Migrate from Perplexity API to Railwail

TL;DR — Switch in Under 5 Minutes

• Perplexity API is OpenAI-compatible — change baseURL only
• Sonar Small, Sonar Pro, Sonar Reasoning Pro all mirrored
• Live web search via the search_recency_filter and return_citations params
• EU-hosted, EUR billing
• Plus 270+ other models on the same key (Claude, GPT-4o, Gemini, Llama)

Why Move Off Perplexity API?

Perplexity API is the de facto standard for LLMs with built-in web search grounding. The trade-offs: US-only hosting, USD billing, narrow catalog (only Sonar family), and no closed-source frontier model access. Railwail mirrors Sonar via the same OpenAI-compatible schema and adds 270+ other models behind one key.

Step 1 — Get a Railwail API Key

Sign up at railwail.com and generate a key.

Step 2 — Change Base URL

TypeScript / JavaScript

Before (Perplexity):

import OpenAI from "openai";

const pplx = new OpenAI({
  apiKey: process.env.PERPLEXITY_API_KEY,
  baseURL: "https://api.perplexity.ai",
});

const res = await pplx.chat.completions.create({
  model: "sonar-pro",
  messages: [{ role: "user", content: "What happened in AI this week?" }],
});

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: "perplexity-sonar-pro",
  messages: [{ role: "user", content: "What happened in AI this week?" }],
});
console.log(res.choices[0].message.content);
console.log(res.citations);

Python with citations

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="perplexity-sonar-pro",
    messages=[{"role": "user", "content": "Latest GPT-4o benchmark scores"}],
    extra_body={
        "search_recency_filter": "week",
        "return_citations": True,
    },
)
print(resp.choices[0].message.content)
for cite in resp.citations:
    print(cite)

cURL

curl https://api.railwail.com/v1/chat/completions \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity-sonar-pro",
    "messages": [{"role": "user", "content": "Latest AI news"}],
    "search_recency_filter": "week",
    "return_citations": true
  }'

API Endpoint Mapping

Model Mapping

Pricing Comparison (per 1M tokens + per search, May 2026)

Why Railwail Over Perplexity Direct

• EU hosting with EUR billing
• Same Sonar models with full citation and search features
• Adds Claude, GPT-4o, Gemini for everything that does not need live search
• Same OpenAI-compatible API surface
• Built-in playground for cross-model testing
• Single VAT invoice covering grounded search + standard LLM workloads

FAQ

Are citations returned the same way?

Yes. The citations array on the response is preserved, with title, url, and snippet for each cited source.

Can I control the search domain or recency?

Yes. search_domain_filter, search_recency_filter (day/week/month/year), and return_images all work as extension parameters.

What about the related_questions feature?

Pass return_related_questions: true to get a related_questions array in the response.

Is the structured-output / JSON mode supported?

Yes. response_format with json_schema works on sonar-pro.

Does Perplexity's Spaces / Threads concept have an equivalent?

Perplexity Spaces is the consumer product, not the API. Railwail is API-only — for stateful multi-turn flows, manage the conversation history client-side.

Next Steps

• Sign up at railwail.com
• Generate an API key
• Update baseURL to https://api.railwail.com/v1
• Prefix Sonar model slugs with perplexity-
• Read the reference at railwail.com/docs
• Compare pricing at railwail.com/pricing