llama-index-llms-duel 0.1.0

llama-index llms duel agents integration

LlamaIndex Llms Integration: Duel Agents

Duel Agents routes each prompt against multiple models and bills the cheapest answer that still wins, behind an OpenAI-compatible proxy.

Installation

pip install llama-index-llms-duel

Create an API key at duelagents.com/dashboard/settings (an active subscription is required) and set it:

export DUEL_API_KEY="duel_<prefix>_<secret>"

Usage

from llama_index.llms.duel import DuelLLM

llm = DuelLLM(model="duel-auto")

resp = llm.complete("Explain concurrent agents in one sentence.")
print(resp)

Chat:

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(role="system", content="You answer concisely."),
    ChatMessage(role="user", content="What is model routing?"),
]
print(llm.chat(messages))

duel-auto lets Duel pick the model. You can also pass a specific model name (for example gpt-4o-mini or claude-3-5-haiku-latest) to route to that provider.

License

MIT