LLM Reference

Using SWE-2 on Devin

Implementation guide · SWE-2 · Cognition

Serverless

Devin exposes SWE-2 through model ID swe-2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

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

Quick Start

  1. 1
    Create an account at Devin and generate an API key.
  2. 2
    Use the Devin SDK or REST API to call swe-2 — see the documentation for request format.
API PortalDocumentationPricingModel Card

Code Examples

See Devin documentation for integration details.

Pricing on Devin

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.

Full model details →

Model Specs

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

Provider

Devin

Cognition

San Francisco, California, United States