Skip to main content
Comms hosts the model. Your app (or your hosted agent) spends tokens. Those tokens count against your plan. You do not paste a third-party model key into Comms for the workspace path. Bring-your-own providers remain available on an agent if you add one.

​
What is metered

Both write to the same ai_token meter for the billing period.

​
Rates

​
Included tokens

Self-serve plans stop at the included amount with HTTP 402. They do not silently overage. MSA workspaces keep running. AI line items land on the monthly usage invoice with dedicated-line fees and message overage.

​
API

  1. Mint a key with the AI scope (comms_ai) on API keys.
  2. Call chat completions.
  3. Read AI usage when you need remaining headroom.
The dashboard Developers → AI tab has the same endpoint, rates, and a live meter.

​
Compatibility

The completions endpoint is OpenAI-shaped:
  • messages[] with role + content
  • model, temperature, max_tokens
  • response choices[0].message.content and usage
Point an OpenAI SDK baseURL at https://osis.co/api/v1/comms and set apiKey to your Comms key. Streaming is not supported yet (stream: true returns 400).