Skip to content
AIMarketCap

SWE-1.6

Model
CognitionFamily SWE model familyactive

Fast agentic coding model served at up to 950 tokens per second and widely used in Devin Desktop.

Released
—
Context window
—
Modality
—
Open source
—
API available
—
Releases
1

Releases

1
May 27, 2026Cognition releases SWE-1.6SWE-1.6 · SWE-1.6

Cognition disclosed the release of SWE-1.6, a fast coding model that became the most-used model in Devin Desktop and could be served at up to 950 tokens per second.

Cognition Model releaseCognitionSWE-1.6