LLM Reference

SWE-2 on Devin

SWE-2 · Cognition

Serverless

Last refreshed 2026-09-10. Next refresh: weekly.

Why use SWE-2 on Devin?

Devin offers SWE-2 with competitive pricing. Devin is Cognition's autonomous AI software engineer platform, providing Web, Desktop, CLI, and API access to Cognition-trained SWE models for long-horizon coding and agentic software-engineering work.

Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: swe-2
Model ID
swe-2

Request example

Curated snippets for this provider are not sourced yet. Use Devin documentation with model ID swe-2.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Capabilities

ReasoningJSON / Tool useCode Execution

About SWE-2

SWE-2 is Cognition's proprietary coding model for long-horizon asynchronous software-engineering tasks in Devin, launched September 10, 2026. Post-trained from the Kimi K3 2.8T-parameter base with additional RL at multi-trillion-parameter scale, SWE-2 pushes the cost–performance Pareto frontier and is available through Devin Desktop and CLI at launch, with rollout to Devin Web and Fusion.

Get Started

Model Specs

Released2026-09-10
Parameters2.8T (base: Kimi K3)