Skip to main content

RouteLLM

RouteLLM provides an OpenAI-compatible API endpoint that intelligently routes your requests to the most appropriate underlying model based on cost, speed, and performance requirements.

Overview​

Instead of manually selecting which model to use for each request, you can use RouteLLM (route-llm). The system automatically analyzes the complexity of your request and routes it to the most suitable model, optimizing for a balance of performance and efficiency.

Supported Models​

RouteLLM intelligently routes requests to high-performance models such as:

  • Claude 4.5 Sonnet / Claude 4.5 Opus
  • GPT-5.2 / GPT-4o
  • Gemini 3 Flash / Gemini 3 pro

Usage Limits​

RouteLLM is available for unlimited use for ChatLLM subscribers. While it still tracks credits for accounting purposes, you can continue to use RouteLLM even after hitting your monthly credit limit.

API Integration​

For detailed API documentation, including endpoints, parameters, and code examples in Python and TypeScript, please refer to the RouteLLM API Reference.

Base URL​

  • Self-Serve Organizations: https://routellm.abacus.ai/v1
  • Enterprise Platform: https://<workspace>.abacus.ai/v1

Quick Example (Python)​

from openai import OpenAI

# Use the appropriate base_url for your organization
client = OpenAI(
  base_url="https://routellm.abacus.ai/v1",
  api_key="<your_api_key>",
)

chat_completion = client.chat.completions.create(
  model="route-llm",
  messages=[{"role": "user", "content": "Explain quantum computing."}]
)

print(chat_completion.choices[0].message.content)