Your agents deserve an open tab.
Cirthan is an AI inference API with flat monthly pricing. Drop in any OpenAI-compatible client — your prompts are never stored.
Request an Invite
- OpenAI-compatible
- Up to 200K context
- Vision & audio
- Hosted in the USA
- Zero data retention
How it works
Get your API key
Sign up, pick a plan, and generate a key from your dashboard.
Point your client
Set your base URL to api.cirthan.com. Works with any OpenAI-compatible SDK or tool.
client = OpenAI(
base_url="https://api.cirthan.com/v1",
api_key="sk-..."
)
Build
Call chat completions, analyze images, transcribe audio. One flat monthly bill.
The models
Breglan
Fast and versatile. Vision, reasoning, 200K context. The workhorse for most tasks.
Saelorn
Smarter, deeper reasoning. More deliberate but thinks harder. Best when accuracy matters more than speed.
All plans include audio transcription.
What you can build
Coding agents
Point Pi, OpenCode, or any OpenAI-compatible coding agent at Cirthan. 200K context fits entire codebases. Iterate freely.
Always-on assistants
Run OpenClaw or similar autonomous agents on WhatsApp, Discord, or Slack. Always-on without usage spikes eating your budget.
Document & image processing
Summarize contracts, extract data from PDFs, or analyze screenshots with vision-capable models. Process in bulk — vision models handle PDFs, screenshots, and scanned documents.
Audio pipelines
Transcribe meetings, podcasts, or voice notes. Chain transcripts into language models for summaries and action items.
What makes Cirthan different
Pricing
Simple plans. No surprises.
Pro
The sweet spot for always-on agents
- Breglan + Saelorn
- 200K context
- 2x throughput
Ultra
Priority speed for interactive workflows
- Breglan + Saelorn
- 200K context
- 4x throughput
Fair use policy applies.
Cirthan is invite-only
We are onboarding developers in small batches to keep quality high. Leave your email and we will send you an invite when a slot opens.
No spam. No mailing list. Just an invite.
Already have an invite code? Sign up now