Migrate from Mistral La Plateforme to Railwail

TL;DR — Switch in Under 5 Minutes

• Both APIs are OpenAI-compatible — change base URL and key only
• All Mistral models supported: Large 2, Small, Codestral, Pixtral 12B, Ministral 8B
• Both Mistral La Plateforme and Railwail host in the EU — full EU residency preserved
• Plus access to Claude, GPT-4o, Gemini, Llama through the same key
• EUR billing on both, but unified VAT invoice on Railwail

Why Move Off Mistral La Plateforme?

Mistral is excellent for EU-resident inference and competitive open-weight models. The trade-off is catalog scope — La Plateforme only hosts Mistral's own models. If you want to A/B against Claude or GPT-4o, you need a second account, second SDK, and second billing relationship. Railwail keeps the EU residency and adds the rest of the market.

Step 1 — Get a Railwail API Key

Sign up at railwail.com and generate a key.

Step 2 — Change Base URL

TypeScript / JavaScript

Before (Mistral SDK):

import { Mistral } from "@mistralai/mistralai";

const mistral = new Mistral({ apiKey: process.env.MISTRAL_API_KEY });

const res = await mistral.chat.complete({
  model: "mistral-large-2411",
  messages: [{ role: "user", content: "Hello" }],
});

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://api.railwail.com/v1",
});

const res = await client.chat.completions.create({
  model: "mistral-large-2411",
  messages: [{ role: "user", content: "Hello" }],
});

Python

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://api.railwail.com/v1",
)

resp = client.chat.completions.create(
    model="mistral-large-2411",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

cURL

curl https://api.railwail.com/v1/chat/completions \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-large-2411",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

API Endpoint Mapping

Model Mapping

Pricing Comparison (per 1M tokens, May 2026)

Why Railwail Over Mistral La Plateforme

• Unified VAT invoice covering Mistral + all other model providers
• Single API key — one fewer credential to rotate
• OpenAI-compatible API — drop the @mistralai/mistralai SDK
• Access to closed-source frontier models (Claude, GPT-4o, Gemini) for A/B
• Built-in playground for cross-model comparison
• Same EU residency Mistral La Plateforme provides

FAQ

Is data residency preserved?

Yes. Calls to Mistral models route to Mistral's EU infrastructure via Railwail's EU gateway. End-to-end EU residency is maintained.

Is fill-in-the-middle for Codestral supported?

Yes. POST /v1/completions with the codestral-2501 model and the prefix/suffix params triggers FIM mode.

Does the Pixtral vision API work?

Yes. Pass content as an array with text and image_url blocks (OpenAI vision schema). Railwail converts internally.

What about the Mistral Agents API?

Stateful agents (with built-in retrieval) are Mistral-proprietary. For equivalent behaviour on Railwail, use chat.completions with your own retrieval step and the tools array.

Are batch endpoints available?

Yes. POST /v1/batches accepts the OpenAI batch format for any Mistral model, 50% discount on async.

Next Steps

• Sign up at railwail.com
• Generate an API key
• Drop @mistralai/mistralai and use the OpenAI SDK
• Update baseURL and apiKey
• Read the reference at railwail.com/docs
• Browse Mistral models at railwail.com/models?provider=mistral
• Compare pricing at railwail.com/pricing