Simple, transparent pricing.
Start free and scale as you grow. No hidden fees, no surprises.
Free
$0 /mo
Get started instantly
No credit card required
- qwen3:8b access
- Model-dependent context
- 100 requests/day
- API keys
- Community support
Recommended Pro
Coming Soon
For professionals and teams
Notify me →Everything in Free, plus:
- Roadmap model access
- Long-context models as they land
- Higher limits
- Priority routing
- Streaming and tool support
- Email support
Max
Coming Soon
For power users and enterprises
Notify me →Everything in Pro, plus:
- Custom rate limits
- Priority queue access
- Dedicated capacity
- Custom model hosting
- Custom SLA options
- Dedicated support
Compare Plans
Feature breakdown.
Feature
Free
$0/mo
Pro
Coming soon
Max
Coming soon
Models
qwen3:8b
Roadmap catalog
Custom catalog
Context window
Model-dependent
Long-context roadmap
Custom
Rate limit
100/day
Higher
Custom
Streaming
Tool support
Roadmap
Custom
Priority routing
Roadmap
Custom
Custom models
Support
Community
Email
Dedicated
SLA
Custom
FAQ
Common questions.
The free tier gives you access to qwen3:8b with up to 100 requests per day. No credit card is required. Sign up, get an API key, and start building through the OpenAI-compatible chat API.
Paid plans will open around expanded model access, higher limits, priority routing, and dedicated capacity. Sign up for notifications on the pricing cards above to get early access as those plans come online.
idyl.inference is compatible with the OpenAI Chat Completions request shape. Common SDKs and tools can use idyl by setting the base URL and choosing qwen3:8b. Some provider-specific OpenAI APIs are outside the current scope.
Free access currently starts with qwen3:8b. The roadmap is built around Qwen, DeepSeek, Llama, Mistral, Gemma, Phi, Kimi, and other open-weight families as model support and network capacity come online.
Yes. Accounts and API keys are designed to carry forward as paid plans open, so teams can start on free access and move into higher limits or dedicated capacity later.
For teams that need dedicated infrastructure, custom model hosting, volume discounts, or specific SLA requirements, we can discuss a tailored enterprise plan.