Simple, transparent pricing

Start free as a solo maker. Grow without friction.
Pay only for usage — no surprises, no lock-in. Cancel anytime.

Start here
Free

For indie hackers & solo makers

$0 /month forever
No overage requests

Building alone? Validate ideas, ship MVPs, or add AI to your side projects. Everything you need to go live, free forever.

Plan Features
  • 25,000 requests/month
  • Rate limit: 40 requests/min
  • 1 team member
  • All core features
  • Community support

No credit card required. Just sign up and start making your AI reliable today.

Starter

For creators adding their first collaborators

$9 /month
Overage: $0.004 / request

Ready to collaborate? Bring on your first co-founder or helper. Scale with multi-user access and higher request limits.

Everything in Free, plus
  • 75,000 requests/month
  • Rate limit: 90 requests/min
  • Up to 5 team members
  • Organization management
  • Email support

Great for indie teams or bootstrapped startups moving from solo to small group.

Recommended
Core

For teams shipping production AI

$29 /month
Overage: $0.0025 / request

The sweet spot for production teams. Scale without bottlenecks with unlimited members, priority support, and serious reliability.

Everything in Starter, plus
  • 250,000 requests/month
  • Rate limit: 170 requests/min
  • Unlimited team members
  • Priority email support
  • Team collaboration without limits

The go-to plan for founders turning side projects into real businesses.

Growth

For scaling teams that demand premium reliability

$99 /month
Overage: $0.0018 / request

For high-traffic, mission-critical AI. Get premium reliability with personalized onboarding and dedicated help to optimize your setup.

Everything in Core, plus
  • 750,000 requests/month
  • Rate limit: 200 requests/min
  • Personalized onboarding
  • Priority human support

Built for high-growth startups and production apps where uptime = revenue.

Enterprise

For massive volume & custom needs

Custom
Custom overage pricing

Large scale needs? Dedicated SLAs, custom routing, and advanced security. Tailored solutions built for your organization.

Plan Features
  • Custom volume limits & SLAs
  • Dedicated support & integrations
  • Advanced security & compliance
  • Custom deployment options
99.9999% Uptime Verified

Compare Plans

Find the right features for your scale.

Key FeaturesFreeStarterCoreGrowthScaleScale PlusEnterprise
Subscription Price$0/mo$9/mo$29/mo$99/mo$399/mo$699/moCustom
Requests / month25,00075,000250,000750,0003,000,0008,000,000Custom
Rate Limit (req/min)40901702005001,000Custom
Team Members15UnlimitedUnlimitedUnlimitedUnlimitedUnlimited
All Core Features
Priority Support
Overage Fee (per req)None$0.004$0.0025$0.0018$0.0012$0.0010Custom

All plans include core features: unified API, real-time streaming, observability, playground, SDKs, and automatic failovers.

Frequently asked questions

Every API call routed through ModelRiver, including retries and real-time streams. We provide transparent billing with no hidden fees — you only pay for what your application actually uses.

Yes, you can upgrade or downgrade your plan at any time with no lock-in. Upgrades take effect immediately, while downgrades take effect at the start of your next billing cycle. We'll automatically prorate any mid-cycle upgrades so you only pay for what you use.

Pay-as-you-go requests are billed at the per-request rate shown for your plan. You'll never be cut off mid-month - we'll automatically handle the pay-as-you-go usage and bill you at the end of your billing cycle. You can set up usage alerts in your console.

We support all major AI providers including OpenAI (GPT-5.1, o3, GPT-4.1), Anthropic (Claude Sonnet 4.5, Claude Opus 4.1), Google (Gemini 3, Gemini 2.5 Pro), Cohere (Command A), and more. You can switch between providers seamlessly using our unified API, and we handle automatic failover if a provider is unavailable.

When a request fails due to rate limits, errors, or downtime, ModelRiver automatically retries your request with an alternative provider you've configured. This happens transparently - you don't need to change your code. You can configure failover strategies in your workflow settings.

Every plan includes our full technical infrastructure: automatic failover, smart routing, unified SDKs, request observability, real-time streaming, and access to all supported AI models. Your plan choice simply scales your request capacity and adds higher levels of technical support.

Webhooks allow you to process AI requests asynchronously - we'll notify your endpoint when the response is ready. Websockets provide real-time streaming updates for long-running requests. Both support automatic retry logic and custom data passing for easy request tracking.

You connect using your own API keys for each provider you want to use. ModelRiver acts as a gateway that routes requests through your configured providers. We support all major AI providers (OpenAI, Anthropic, Google, Cohere) and you can also add custom providers with your own endpoints.

Yes! Every account starts with 25,000 free requests per month to test all features. No credit card required to get started. This lets you fully integrate and test ModelRiver in your development environment before committing to a paid plan.

All subscriptions are billed monthly and are non-refundable except as stated in our refund policy. We recommend starting with the free tier to test the service thoroughly before upgrading.