← all models
Mercury 2.5
inception
openrouter
Parameters
—
not published
Context
260K
260000 tokens
Input
$0.04
OpenRouter
Output
$0.15
OpenRouter
Cache read
$0.0040
OpenRouter
Accepts
text
Capabilities
include_reasoning
max_tokens
reasoning
reasoning_effort
response_format
stop
structured_outputs
temperature
tool_choice
tools
Description
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...
Also known as
openrouter
inception/mercury-2.5
version slug
inception/mercury-2.5-20260908
name
Inception: Mercury 2.5
display name
Mercury 2.5
Identifiers
- Vendor
-
inception
- OpenRouter
-
inception/mercury-2.5
- Version slug
-
inception/mercury-2.5-20260908
- Released
-
2026-09-08T18:28:57.000Z
- First seen
-
59 d ago
- Last crawled
-
10 d ago