Flux RouterDocumentation

Use Flux with LlamaIndex

Point LlamaIndex's OpenAI LLM at FluxRouter with a custom api_base and your Flux key.

LlamaIndex talks to FluxRouter through its OpenAI LLM. Because Flux is OpenAI-compatible, you use the OpenAI LLM class and set api_base to https://api.fluxrouter.ai/v1, your Flux key, and the model to flux-auto.

Set up the OpenAI LLM to use Flux

Install the LlamaIndex OpenAI integration (pip install llama-index-llms-openai), then point the LLM at Flux:

python
from llama_index.llms.openai import OpenAI

llm = OpenAI(
    model="flux-auto",                            # let Flux route, or pin a flux-* id
    api_key="sk-...",                             # your Flux key
    api_base="https://api.fluxrouter.ai/v1",      # the one line that points at Flux
)

response = llm.complete("Say hello from FluxRouter.")
print(response.text)

api_base is the documented parameter on the LlamaIndex OpenAI LLM for a custom OpenAI-compatible endpoint.

Read the key from the environment

python
import os
from llama_index.llms.openai import OpenAI

llm = OpenAI(
    model="flux-auto",
    api_key=os.environ["FLUX_API_KEY"],
    api_base="https://api.fluxrouter.ai/v1",
)

Use it as the default LLM

Set Flux as the global LLM through Settings, and the rest of LlamaIndex (query engines, agents, indexes) uses it automatically:

python
from llama_index.core import Settings

Settings.llm = llm

Pick a model

flux-auto routes each request for you. To pin a model, swap the model value for a tier alias (flux-fast, flux-standard, flux-reasoning) or a flux-pinned-* id. See Models.