8Claude Code Release Notes·
Claude Code 2.1.219 adds Claude Opus 5 as default model with 1M context and nested subagent support
Anthropic's Claude Code release 2.1.219 introduces Claude Opus 5 (claude-opus-5) as the new default Opus model, featuring 1M context window and fast mode priced at $10/$50 per million tokens. The release also expands agentic capabilities by raising the default nested subagent depth from 1 to 3, adds a DirectoryAdded hook for mid-session working directory registration, and improves stream-json subagent forwarding. Numerous bug fixes address permission handling, model picker display, Windows compatibility, and self-hosted runner lifecycle issues.
Related guides (5)
Anthropic
Anthropic: Frontier AI Lab at the Intersection of Capability and Safety Governance
Read asIn-depth
Related events (8)
Claude Opus 4.6 Released with 1M Token Context, Agentic Coding Advances, and State-of-the-Art Benchmarks
Anthropic has released Claude Opus 4.6, its most capable model to date, featuring a 1M token context window in beta, improved agentic coding and planning capabilities, and adaptive thinking with developer-controlled effort levels. The model claims top scores on Terminal-Bench 2.0, Humanity's Last Exam, GDPval-AA, and BrowseComp, outperforming OpenAI's GPT-5.2 by 144 Elo points on GDPval-AA. New product features include agent teams in Claude Code, context compaction for long-running tasks, and Claude in PowerPoint (research preview). Pricing remains unchanged at $5/$25 per million input/output tokens.
Claude Sonnet 5 launches as default model in Claude Code with 1M-token context
Anthropic has released Claude Sonnet 5, now the default model in Claude Code, featuring a native 1M-token context window. The model is available at promotional pricing of $2/$10 per million tokens (input/output) through August 31, 2026. Users must update to Claude Code version 2.1.197 to access the new model.
Anthropic Releases Claude Opus 4.5 with State-of-the-Art Coding, Agent, and Computer Use Capabilities
Anthropic has released Claude Opus 4.5, positioning it as the best model in the world for coding, agentic workflows, and computer use, with pricing reduced to $5/$25 per million input/output tokens. The model demonstrates significant token efficiency gains—up to 65% fewer tokens than prior models on equivalent tasks—alongside improvements in long-horizon autonomous task execution, multi-step reasoning, and self-improving agent behavior. The release is accompanied by updates to Claude Code, the Claude Developer Platform, and integrations with Excel, Chrome, and desktop environments. Early partner feedback from GitHub Copilot, Cursor, Notion, Warp, and others reports measurable benchmark improvements and new use cases previously out of reach.
Claude Code 2.1.217 release: subagent concurrency caps, MCP memory fix, and multi-platform bug fixes
Anthropic released Claude Code version 2.1.217 with a notable new cap on concurrently-running subagents (default 20, configurable via CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS) and a change preventing nested subagent spawning by default. The release also fixes a memory leak in MCP tool output handling, resolves auto-compact failures for Claude Opus 4.8 on Bedrock, and patches several Windows, corporate proxy/TLS, and session isolation bugs. The subagent concurrency and budget enforcement changes are architecturally significant for agentic workflows, preventing unbounded fan-out.
Anthropic Releases Claude Sonnet 4.6 with 1M Token Context, Improved Computer Use, and Coding Capabilities
Anthropic has released Claude Sonnet 4.6, positioned as a major upgrade over Sonnet 4.5 with improvements across coding, computer use, long-context reasoning, and agent planning. The model features a 1M token context window in beta and is now the default on claude.ai Free and Pro plans at unchanged pricing ($3/$15 per million tokens). Notably, users preferred Sonnet 4.6 over the prior Opus 4.5 frontier model 59% of the time in coding tasks, and the model shows significant gains on OSWorld computer-use benchmarks alongside improved prompt injection resistance. Safety evaluations found no major alignment concerns and rated it as safe or safer than prior Claude models.
Claude Code 2.1.207 release: Auto mode GA on Bedrock/Vertex/Foundry, default model updated to Claude Opus 4.8
Claude Code version 2.1.207 ships Auto mode as generally available on Bedrock, Vertex AI, and Foundry without an opt-in flag, and changes the default model for those platforms to Claude Opus 4.8. The release includes roughly 20 bug fixes spanning terminal performance, agent team crash loops, Remote Control session reliability, Windows credential stalls, and a shell-injection security fix in plugin hooks. Plugin option values are now restricted to user-level and managed settings, removing project-level .claude/settings.json as a source.
Anthropic Releases Claude Sonnet 4.5: Top Coding and Computer-Use Model with Agent SDK
Anthropic has released Claude Sonnet 4.5, claiming it is the best coding model and strongest model for building complex agents, with a 61.4% score on OSWorld (up from 42.2% for Sonnet 4) and state-of-the-art performance on SWE-bench Verified. The release is accompanied by major product upgrades including checkpoints in Claude Code, a native VS Code extension, a Claude Agent SDK giving developers access to the same infrastructure powering Claude Code, and new context editing and memory tools in the Claude API. Pricing is unchanged from Sonnet 4 at $3/$15 per million input/output tokens. Early enterprise customers including Cursor, GitHub Copilot, Devin, Canva, and Figma report significant gains in coding, agentic, and long-context tasks.
Claude Code 2.1.196 release: org-default models, MCP security fix, background agent reliability improvements
Anthropic released Claude Code version 2.1.196 with a notable security fix preventing untrusted workspace .mcp.json servers from auto-spawning, and added support for organization-level default model configuration via the admin console. The release includes significant background agent reliability improvements — long-running workflows now survive process restarts on all platforms including Windows — plus a streaming idle watchdog enabled by default that aborts and retries stalled response streams after 5 minutes. Numerous bug fixes address agent session state management, MCP OAuth scope handling, PowerShell compatibility, and a /code-review token usage reduction of ~25%.