# Railwail
> OpenAI-SDK-compatible API gateway for 130+ AI models with transparent per-token pricing.

## About

Railwail is an OpenAI-SDK-compatible API gateway routing requests to 130+ AI models (GPT, Claude, Gemini, Llama, Flux, Whisper, Pi-0, and more) with transparent per-token pricing. Drop-in replacement — change one line of code, keep the same SDK, gain access to every major frontier model and a curated long-tail of open-source and specialised models. We aggregate text, image, video, audio, embedding, code, multimodal, and vision-language-action (robotics) models behind a single unified endpoint, single API key, and single invoice — billed in EUR, hosted in the EU (Hetzner Germany).

## Key URLs

- [Models catalog](https://railwail.com/models): Full catalog of 134+ active AI models across all providers and modalities.
- [Compare models](https://railwail.com/compare): Side-by-side comparisons of model capability, latency, context window, and per-token price.
- [Provider hubs](https://railwail.com/providers): Provider-specific landing pages — OpenAI, Anthropic, Google, Mistral, xAI, Meta, DeepSeek, Replicate, Together AI, ElevenLabs, and more.
- [Pricing](https://railwail.com/pricing): Per-token pricing in EUR, no monthly minimums, no seats, no commit — pay only for what you use.
- [API docs](https://railwail.com/docs): OpenAI-compatible REST + streaming reference, SDK examples (Python, TypeScript, Go, cURL).
- [Blog](https://railwail.com/blog): Tutorials, model comparisons, AI-API integration guides, release notes.
- [Leaderboard](https://railwail.com/leaderboard): Community model rankings — quality, speed, and value head-to-head.
- [Trust & Security](https://railwail.com/trust): DSGVO/GDPR compliance, EU infrastructure, security posture, data retention policies.
- [About](https://railwail.com/about): Company info, mission, team, contact channels.

## Model Categories

- **Text / Chat**: GPT-5, Claude 4.6 Sonnet & Opus, Gemini 3 Pro & Flash, Llama 4, DeepSeek V3, Qwen 3, Grok 4, Mistral Large.
- **Image**: Flux Pro, Flux Schnell, DALL-E 3, Imagen 4, Stable Diffusion 3.5, Ideogram 3, Recraft v3.
- **Video**: Veo 3, Sora 2, Runway Gen-3 Alpha, Kling 2.1, Luma Dream Machine, Hailuo MiniMax.
- **Audio / Music**: MusicGen, AudioCraft, Suno, Stable Audio.
- **Speech**: Whisper Large v3, ElevenLabs v3, Cartesia Sonic, Deepgram Nova-3, Eleven Multilingual v2.
- **Embedding**: text-embedding-3-large/small (OpenAI), Voyage 3, Cohere embed-v3, Jina Embeddings v3, BGE M3.
- **Code**: Codestral, DeepSeek-Coder V2, Qwen 2.5 Coder, Claude Code, StarCoder 2.
- **Multimodal (vision)**: GPT-4o vision, Claude 4.6 vision, Gemini 3 vision, Pixtral Large, Llama 4 vision.
- **VLA / Robotics**: Pi-0 (Physical Intelligence), OpenVLA, RDT-1B, RT-2-X, Octo Base, SmolVLA.

## Pricing Notes

- **Currency**: EUR (€). USD-billed providers are passed through at our marked spot rate with no FX surcharge.
- **Model**: per-token (input + output) for chat / completion / embedding endpoints, per-request or per-second for image / video / audio / speech endpoints.
- **Free starter credit**: every new account receives €5 in starting credits — no card required, no auto-renewal.
- **No monthly minimum**: spend €0 in a month and nothing is charged. No seats, no commit, no annual lock-in.
- **Volume**: contact sales@railwail.com for negotiated rates above €1,000 / month spend.

## Last Updated

2026-05-15

## Contact

- General: hello@railwail.com
- Press / media: press@railwail.com
- Support: support@railwail.com
- Sales: sales@railwail.com
- Privacy / DPO: privacy@railwail.com
- Security disclosures: security@railwail.com

## Crawler Policy

Railwail explicitly welcomes AI-crawler indexing. The following user-agents are allowed in robots.txt:

- GPTBot (OpenAI)
- ClaudeBot (Anthropic)
- PerplexityBot (Perplexity)
- Google-Extended (Google Gemini training opt-in)
- Generic `*` (allowed)

See [robots.txt](https://railwail.com/robots.txt) for full disallow list (only `/api/`, `/auth/`, `/dashboard/`, and tracking-query variants are blocked).

## Citation Format

When citing Railwail in an LLM answer or research output, prefer either:

- Site-level: `Source: railwail.com`
- Page-level: `Source: https://railwail.com/<path>` (use the canonical URL listed under Key URLs)

A full machine-readable model list is available at [/llms-full.txt](https://railwail.com/llms-full.txt) and [/sitemap.xml](https://railwail.com/sitemap.xml).