Skip to content
Models
PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin launches Devin Apps, private web tools hosted on its cloud compu… Devin adds free SWE‑2 sessions and desktop access to Teams plan Gemini 4 Hydrogen launches in Devin Desktop and CLI, matching GPT‑6.1 … Basis reduces 20‑hour accounting process to 30 minutes with Devin Clou… Claude Mythos 5.2 added to Devin Security with benchmark score of 73.5 Gemini 4 Carbon added to Devin Desktop and CLI, scores 40% on Frontier… Claude Fable 5.2 added to Devin, leads FrontierCode 2.0 benchmark with… Devin offers 50% off Teams plan for users migrating from competing cod… PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin launches Devin Apps, private web tools hosted on its cloud compu… Devin adds free SWE‑2 sessions and desktop access to Teams plan Gemini 4 Hydrogen launches in Devin Desktop and CLI, matching GPT‑6.1 … Basis reduces 20‑hour accounting process to 30 minutes with Devin Clou… Claude Mythos 5.2 added to Devin Security with benchmark score of 73.5 Gemini 4 Carbon added to Devin Desktop and CLI, scores 40% on Frontier… Claude Fable 5.2 added to Devin, leads FrontierCode 2.0 benchmark with… Devin offers 50% off Teams plan for users migrating from competing cod…

Devin Desktop · Continuity · Apr 6–12, 2026

5 releases · updated

Devin Desktop: Enhanced MCP registry support

This week, Devin Desktop shipped five releases, with the main change being enhanced MCP registry support, which helps users with OAuth connections to MCP servers. The releases also included improvements to the adaptive model and fixes for various bugs. These changes benefit users on Pro, Max, and Teams plans who use adaptive models and MCP servers.

v1.9600.1047 (Next) · April 10, 2026

This release fixed resource parameter support for OAuth connections to MCP servers and enhanced MCP registry support. These changes improve the stability and functionality of Devin Desktop for users with MCP servers.

Official release notes

Bug Fixes and Improvements

  • Fixed resource parameter support for OAuth connections to MCP servers
  • Enhanced MCP registry support

v1.9600.41 · April 8, 2026

Also shipped to the Next channel as v1.9600.1042.

This release fixed a bug with the adaptive model router that prevented switching models after the first request. All users who encountered the bug had their quota reset and overage restored.

Official release notes

Adaptive Fix

We fixed a bug with the adaptive model router which prevented switching models after the first request.

All users who encountered the bug have had quota reset and overage restored.

v1.9600.40 · April 7, 2026

Also shipped to the Next channel as v1.9600.1040.

This release improved the visibility of the adaptive model in the model picker, making it easier for users to select and manage their models.

Official release notes

Adaptive Model Visibility

We’ve improved the visibility of the adaptive model in the model picker.

v1.9600.1038 (Next) · April 6, 2026

This release introduced the Adaptive model option, which intelligently selects the best model for each task and helps users manage their quota. It also includes dynamic model selection, extra usage promo, and updated token pricing information.

Official release notes

Introducing Adaptive

We’ve made several model packaging changes, with more info here.

Adaptive Model Router

A new Adaptive model option is now available in the model picker. Adaptive intelligently selects the best model for each task, helping you make your quota last longer by avoiding overuse of premium models.

  • Availability: Now available to all self-serve users on Pro, Max, and Teams plans.
  • Dynamic model selection - Automatically chooses the right underlying model for your task while drawing down quota at a fixed per-token rate.
  • Extra usage promo - Beyond your quota, extra usage is offered at 0.50 USD per 1M input tokens, 2.00 USD per 1M output tokens, and 0.10 USD per 1M cache read tokens for the next 2 weeks.

v1.9600.38 · April 6, 2026

This release introduced the Adaptive model option and updated the model picker with pricing context, including token pricing information, prompt cache timer, and token counts in response cards.

Official release notes

Introducing Adaptive

We’ve made several model packaging changes, with more info here.

Adaptive Model Router

A new Adaptive model option is now available in the model picker. Adaptive intelligently selects the best model for each task, helping you make your quota last longer by avoiding overuse of premium models.

  • Availability: Now available to all self-serve users on Pro, Max, and Teams plans.
  • Dynamic model selection - Automatically chooses the right underlying model for your task while drawing down quota at a fixed per-token rate.
  • Extra usage promo - Beyond your quota, extra usage is offered at 0.50 USD per 1M input tokens, 2.00 USD per 1M output tokens, and 0.10 USD per 1M cache read tokens for the next 2 weeks.

Updated Model Picker with Pricing Context

The model picker now shows token pricing information directly, so you can see the exact rate extra usage is billed at.

  • Token pricing display - Per-model input, output, and cache read token rates visible in the picker.
  • Prompt cache timer - A new prompt cache timer is integrated into the context window indicator to help you track caching status.
  • Token counts in response cards - Response cards after messages now include token counts so you can understand exactly how each message cost was calculated.

Fan coverage from Devin Central — not an official Cognition announcement. Devin is a trademark of Cognition.