USE CASE
Flat-rate LLM API for chat and roleplay
Long chat sessions and roleplay generate heavy token use — exactly the workload where a per-token meter hurts. A flat monthly rate means the meter never decides how long a scene can run.
Connect your favorite frontend
Profundo speaks OpenAI-compatible Chat Completions, so it plugs into the chat clients you already use:
- SillyTavern — supported Chat Completions setup
- Janitor AI — supported browser connection
- RisuAI — supported connection
- Any custom client that accepts an OpenAI-compatible base URL
// SillyTavern, Janitor AI, RisuAI, or any OpenAI-compatible chat client
URL: https://api.profundoai.com/v1
API key: YOUR_PROFUNDO_KEY
Model: gpt-6-astra (or claude-fable-5-1 / gpt-5.6-luna / kimi-k3)Models for chat
Strong chat and roleplay picks from the catalog include GPT 6 Astra, Claude Fable 5.1, GPT 5.6 Luna, and Kimi K3. All models are included in every plan — switch any time.
Pricing that fits long sessions
Plus is $10/mo for 250 requests/day. Priority is $40/mo for 2,000 requests/day. Performance is $100/mo with no daily cap. See all plans.