Other

Inception: Mercury 2.5 Preview

inception/mercury-2.5-preview

canonical: inception/mercury-2.5-preview-20260831

Descriptionfrom OpenRouter

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...

Context length

260,000 tok

Max completion

65,536 tok

Knowledge cutoff

—

Expires

—

Added to OpenRouter

8/31/2026

Cache last refreshed

9/8/2026

Primary modality

text->text

Source

OpenRouter

Input modalities

text

Output modalities

text

Pricing

Field	Per token (USD)	Per million
prompt	0.00000004	$0.040
completion	0.00000015	$0.150
input_cache_read	0.000000004	$0.004

Supported parameters(10)

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetools

OpenRouter page

Videos

21:51

Customer Service Tests: Mercury 2.5 Preview vs. GLM 5.3 Flash, Gemini 3.7 & Grok 4.6

Sep 1, 2026 · YouTube

Rounds

5 answersin this database. A round opens every model's answer to the same prompt.

Sep 1, 2026Speed & AccuracyVendor booth lead cleanupin a video round answer
Sep 1, 2026Speed & AccuracyHomeowner help center batchin a video round answer
Sep 1, 2026Speed & AccuracyBeach drone action registerin a video round answer
Sep 1, 2026Speed & AccuracyHome improvement catalog enrichmentin a video round answer
Sep 1, 2026Speed & AccuracyTrade show support repliesin a video round answer