--- title: Junie Eco Mode | daily.dev description: JetBrains' Junie coding agent now has an Eco mode that splits tasks between two models to cut costs. Your selected model investigates the task and writes a... canonical: https://daily.dev/posts/junie-eco-mode-vzcva9q69 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Junie Eco Mode | daily.dev og:description: JetBrains' Junie coding agent now has an Eco mode that splits tasks between two models to cut costs. Your selected model investigates the task and writes a... og:url: https://daily.dev/posts/junie-eco-mode-vzcva9q69 og:image: https://api.daily.dev/og/posts/Vzcva9q69.png og:image:alt: Junie Eco Mode og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Junie Eco Mode **[JetBrains](https://daily.dev/sources/jetbrains)** · 9 min read · 0 upvotes · 0 comments ## Summary JetBrains' Junie coding agent now has an Eco mode that splits tasks between two models to cut costs. Your selected model investigates the task and writes a structured plan, then hands implementation and testing to a cheaper model, currently GPT-6 Luna. Across two internal benchmarks, average model cost per task fell 57% and 48%, while resolve rates changed by less than one percentage point. Eco mode is generally available in Junie CLI 26.10.20 and on by default for several supported models including Opus 5.5, Fable 5.1, and Grok 4.7. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Junie Eco mode and how does it reduce AI coding costs? Junie Eco mode splits a coding task between two models: your selected model investigates the code and writes a structured plan, then a cheaper model (currently GPT-6 Luna) implements and tests it. In internal benchmarks this cut average model cost per task by 57% on one benchmark and 48% on another, while average resolve rates changed by less than one percentage point. _Anyone weighing AI coding agent costs against output quality can track real-world benchmarks like this on daily.dev._ ### Does using a cheaper model for implementation hurt AI coding agent accuracy? Not meaningfully, according to JetBrains' internal testing of Junie Eco mode. On benchmark B, resolve rate moved from 49.1% to 48.5% (a 0.6 point drop) while cost fell 57%. On benchmark A, resolve rate stayed at 32.1% both with and without the cost-saving mode, with cost down 48%. _Developers choosing between pricier and cheaper AI models for coding tasks can follow benchmark results like these on daily.dev._ ### When is the Junie Eco mode feature available and which models support it? Junie Eco mode is generally available in Junie CLI version 26.10.20 and later, and available in JetBrains Air EAP for IDEs including IntelliJ IDEA 2026.3 Beta and 2026.2 JetBrains IDEs. It's on by default for Opus 5, Opus 5.5 at medium effort and above, Fable 5.1, Grok 4.5 through 4.7, GPT-5.6 Sol, GPT-6 Sol, GPT-5.6 Terra, and GPT-6 Astra. _Teams rolling out new Junie CLI versions can keep up with release specifics like this on daily.dev._ ## Similar posts on daily.dev - [Junie: The JetBrains AI Coding Agent Leaves Beta.](https://daily.dev/posts/junie-the-jetbrains-ai-coding-agent-leaves-beta--leoe26dci) · JetBrains · 8 upvotes · 0 comments - [Junie CLI, the LLM-agnostic coding agent, is now in Beta](https://daily.dev/posts/junie-cli-the-llm-agnostic-coding-agent-is-now-in-beta-f8mv9st0t) · JetBrains · 0 upvotes · 0 comments - [We Tested Grok, Opus, Sonnet, GPT, and Gemini in Kilo Code Reviewer](https://daily.dev/posts/we-tested-grok-opus-sonnet-gpt-and-gemini-in-kilo-code-reviewer-yjkkqinsy) · Kilo Blog · 8 upvotes · 1 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#llm](https://daily.dev/tags/llm), [#jetbrains](https://daily.dev/tags/jetbrains) [View this post on daily.dev](https://daily.dev/posts/junie-eco-mode-vzcva9q69) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Junie Eco Mode","url":"https://daily.dev/posts/junie-eco-mode-vzcva9q69","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/junie-eco-mode-vzcva9q69"},"datePublished":"2026-10-29T13:17:24.917Z","dateModified":"2026-10-29T13:18:22.267Z","description":"JetBrains' Junie coding agent now has an Eco mode that splits tasks between two models to cut costs. Your selected model investigates the task and writes a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9b5c7380589ad2b48ade74e76eb5d506?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9b5c7380589ad2b48ade74e76eb5d506?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"JetBrains","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"JetBrains","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/53ecf0c676f34b3896ee109609d91efa","url":"https://daily.dev/sources/jetbrains"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/junie-eco-mode-vzcva9q69","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,llm,jetbrains","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"JetBrains","item":"https://daily.dev/sources/jetbrains"},{"@type":"ListItem","position":3,"name":"Junie Eco Mode"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/junie-eco-mode-vzcva9q69#faq","mainEntity":[{"@type":"Question","name":"What is Junie Eco mode and how does it reduce AI coding costs?","acceptedAnswer":{"@type":"Answer","text":"Junie Eco mode splits a coding task between two models: your selected model investigates the code and writes a structured plan, then a cheaper model (currently GPT-6 Luna) implements and tests it. In internal benchmarks this cut average model cost per task by 57% on one benchmark and 48% on another, while average resolve rates changed by less than one percentage point. Anyone weighing AI coding agent costs against output quality can track real-world benchmarks like this on daily.dev."}},{"@type":"Question","name":"Does using a cheaper model for implementation hurt AI coding agent accuracy?","acceptedAnswer":{"@type":"Answer","text":"Not meaningfully, according to JetBrains' internal testing of Junie Eco mode. On benchmark B, resolve rate moved from 49.1% to 48.5% (a 0.6 point drop) while cost fell 57%. On benchmark A, resolve rate stayed at 32.1% both with and without the cost-saving mode, with cost down 48%. Developers choosing between pricier and cheaper AI models for coding tasks can follow benchmark results like these on daily.dev."}},{"@type":"Question","name":"When is the Junie Eco mode feature available and which models support it?","acceptedAnswer":{"@type":"Answer","text":"Junie Eco mode is generally available in Junie CLI version 26.10.20 and later, and available in JetBrains Air EAP for IDEs including IntelliJ IDEA 2026.3 Beta and 2026.2 JetBrains IDEs. It's on by default for Opus 5, Opus 5.5 at medium effort and above, Fable 5.1, Grok 4.5 through 4.7, GPT-5.6 Sol, GPT-6 Sol, GPT-5.6 Terra, and GPT-6 Astra. Teams rolling out new Junie CLI versions can keep up with release specifics like this on daily.dev."}}]} ```