Skip to content- Sources: primary, discussion
- Summary: The OpenRouter listing describes a 600B-parameter sparse mixture of experts with 27B active parameters and a 1M-token context, served by a single provider. Listed pricing is $1.00 per million input tokens, $2.70 per million output tokens and $0.05 per million cache reads. The listing publishes no benchmark figures.
- Why it matters: It lists at $1.00 per million input tokens, $2.70 per million output and $0.05 cache reads from a single provider, which puts a 1M-context model aimed at agentic work well below frontier pricing, and the listing publishes no benchmark figures to check.