Skip to main content

Artemis LLM Gateway

Artemis is the centralized LLM gateway that provides a unified API for all AI services in the Jetta infrastructure.

Overview​

URL: https://artemis.jettaintelligence.com

Artemis routes LLM requests to various providers (Anthropic, OpenAI, etc.) with:

  • API key management - Centralized credential handling
  • Request routing - Provider selection and fallbacks
  • Usage tracking - Token counting and cost monitoring
  • Rate limiting - Request throttling

Usage​

All internal services should use Artemis instead of calling LLM providers directly:

import httpx

response = httpx.post(
    "https://artemis.jettaintelligence.com/v1/messages",
    json={
        "model": "claude-sonnet-4-20250514",
        "messages": [{"role": "user", "content": "Hello"}]
    },
    headers={"Authorization": "Bearer <your-key>"}
)

Supported Models​

  • Claude (Anthropic)
  • GPT-4 (OpenAI)
  • Custom fine-tuned models