LLM Reference

Using SWE-1 on Devin

Implementation guide · SWE-1 · Cognition

Serverless

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 — see the documentation for request format.

Code Examples

See Devin documentation for integration details.

About Devin

Devin is a hosted coding-agent platform rather than a token-metered model API. Users sign up at app.devin.ai, install the Devin CLI or Desktop client, or create programmatic sessions through the Devin REST API. Model selection resolves family aliases such as swe to the latest SWE version; Devin pricing is plan, quota, and on-demand credit based rather than published per-model token 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.

Pricing on Devin

Capabilities

ReasoningFunction CallingTool UseCode Execution

About SWE-1

SWE-1 is Cognition's proprietary coding model family for long-horizon asynchronous software-engineering tasks in Devin. The current first-party version is SWE-1.7 (July 8, 2026), trained from the Kimi K2.7-Code base with additional RL and available through Devin Web, Desktop, CLI, and API sessions. Devin CLI resolves the swe family alias to the latest SWE version.

Model Specs

Released2026-07-08

Provider

Devin

Cognition

San Francisco, California, United States