One API.
60-80% savings.
Intelligent routing automatically selects the cheapest and fastest model for every request. Start free, scale as you grow.
Free / Starter
Perfect for indie developers testing the API and small projects.
Get Free API Key- 200,000 tokens/month
- Basic model routing
- Community support
- OpenAI-compatible API
- Up to 5 API keys
- Semantic caching
- Custom guardrails
- Analytics dashboard
- Priority support
Pro
For growing startups and development teams who need more power.
Start Pro Trial- 5 million tokens included
- Semantic caching (30% savings)
- Guardrails & safety filtering
- Advanced analytics dashboard
- Cost optimizer recommendations
- Up to 100 API keys
- Virtual keys with budgets
- Email support
- Custom industry APIs
- Managed agents
- Dedicated account manager
Team / Growth
For small teams and agencies managing multiple projects and clients.
Start Team Plan- 20 million tokens included
- Everything in Pro, plus:
- Unlimited team seats
- Custom guardrails per project
- Budget alerts & controls
- Usage reporting per key
- Up to 500 API keys
- Slack/Discord support
- Custom industry APIs
- Managed agents
- SOC2 compliance
Enterprise
For mid-market & enterprises needing custom integrations and SLAs.
Contact Sales- Unlimited tokens (fair-use SLA)
- Everything in Team, plus:
- Custom industry APIs
- Managed Hermes/OpenClaw agents
- Long-term memory & self-improvement
- Tool calling & orchestration
- SOC2 compliance available
- SLA guarantees
- Dedicated account manager
Token Pricing
We add a 20-35% markup on all provider costs. See live pricing across all models on our Yields page.
Input Tokens
$0.04
per 1M tokens
vs OpenAI $2.50/1M — 98% savings
Output Tokens
$0.12
per 1M tokens
vs OpenAI $10/1M — 99% savings
Avg Cost Reduction
60-80%
vs direct API calls
via intelligent model routing
Feature Comparison
| Feature | Free | Pro | Team | Enterprise |
|---|---|---|---|---|
| Monthly tokens | 200K | 5M | 20M | Unlimited |
| API keys | 5 | 100 | 500 | Unlimited |
| Intelligent routing | ✓ | ✓ | ✓ | ✓ |
| Semantic caching | — | ✓ | ✓ | ✓ |
| Guardrails & safety | — | ✓ | ✓ | ✓ |
| Analytics dashboard | — | Advanced | Advanced | Custom |
| Virtual keys & budgets | — | ✓ | ✓ | ✓ |
| Custom guardrails | — | — | ✓ | ✓ |
| Budget alerts | — | — | ✓ | ✓ |
| Custom industry APIs | — | — | — | ✓ |
| Managed agents | — | — | — | ✓ |
| SLA & SOC2 | — | — | — | ✓ |
| Support | Community | Slack/Discord | Dedicated |
Frequently Asked Questions
How does intelligent routing work?
Our routing layer analyzes each request and routes it to the cheapest capable model. Simple tasks like summarization go to fast models ($0.04/1M), while complex reasoning goes to premium models. You always get the best quality-to-cost ratio.
What happens to my credits?
Credits never expire. Pro and Team plans include monthly token allocations. Enterprise plans have fair-use unlimited pricing.
Can I switch plans?
Yes, you can upgrade or downgrade anytime. Upgrades take effect immediately. Downgrades take effect at the start of your next billing cycle.
What models are available?
Access to 100+ models across OpenAI, Anthropic, Google, Meta, DeepSeek, Mistral, Groq, Fireworks, Together.ai, and more. Full pricing list on our Yields page.
Start saving on LLM costs today
Get a free API key. No credit card required. Start making smarter, cheaper LLM calls in minutes.