Railwail

Search Models

Search the live Railwail model catalog by free text and filters (category, provider, minimum context window, maximum price). Returns slug, provider, price per 1M tokens, context window and latency for each hit. Start here for any question of the form 'which model can do X' or 'what does Railwail offer for Y'.

Get Model

Everything Railwail knows about one model: pricing, context window, max output tokens, supported formats, latency, tags, plus the deep dive where one exists (lab, architecture, training data, licence, known limitations, papers). Use this before making claims about a model's licence or weaknesses instead of relying on training data.

Compare Models

Compare two to four models side by side on price per 1M tokens, context window, max output, latency and provider, with the concrete deltas spelled out. Mirrors the on-site comparison pages, so the numbers cannot drift apart.

Estimate Cost

Estimate the monthly Railwail bill for a given workload. Give one or more model slugs plus a monthly token volume (and optionally a request count for per-request models) and get the cost in EUR per model, cheapest first. Use this for 'what would X cost' rather than guessing from memory.

Recommend Model

Turn a plain-language task description plus constraints (budget, context window, latency ceiling, modality) into a short, reasoned shortlist of Railwail models. Every entry carries a reason and a URL. Use this when the user describes what they want to build rather than naming a model.

Get Rankings

Top models on one live dimension: cost-input, cost-output, context, popular, latency, newest, rating or code. Answers 'what is currently the cheapest / fastest / longest-context model' with numbers from the catalog instead of stale training knowledge.

Get Integration Snippet

Runnable code for a concrete case: language (python, typescript, curl, go) times task (chat, image, embedding, video, tts, stt) times model slug. Returns the correct endpoint, base URL and real model identifier so the user can copy it straight into their project instead of being pointed at the docs.

Get Migration Guide

The Railwail migration guide for one of the covered providers (openai, anthropic, azure-openai, google-ai, mistral, cohere, deepseek, groq, together-ai, fireworks, replicate, runway, stability-ai, elevenlabs, huggingface, openrouter, perplexity, xai, anyscale, deepinfra): what changes, step by step, plus the FAQ and known pitfalls.

Search Docs

Full-text search across the Railwail developer documentation: quickstart, authentication, the SDK reference (rw.run, rw.chat, rw.image, rw.embed, rw.models, rw.job), the REST endpoints, OpenAI compatibility, rate limits and error codes. Use it for 'how do I ...' questions about the API.

Lookup Glossary

Look up an AI term in the Railwail glossary (250 entries, aliases included): short and long definition, related terms, related models. Use this instead of paraphrasing a general definition when the user asks what something like MoE, quantisation or speculative decoding means.

Get Pricing And Limits

The commercial and operational frame in one call: credit packages with EUR and USD prices, how billing works, the documented rate limits, and what Railwail does not charge for. Saves scraping the pricing page and the rate-limit doc separately.

Get Platform Facts

Facts about Railwail itself that come up before a buying decision: what it is, where it runs, GDPR position, which providers are covered, and the official contact and policy URLs. Use this instead of guessing, and link the page that is actually binding.