Free
$0/mo
1K req/day, individuals
Gemini Code Assist
Google's AI coding assistant — from IDE to terminal to Android Studio.
Google's AI coding assistant powered by Gemini 2.5 Pro. Agent Mode is now GA in VS Code and IntelliJ — it plans multi-file changes, applies inline diffs, and runs IDE tools autonomously. Gemini CLI brings the same model to the terminal. Android Studio support, a 2M token context window (Vertex AI), Codebase Context for project-wide queries, MCP integration, and custom rules and commands round out the 2026 platform. 2.5× improvement in task completion vs unassisted developers.
+Pros
- Powered by Gemini 3 with a 1M-token context window, enabling whole-codebase awareness and highly accurate code completions, chat, and agentic tasks.
- Agent mode (Preview) with multi-file editing, MCP server integration, and human-in-the-loop review — enabling complex multi-step SDLC tasks directly from the IDE.
- Enterprise-grade security and privacy: customer code is never used for model training, backed by IP indemnification, SOC 1/2/3, ISO 27001/27017/27018/27701 certifications, and VPC Service Controls.
- Broad IDE support across VS Code, JetBrains (IntelliJ, PyCharm, GoLand, WebStorm), Cloud Workstations, Cloud Shell Editor, plus Gemini CLI for terminal-based AI assistance.
- Code customization using private organizational codebases and Markdown docs for tailored suggestions, plus a built-in usage analytics dashboard for enterprise ROI tracking.
−Cons
- Pricing is steep compared to competitors: Standard at $22.80/user/month and Enterprise at $54/user/month, with no truly free tier for commercial teams.
- The free individual tier is being sunset on June 18, 2026 — Gemini CLI and IDE extensions for individuals are migrating to Antigravity, creating disruption risk for unpaid users.
- Best features (Apigee API dev, BigQuery insights, Cloud Run deployment, Application Integration) are deeply tied to the Google Cloud ecosystem, reducing value for teams on other cloud providers.
Pricing
Standard
$22.80/mo
1.5K req/day
Enterprise
$54/mo
2K req/day, Vertex AI, 2M context
Google Developer Program Premium
$24.99/mo
Premium developer features
Gemini Code Assist is Google's AI coding assistant, now powered by Gemini 2.5 Pro across all tiers — free and paid. Generally available since Google I/O 2025, it serves individual developers, teams on Google Cloud, and enterprises via Vertex AI. In an internal study, developers using Gemini Code Assist completed common tasks 2.5× more successfully than those without AI assistance.
Agent Mode — stable in IntelliJ and in preview for VS Code — lets the assistant autonomously plan and execute complex, multi-file development tasks: generating unit tests, performing large refactors, fixing build errors, and creating GitHub pull requests via MCP. The agent formulates a plan, applies changes across files with inline diffs, and lets developers review, refine, or auto-approve each step. Codebase Context (launched March 2026) enables project-wide queries such as 'where is the payment logic?' directly from the IDE, giving the agent full architectural awareness.
The 2026 platform spans four surfaces: VS Code and JetBrains extensions, Android Studio (covering the full Android development lifecycle), GitHub integration for code review, and the Gemini CLI for terminal-native workflows. Standard and Enterprise customers on Vertex AI will gain access to a 2 million token context window — enabling bug tracing, large-scale code transformations, and onboarding guide generation across massive codebases. Custom rules ('always add unit tests') and custom commands ('generate exception handling logic') let teams enforce project standards on every AI generation.
Key Features
• Gemini 2.5 Pro: powers all tiers, free and paid
• Agent Mode: autonomous multi-file planning and execution (VS Code preview, IntelliJ stable)
• Codebase Context: project-wide natural-language queries across all files (March 2026)
• Gemini CLI: terminal-native coding assistant, same model, free with Google account
• Android Studio: Agent Mode and full Android lifecycle AI support
• GitHub integration: code review agent, PR comments, and suggestions
• MCP support: connect to GitHub, external tools, and custom MCP servers
• 2M token context window: for Standard/Enterprise on Vertex AI (coming 2026)
• Custom rules and commands: enforce team standards on every AI generation
• Chat history and threads: resume tasks and explore directions across sessions
• GCP-aware: deep knowledge of AWS APIs, Cloud Run, BigQuery, Firebase, and more
• 2.5× task completion improvement vs unassisted developers (internal study)
Version History
Agent mode bug fix for Cloud Workstations; various bug fixes and minor product enhancements across both IDEs.
Gemini 3.1 Pro and Gemini 3.0 Flash models made available in Preview for agent mode, chat, and code generation to all Standard and Enterprise subscribers.
File outline and finish changes features reached General Availability (GA) in VS Code, allowing AI pair-programming that observes work-in-progress.
File outline and finish changes features reached General Availability (GA) for IntelliJ IDEA-based IDEs.
Gemini 2.5 Pro and 2.5 Flash models became Generally Available, powering chat, code generation, and transformation with improved reasoning capabilities.
Signature Snippet
In VS Code, open Agent Mode and type: 'Add OpenTelemetry tracing to every API handler, update the integration tests, and open a GitHub PR.' Gemini Code Assist reads the full codebase via Codebase Context, plans the changes across 12 files, applies inline diffs file by file, runs the test suite, and creates the PR via MCP — pausing for your review at each step.More in this Space
Prime Agent (Prime Intellect)
Prime Agent is an open-source (MIT) self-improving coding and research harness by Prime Intellect, built on a Recursive Language Model that runs inside a persistent IPython REPL and a Continual Harness that refines its own state via /refine. It took the same frontier weights from 30.2% to 95.5% on ARC-AGI-3 RHAE Best@1, powered daemon-backed sessions, and ships no hosted offering.
OpenCodeReview (ocr)
OpenCodeReview (ocr) is Alibaba's open-source AI code-review CLI. It reads git diffs and drives an LLM agent through a hybrid architecture where deterministic pipelines handle file selection, rule matching, and comment positioning while the agent does the reasoning. Built on two years of internal use at Alibaba scale, it ships a multi-language ruleset and consumes roughly 1/9 of the tokens of general-purpose agents.
Delta (by Zed)
Multiplayer environment from Zed for coding with agents. Threads unify the agent conversation, the code edits, and human review in one shareable artifact, replacing the branch/PR loop. Built on DeltaDB, a CRDT-based version control layer that records every edit between commits alongside the prompts and reasoning that produced them.