto Follow workflow order (primary, then backups)
claude-haiku-4-5-20251001 Primary model
gpt-5.4-mini Backup 1
grok-4.20-0309-non-reasoning Backup 2
Pipeline steps

Backend pipeline flow for this test — pin a model on linked workflows when needed.

1
movie_suggestions BACKEND WEBHOOK
Backend webhook + auto callback
2
movie_ratings AI WORKFLOW
json_extractor · gpt-5.4-mini
Run linked workflow with model
Auto Follow workflow order (primary, then backups)
gpt-5.4-mini Primary model
gemini-2.5-flash-lite Backup 1
3
final_movies FINAL CALLBACK
Backend callback, then deliver
Response format
book_notes
CACHE
15m cache window
Cache skipped — 15m cache window disabled in playground for fresh responses
Backend pipeline test — Backend steps use auto callbacks; linked workflow models follow your selections above
JSON payload
1{
2 "messages": [
3 {"role": "user", "content": "Hello from Northstar AI"}
4 ]
5}
Response
Raw JSON Preview
1{
2 "data": {
3 "author": "Northstar AI",
4 "title": "The Midnight Library",
5 "notes": [
6 "Philosophical fiction exploring life's infinite possibilities",
7 "Strong character development and emotional resonance"
8 ],
9 "schema": {
10 "type": "json_schema",
11 "strict": true,
12 "properties": { "type": "object" }
13 },
14 "structure_id": "cddd219a-6e55-42b3-8f98-d343fe5f7f72"
15 },
16 "status": "success",
17 "channel_id": "628f6a0d-ec75-4a8c-be7c-4208cafe6b72",
18 "customer_data": {}
19}
Back to request logs

Request details

OpenAI gpt-5-mini 140d ago
ticket_creat... Success
Input tokens
468
Output tokens
368
Duration
8.4s
Price
$0.000853
Cache reuse
0
No downstream cache hits
Response source
Provider
Cached from request ID
N/A
Estimated price without cache
N/A

Timeline logs

Failed
anthropic/claude-haiku-4-5
661ms • 141d ago
Success
openai/gpt-5-mini
7.7s • 141d ago
Error
Trigger webhook
141d ago • 3ms • Callback: success
Success
Backend callback
141d ago
Success
WebSocket output
141d ago
Webhook Deliveries
Failed WebSocket 3ms Attempt 1
URL: cli://localhost CLI
No CLI client connected
Sent 140d ago Details

Members

15 members
+ Invite member
Michael Carter Owner
[email protected]
Joined Nov 14, 2025
Emily Johnson Member
[email protected]
Joined Nov 18, 2025
James Wilson Member
[email protected]
Joined Dec 2, 2025
Sarah Martinez Member
[email protected]
Joined Dec 15, 2025
Robert Thompson Member
[email protected]
Joined Jan 8, 2026
Jennifer Lee Member
[email protected]
Joined Jan 22, 2026
David Brown Member
[email protected]
Joined Feb 3, 2026
Amanda Davis Member
[email protected]
Joined Feb 19, 2026
Christopher Miller Member
[email protected]
Joined Mar 1, 2026
Jessica Taylor Member
[email protected]
Joined Mar 14, 2026
Matthew Anderson Member
[email protected]
Joined Apr 2, 2026
Ashley Thomas Member
[email protected]
Joined Apr 18, 2026
Ryan Garcia Member
[email protected]
Joined May 6, 2026
Nicole White Member
[email protected]
Joined May 21, 2026
Brandon Clark Member
[email protected]
Joined Jun 3, 2026

Pending invitations

No invitations awaiting acceptance

No pending invitations

Live demo — watch AI requests flow through providers, failover, budgets, and logs

Build customer support AI, CRM assistants, and more

Start from a proven workflow instead of building everything from scratch.

Customer support AI

Resolve tickets and answer customers with AI that understands your product.

Browse use cases

AI CRM assistant

Qualify leads, update records, and draft follow-ups automatically.

Browse templates

Document processing

Extract, classify, and summarize documents with structured outputs.

View guides

Why teams build with ModelRiver

See how teams use ModelRiver

Test AI before you pay

Test workflows with sample responses before paying AI providers.

Open playground

Test workflow

Sample JSON in, structured response out

Send request
Testing mode — returns sample data, no provider call
Workflow
book_info
{ "messages": [{ "role": "user", "content": "Percy Jackson" }] }
Response
{
  "title": "Percy Jackson & the Olympians",
  "author": "Rick Riordan",
  "genre": "Fantasy"
}

Connect once, use any AI

One integration works with OpenAI, Anthropic, Gemini, and more. Switch providers from the dashboard.

Swap a provider
book_info
Testing Chat
Primary
OpenAI
gpt-5-mini
Backups
Anthropic
claude-haiku-4-5

Structured outputs

JSON schemas for responses

sample 4 properties
book_notes 3 properties

Keep AI costs predictable

Daily budgets. Live usage. No surprise bills.

Set a budget
customer_support_workflow
Live
Primary model $20/day
gpt-5.4-mini
$7 of $20 used$13 left today
Backup model $10/day
claude-haiku-4-5
$2 of $10 used$8 left today

See every step of a request

Follow AI requests through every backend pipeline until the final response.

View request log

Request details

ticket_creat… OpenAI · gpt-5-mini 140d ago
Success
Tokens
836
Duration
8.4s
Price
$0.0009
Timeline
Failed OpenAI gpt-5-mini — rate limit exceeded 0ms
Failover Retrying Anthropic claude-haiku-4-5 1.2s
Success Structured output delivered to webhook 8.4s

One connection. Every AI model. You stay in control of your data.

Your app connects to ModelRiver once. ModelRiver talks to AI providers, retries requests, and runs multi-step workflows. Your business logic stays in your system.

Your backend decides what AI sees.

Learn more about request flow
Your app
POST /v1/chat/completions POST /v1/ai POST /v1/ai/async POST /v1/callback/:channel_id
ModelRiver
Backend pipelines AI orchestration Auto failover Guardrails Spending limits Testing Caching Cost analysis
Your backend & data
Your CRM Your database (Supabase • Neon • Postgres) Your business rules Your API keys & secrets

All major AI providers

You control your data and API keys. ModelRiver handles routing, retries, and provider management.

Example · Refund request

ModelRiver can ask your backend for data, call AI again with that context, then deliver the final answer to your system and the customer.

1. AI reads the request

Customer asks for a refund AI understands the request

2. Your backend checks the order

ModelRiver asks your backend Your backend checks CRM Order details sent back

3. AI writes the reply

AI drafts the reply Your backend gets the answer Customer sees the reply

Why not just hand it to an AI agent?

AI agents often work best when given broad access. ModelRiver lets your backend decide exactly what AI receives instead.

Agents
ModelRiver
Where your data goes
Can require broad access to your systems and data
Your backend decides exactly what information AI receives
Building AI workflows
You orchestrate retries, multiple AI calls, and integrations yourself
Built-in backend pipelines coordinate AI and your code
Switching providers
Usually requires engineering work and redeployment
Switch providers from the dashboard
AI costs
Often send every task to larger AI models
Use the right AI model for each task to help reduce costs
Who pays for AI
You pay AI providers directly
Same. You pay AI providers directly. We charge only for the ModelRiver platform.
See all providers

Start building AI-powered business tools.

Start free