Integrations

Integrations for SDKs, coding agents and editors

LLMFlux speaks the OpenAI and Anthropic API formats, so the SDKs, coding agents and frameworks you already use connect with a base URL and a key. One integration gives them every model in the catalogue.

Official SDKs

OpenAI SDK (Python, Node.js and others): set the base URL to https://api.llmflux.dev/v1.

Python (openai)python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmflux.dev/v1",
    api_key="YOUR_LLMFLUX_API_KEY",
)

resp = client.chat.completions.create(
    model="claude-sonnet-5-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Anthropic SDK: set the base URL to https://api.llmflux.dev.

Python (anthropic)python
import anthropic

client = anthropic.Anthropic(
    base_url="https://api.llmflux.dev",
    api_key="YOUR_LLMFLUX_API_KEY",
)

message = client.messages.create(
    model="claude-sonnet-5-5",
    max_tokens=512,
    messages=[{"role": "user", "content": "Hello, Claude"}],
)
print(message.content[0].text)

Coding agents

Claude Code uses the Anthropic Messages format:

Claude Codebash
export ANTHROPIC_BASE_URL="https://api.llmflux.dev"
export ANTHROPIC_API_KEY="YOUR_LLMFLUX_API_KEY"
claude

Codex CLI uses the Responses format through a provider block in ~/.codex/config.toml. The SDKs and editors guide has the complete block and the base-URL detail Codex needs.

Codex CLI (excerpt)toml
# ~/.codex/config.toml — see the docs for the full provider block
model_provider = "llmflux"
model = "claude-sonnet-5-5"

Frameworks and editors

Most frameworks and editor extensions with an “OpenAI-compatible” or “custom base URL” option work with LLMFlux. Many read these environment variables:

Environmentbash
export OPENAI_BASE_URL="https://api.llmflux.dev/v1"
export OPENAI_API_KEY="$LLMFLUX_API_KEY"

Use model ids from the model catalogue. For the endpoint details see the OpenAI-compatible API and Anthropic-compatible API pages.

Documentation

Frequently asked questions

How do I integrate multiple LLM providers?
Integrate LLMFlux once with an OpenAI or Anthropic SDK. Every model in the catalogue, from several model makers, is then available through that one integration by changing the model id.
Does my framework work with LLMFlux?
If it lets you set an OpenAI-compatible base URL (often OPENAI_BASE_URL) or an Anthropic base URL, it can use LLMFlux. Set the base URL and use your LLMFlux key.
Which tools are documented?
The docs have step-by-step guides for Claude Code, Codex CLI, the OpenAI SDKs for Python and Node.js, editors that accept an OpenAI-compatible endpoint, and curl.

Start with one key

Create an account, generate an API key, and send your first request in a few minutes.