Inception
Mercury 2.5
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception
mercury-2.5Context
260K
Max output
65.5K
Input $/M
$0.04
Output $/M
$0.15
Cache read $/M
$0.004
Cache write $/M
—
Against the catalogue
Context window260K
Larger than 44% of the 7,784 models listed
Input price$0.04
Cheaper than 89% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentsnot supported
Temperaturesupported
Open weightsnot supported
Interleaved thinkingnot supported
Modalities
Input
Text
Output
Text
Reasoning controls
effortlow, medium, highPricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.04 |
| Output | $0.15 |
| Cache read | $0.004 |