rmtly Intelligent
After all, it's just AI.
What it is
An OpenAI-compatible inference endpoint and a web console you can log into.
Currently running:
- Qwen 3.8 27b
- 64k context, 45t/s avg, text only
- $1.00 / $4.00
Prices are per million tokens, input / output. List updated 17 October 2026
The console
With rmtly Intelligent you can log into the LiteLLM instance that runs the service and read your own usage statistics from the same place we do:
- your account credit
- which models are loaded and what they cost
- your API keys
What we keep
We keep as little as possible while still being able to support customers.
- Prompts and responses
- not retained
- Request metadata
- 30 days
Exact retention windows are in the privacy policy.
Request metadata comprises timestamps, token counts, model names, status codes, and your key’s identifier. It helps us support you, and does not include any prompt or response content.
Details are in the privacy policy, and the limits on how you can use it are in the acceptable use policy.
Getting an account
To get started, visit the Shop and purchase some credit. Your account will be automatically created if this is your first time.
For questions, you can always Write to us.