llmrelay
// price and coverage

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:

Anthropic official list
$5.00
baseline
OpenRouter
~$5.25
list + credit surcharge + per-call fee
llmrelay
$2.50
50% off list

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

OpenRouter
  • — 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
llmrelay
  • — 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 →