mercury familyActive
Mercury 2.5
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception
Context
260,000
Max output
65,536
Input / 1M
$0.04
Output / 1M
$0.15
Providers
5
01Profile
Profile
Released
2026-09-08
Last updated
2026-09-10
Knowledge cutoff
2025-11-01
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 5 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
9+ recent events since 2026-09-08
2026-09-10Addedinceptionoffering→ new
2026-09-10Price upveniceinput / 1M$0.05→ $0.25
2026-09-10Price cutveniceinput / 1M$0.25→ $0.05
2026-09-10Price upveniceoutput / 1M$0.19→ $0.94
2026-09-10Price cutveniceoutput / 1M$0.94→ $0.19
2026-09-09Addedveniceoffering→ new
2026-09-08Addedkilooffering→ new
2026-09-08Addedopenrouteroffering→ new
2026-09-08Addedverceloffering→ new