~openai

OpenAI GPT Luna Latest

Verified from OpenRouter · Text & embedding rates at 2026-09-11T15:21:24.543Z.

RatePriceBilling unitCondition
InputUSD 0.2per 1M input tokens
OutputUSD 1.2per 1M output tokens
Cache readUSD 0.02per 1M cached input tokens
Cache writeUSD 0.25per 1M cache-write tokens
Web searchUSD 0.01per web search
InputUSD 0.4per 1M input tokenswhen prompt exceeds 272,000 tokens
OutputUSD 1.8per 1M output tokenswhen prompt exceeds 272,000 tokens
Cache readUSD 0.04per 1M cached input tokenswhen prompt exceeds 272,000 tokens
Cache writeUSD 0.5per 1M cache-write tokenswhen prompt exceeds 272,000 tokens