{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiagopezjqxe7tgccenbrpwagvscuelf6xt6d6kaedffdgab7sxpzy",
    "uri": "at://did:plc:dz7fbvkxedbwlm4sroohfpee/app.bsky.feed.post/3mf3kjuxakaa2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreibszsj4ju3ipshqewnx2vvp3p2vqjrbmryuqmzk4ptch6mn23mjeq"
    },
    "mimeType": "image/jpeg",
    "size": 38664
  },
  "description": "What's new? Anthropic launched Claude Sonnet 4.6 with a 1m token context, refined instruction following and long-context reasoning; available across all Claude platforms;",
  "path": "/anthropic-releases-claude-sonnet-4-6-with-1m-context-for-all-users/",
  "publishedAt": "2026-02-17T21:54:57.000Z",
  "site": "https://www.testingcatalog.com",
  "tags": [
    "pic.twitter.com/TDId3XUSRs",
    "February 17, 2026",
    "Source",
    "@claudeai"
  ],
  "textContent": "Anthropic has launched Claude Sonnet 4.6, targeting developers, enterprises, and knowledge workers who rely on advanced AI for coding, document processing, and complex computer-based tasks. The model is immediately available across all Claude plans, including Free, Pro, and enterprise offerings, and is accessible through Claude.ai, Claude Cowork, Claude Code, the Claude API, and major cloud platforms. Pricing remains unchanged from the previous version, ensuring access for both individual and organizational users.\n\n> This is Claude Sonnet 4.6: our most capable Sonnet model yet.\n>\n> It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design.\n>\n> It also features a 1M token context window in beta. pic.twitter.com/TDId3XUSRs\n>\n> — Claude (@claudeai) February 17, 2026\n\nClaude Sonnet 4.6 features a 1M token context window (in beta), improved consistency, better instruction following, and marked gains in long-context reasoning and agentic planning. It excels at navigating real-world software, such as spreadsheets and web forms, without needing special APIs. This release closes the performance gap with Anthropic's more expensive Opus models, offering near-Opus-level intelligence and outperforming Sonnet 4.5 on benchmarks such as OSWorld-Verified and Vending-Bench Arena. Early customer feedback highlights major improvements in code modifications, document comprehension, and frontend design. Notably, the model is less prone to overengineering and hallucinations, and it demonstrates strong reliability on multi-step, branched tasks. Safety evaluations indicate robust resistance to prompt injection attacks.\n\nAnthropic developed Sonnet 4.6 as a successor to Sonnet 4.5, building on its October 2024 introduction of general-purpose computer use in AI. The company continues to advance model capabilities while maintaining a focus on safety, aiming to expand the practical uses of AI for businesses and technical users globally.\n\nSource",
  "title": "Anthropic releases Claude Sonnet 4.6 with 1M context for all users",
  "updatedAt": "2026-02-17T21:54:57.000Z"
}