Models / Inception / Mercury 2

Inception · mercury

Mercury 2

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

$0.25 in · $0.75 out

per 1M tokens · first-party price. Reference price from Inception, the lab's own listing.

Provider input prices run from $0.25 to $0.34 per 1M tokens. Output prices run from $0.75 to $1.03.

Context
128,000
Max output
50,000
Cache read
$0.025
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
No
Open weights
No
License
—
Released
Mar 4, 2026
Updated in source
Mar 4, 2026
Knowledge
—
Providers
4

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Inceptionreference$0.25$0.75$0.025——
NanoGPT$0.25$0.75$0.025——
Venice AI$0.31$0.94$0.031——
AI/ML API$0.34$1.03$0.034——