Migrate from OpenRouter

OpenRouter and FluxRouter are both OpenAI-compatible gateways, so migrating is the same kind of swap you'd do between any two OpenAI-compatible endpoints. You change three things:

1. Base URL to https://api.fluxrouter.ai/v1
2. API key to your Flux key (sk-... from the dashboard)
3. Model to flux-auto (or a specific flux-* id)

The OpenAI SDK, the endpoints, and the request and response JSON stay the same.

Get a Flux key#

Sign up at /auth/sign-up, open the dashboard, and create an API key. It looks like sk-.... The examples below read it from a FLUX_API_KEY environment variable.

Migrate the Python SDK#

Before (OpenRouter)#

from openai import OpenAI

client = OpenAI(
    api_key="sk-or-...",
    base_url="https://openrouter.ai/api/v1",
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Say hello."}],
)

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

After (FluxRouter)#

from openai import OpenAI

client = OpenAI(
    api_key="sk-...",                          # your Flux key
    base_url="https://api.fluxrouter.ai/v1",   # changed base URL
)

response = client.chat.completions.create(
    model="flux-auto",                         # let Flux route, or pin a flux-* id
    messages=[{"role": "user", "content": "Say hello."}],
)

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

Migrate the Node SDK#

Before (OpenRouter)#

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENROUTER_API_KEY,
  baseURL: "https://openrouter.ai/api/v1",
});

const response = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-4-5",
  messages: [{ role: "user", content: "Say hello." }],
});

console.log(response.choices[0].message.content);

After (FluxRouter)#

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.FLUX_API_KEY,            // your Flux key
  baseURL: "https://api.fluxrouter.ai/v1",     // changed base URL
});

const response = await client.chat.completions.create({
  model: "flux-auto",                          // let Flux route, or pin a flux-* id
  messages: [{ role: "user", content: "Say hello." }],
});

console.log(response.choices[0].message.content);

Mapping model ids#

On OpenRouter you pass provider-prefixed model ids like anthropic/claude-sonnet-4-5 or openai/gpt-4o. On Flux you pass a Flux alias instead:

• flux-auto (recommended): Flux routes each request to a sensible model for the prompt, so you usually don't hand-pick a model at all. This is the main difference in day-to-day use, with OpenRouter you choose the model, with flux-auto Flux chooses for you.
• A flux-pinned-* id when you want a specific backing model every time. List them with GET https://api.fluxrouter.ai/v1/models.
• A tier alias (flux-fast, flux-standard, flux-reasoning, flux-image) to target a speed and capability tier.

What stays the same#

• The OpenAI SDK and its method names.
• The endpoints: /v1/chat/completions, /v1/responses, /v1/models.
• Auth header style: Authorization: Bearer sk-....
• The request and response JSON, including streaming, tool calls, and structured outputs.

Next steps#

• Models: every model alias and how flux-auto and pinning work.
• Routing and pricing: the pricing lanes and how requests are priced.