Inception's Mercury 3 is a text-only diffusion llm with selectable reasoning effort and a 1M-token context window. it replaces Mercury 2.5 at lower input and output rates, with the window up from 260K tokens.
pick it if
you need low-cost text work across contexts up to 1M tokens
latency matters; Inception cites 1,068 tokens/s on NVIDIA GPUs
your prompts repeat, so cached input bills at a tenth of input
skip it if
you need image input
you need stable long-term rates; the launch discount has no announced end date
Inception's previous-generation diffusion llm from September 2026, text-only, with tunable reasoning and a 260K context window. it retires on 2026-11-04; Mercury 3, the current generation, has lower input and output rates.
pick it if
you need fast text generation with reasoning and schema-aligned JSON
your prompts repeat, so cached input bills at a tenth of input
skip it if
Mercury 3 costs less on both rates and has a 1M window
you need image input
faq
which is cheaper, Mercury 3 or Mercury 2.5?
Mercury 3 lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Mercury 3 costs $0.22 and Mercury 2.5 $0.45.