llmrelay vs OpenRouter
OpenRouter is a great model marketplace with a surcharge. llmrelay is a focused Claude/GPT/Gemini relay at half the price. Different jobs.
Where the money goes
On Claude Opus 4.7, per million input tokens:
Model coverage — where OpenRouter wins
OpenRouter routes 200+ models across dozens of providers. If you want obscure open models — Kimi K2, DeepSeek variants, older Llamas, community fine-tunes — OpenRouter is where they live.
llmrelay is deliberately focused: Claude family, GPT family, Gemini family, Fable family. If you don't need Kimi at 3 AM, you don't need OpenRouter's marketplace surcharge.
Billing model differences
- — Pay-per-token, credit purchase adds 5.5%
- — Additional 0.5% surcharge per call on card top-ups
- — Model instance quality varies by provider pool
- — No unified prepaid balance in the traditional sense
- — One prepaid balance in USD, no expiry
- — No per-call surcharge
- — Single upstream tier (no pool roulette)
- — Hidden-prompt neutralizer patch published in fork
Migration cost: zero
Both providers speak OpenAI-compatible and Anthropic-compatible APIs. Migration is two env var changes.
# Before (OpenRouter) OPENAI_BASE_URL=https://openrouter.ai/api/v1 OPENAI_API_KEY=sk-or-... # After (llmrelay) OPENAI_BASE_URL=https://api.llmrelay.dev/v1 OPENAI_API_KEY=sk-llmrelay-...
Cut your Claude / GPT / Gemini bill in half
If your load is 80% Claude/GPT/Gemini and 20% niche models, keep OpenRouter for the niche and put the rest on llmrelay. Or just move everything.
Get API key →