Devin

Researched 15d agoPlatformTier 2

Cognition

Devin offers 3 tracked models (0 with output token pricing). This catalog covers general LLM work; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 0 workload areas across 3 available models; last verified 2026-11-05.

Use it for

  • Getting oriented before committing to a specific model

Do not use it for

  • Final benchmark picks without opening the relevant model detail page
  • Strict price-per-token comparisons until output pricing is sourced

Tracked models

3

Models available through this provider

Priced output routes

0

Output pricing not yet tracked

Cheapest output

Unknown

Output pricing not yet tracked

Batch-ready models

0

No batch pricing tracked

Latest model release

2026-11-04

16d since newest release

Freshness

2026-11-05

Researched 15d ago

fresh

Information

TypePlatform
TierTier 2
Models3
CompanyCognition
Founded2023
San Francisco, California, United States

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.

Where this host wins

Not enough capability or benchmark coverage yet to call strengths for this provider.

Getting started

Verify: quotas and regions in the linked vendor documentation.

Platform Overview

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.

Available Models(3)

View all →

All models available as Serverless

Contact provider for pricing

Where else to run this