Pricing

Self-serve and enterprise pricing for our private inference and chat.

Private Chat

Access the latest AI models and chat features, all running privately.

  • One week free trial
  • Access to premium models
  • No rate limits
  • Email and Slack support
GPT-OSSGPT-OSS
Kimi K2Kimi K2
DeepSeek R1DeepSeek R1
Qwen CoderQwen Coder
Llama 3.3Llama 3.3

*Models are subject to change

$10/month

Private Inference

Inference API access to powerful models, all running privately.

  • Access to all premium models
  • OpenAI-compatible API
  • Dashboard and usage metrics
  • Email and Slack support

*Models are subject to change

$2per 1M tokens

Enterprise

Custom deployment and dedicated support for your organization.

  • Dedicated inference endpoints
  • Custom models and prompts
  • Model training and fine-tuning
  • Custom API endpoints
  • SSO and Access Controls
  • Audit logs
  • On-prem integrations
  • Dedicated support

Custom pricing

Frequently Asked Questions

What models are available?

All available models are listed on our inference page. We offer a wide range of state-of-the-art open-source models, all running in GPU-powered secure hardware enclaves.

How is billing calculated?

Private Chat is a flat monthly fee. Private Inference is pay-as-you-go based on token usage. Enterprise plans are custom quoted based on your needs.

Cancel any time?

Yes, you can cancel your subscription at any time. There are no long-term contracts or cancellation fees. Your service will continue until the end of your current billing period.

What payment methods do you accept?

All payments are handled through Stripe for our self-serve plans. Enterprise customers can discuss alternative payment arrangements with our sales team.