mercury familyActive
Mercury Coder Small
Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.
Context
32,768
Max output
16,384
Input / 1M
$0.25
Output / 1M
$1.00
Providers
2
01Profile
Profile
Released
2024-01-01
Last updated
2025-02-26
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-01-01
2026-08-03Addednano-gptoffering→ new
2026-06-06Addedverceloffering→ new
2026-06-04Removednano-gptofferingremoved→ new
2026-06-04Removedvercelofferingremoved→ new
2026-06-03Addednano-gptoffering→ new
2026-05-01Addedverceloffering→ new
2026-04-29Removedvercelofferingremoved→ new
2026-04-16Addedverceloffering→ new
2026-04-14Removednano-gptofferingremoved→ new
2026-04-14Removedvercelofferingremoved→ new
2026-02-17Addednano-gptoffering→ new
2026-01-10Addedverceloffering→ new