← Code
Initial research 2026-09-21Anthropic

Claude Code

Inspect the documented capabilities, access conditions and sources for your task.

Initial research: 2026-09-21. Check current terms before choosing.

Updated

Compare this tool

The facts

Version
2.1.270 (CLI, mid-September 2026)
Price
From $20 per month. Subscription. Included usage and billing terms vary by plan.
API
✓Supported
Open weights
✕Not supported
Commercial use
yes
Agentic editing
✓Supported

Multi-file edits across a whole repository; Morph calls it the better fit for repository-shaped work

Source for Agentic editing (opens in a new tab)
Terminal use
✓Supported

Runs in the terminal and executes commands; scores 57.9% on Terminal-Bench 4.0 driving Claude Fable 5.1

Source for Terminal use (opens in a new tab)
I D E integration
✓Supported

Terminal, IDE, web browser, Slack and scheduled routines

Source for I D E integration (opens in a new tab)
Autonomous P Rs
✓Supported

Can take an issue, inspect code, plan a fix, run tests and open a pull request

Source for Autonomous P Rs (opens in a new tab)

Worth knowing

pricing

Anthropic's temporary 50% weekly limit boost ended 13 September 2026; the permanent replacement leaves 17% less capacity than users had.

2026-09-14BleepingComputer

From the publisher

Automatic source checks. These do not change the verification date of the facts above.

Sources

RELATED AI NEWS

Help Net Security2026-09-18

Plugin4Shell: Zero-Click RCE Hits Claude Code, Codex, Copilot and Gemini CLI (original report, opens in a new tab)

AIR Security researchers disclosed a flaw letting a plugin repository owner swap already-approved code past SHA-pinning checks with no user click, affecting four major coding agents; Anthropic patched in Claude Code 2.1.179 and OpenAI in Codex 0.146.0, while Microsoft shipped no Copilot fix and Google retired Gemini CLI uncorrected.

AnthropicOpenAIGitHubMicrosoftGoogleClaude CodeCodexGitHub CopilotGemini CLI
AI-generated summary. Open the headline to read the original report.

Beyond feature support

Quality evidence.

How well a model performs depends on the task, version, and settings.

We have not published a reviewed quality evaluation for these versions yet. Feature support and price do not establish output quality.

Try the same small task with each option. Check whether the result works, passes your tests, and can be maintained.

Published evaluations to exploreSWE-bench (opens in a new tab)

Check the exact version and test setup. Results on one task do not establish quality on another.

Start a conversation.