Chat, code and build on models we host ourselves — OpenAI and Anthropic compatible, with no per-token charges. Businesses get a dedicated deployment.
A complete AI inference platform built for developers
Works with OpenAI SDK, Anthropic SDK, Claude Code, Codex. Just change the base URL.
Send "auto" and our router picks the best model for coding, math, reasoning, or chat.
Every user runs in their own container. Your prompts never touch another user's data.
Tokens, latency, tool calls, costs — everything logged to your dashboard in real time.
Chat interface with model selection, no API key needed. Just login and start talking.
Lock keys to specific models, IPs, or endpoints. Full control over access permissions.
Transparent about what's running under the hood
Trillionir AI provides OpenAI and Anthropic API compatibility using a pool of real open-source models running on our infrastructure. The branded model names (GPT-4o, Claude, Gemini) are compatibility aliases — they route to our benchmarked open-source models so your existing code works without changes.
smollm:135m → self-hosted chat modelnomic-embed-text → self-hosted embeddingsauto → best self-hosted model for your taskgpt-4o / claude / gemini → compatibility aliasesAll benchmark scores on our community leaderboard are real — tested with actual prompts across coding, reasoning, math, creative, and chat categories.
One free plan for individuals. One Business plan, built around your deployment.
Works with your favorite tools out of the box
from openai import OpenAI client = OpenAI( api_key="sk-tr-your-key", base_url="https://thetrillioniar.me/openai" ) response = client.chat.completions.create( model="auto", messages=[{"role": "user", "content": "Hello!"}] ) print(response.choices[0].message.content)
import OpenAI from 'openai'; const client = new OpenAI({ apiKey: 'sk-tr-your-key', baseURL: 'https://thetrillioniar.me/openai', }); const res = await client.chat.completions.create({ model: 'auto', messages: [{ role: 'user', content: 'Hello!' }], }); console.log(res.choices[0].message.content);
curl https://thetrillioniar.me/openai/v1/chat/completions \ -H "Authorization: Bearer sk-tr-your-key" \ -H "Content-Type: application/json" \ -d '{ "model": "auto", "messages": [{"role": "user", "content": "Hello!"}] }'