inception/ · 2 models
Explore Inception Labs models in one place. Compare capabilities, pricing, and privacy across serving providers to find the right fit.
In this catalog
Compare available routes
Per 1M text tokens
Tokens per request
Mercury 2 is Inception's diffusion-based reasoning language model, which generates by refining many tokens in parallel rather than one at a time. It takes text input and output with a 128K-token context window and supports tunable reasoning depth, native tool calling and schema-aligned JSON output.
Mercury 3 is Inception's most capable diffusion-based reasoning model, generating over 1,000 tokens per second with a 1M-token context window, tunable reasoning, tool calling, and structured output support.
