Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
inception/mercury-3Mercury 3 is an API model from inception, released on Oct 16, 2026, with a context window of 1,000,000 tokens, pricing of $0.1 per million input tokens and $0.35 per million output tokens. It accepts text input and produces text output.
At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.0014.
Specs are sourced from OpenRouter and were last checked on Nov 3, 2026. Always confirm current pricing and limits with the provider before production use.
Mercury 3 supports a context window of 1,000,000 tokens.
Mercury 3 is listed at $0.1 per million input tokens and $0.35 per million output tokens on OpenRouter.
Mercury 3 was published on Oct 16, 2026.
Mercury 3 accepts text input and produces text output.