Anthropic Releases Claude Sonnet 5

ArticleAnthropicAnnouncement

Anthropic has launched Claude Sonnet 5, engineered for advanced agentic performance, tool use, and software development. The model closely approaches the performance of Opus 4.8 while operating at a permanent price of $2 per million input tokens and $10 per million output tokens.

Key points

  1. Sonnet 5 substantially improves upon Sonnet 4.6 in reasoning, tool use, and coding, nearing Opus 4.8 performance levels.
  2. Permanent pricing is set at $2 per million input tokens and $10 per million output tokens via the Claude API.
  3. Available across all user tiers—Free, Pro, Max, Team, and Enterprise—and supported in Claude Code, Cowork, and Chat.
  4. Evaluations on BrowseComp and OSWorld-Verified indicate performance matching Opus 4.8 on specific tasks when using higher effort levels.
  5. Safety audits report reduced rates of hallucinations, sycophancy, and misaligned behavior compared to Sonnet 4.6, backed by default cybersecurity safeguards.

Why it matters

For developers and enterprise teams running multi-step autonomous workflows, Sonnet 5 delivers frontier-grade agentic execution at a fraction of the cost of Opus-class models, making large-scale deployment practical.

Analysis

Sonnet 5 marks Anthropic's effort to democratise high-tier agentic execution. Early partner feedback highlights sustained debugging, root-cause fixes, and complete task follow-through without stalling. By combining adjustable effort levels with automated self-checking and robust safety filters, Anthropic establishes Sonnet 5 as an economical workhorse for agentic automation.

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Article:Anthropic

    Anthropic Introduces Claude Sonnet 4.5 and Claude Agent SDK

    Anthropic has released Claude Sonnet 4.5, delivering significant improvements in software engineering, multi-step agent reasoning, and autonomous computer use. The release is accompanied by developer tools including the Claude Agent SDK and checkpoints for Claude Code.

    AI & LLMs· Announcement

  • Link:Anthropic

    Anthropic Announces Claude Opus 5

    Anthropic has released Claude Opus 5, its flagship model designed for advanced software engineering, autonomous AI agents, and complex enterprise workflows. It introduces effort controls for variable compute depth and is accessible via the API, Claude subscriptions, and major cloud hyperscalers.

    AI & LLMs· Announcement

  • Article:Anthropic

    Anthropic Announces Claude Sonnet 4.6

    Anthropic has released Claude Sonnet 4.6, delivering upgrades across coding, computer use, agent planning, and long-context reasoning alongside a 1M token beta context window.

    AI & LLMs· Announcement

  • Article:Anthropic

    Anthropic Introduces Claude Opus 4.5

    Anthropic has released Claude Opus 4.5, positioning it as their leading model for coding, autonomous agents, and computer use, offered at an accessible price point of $5 per million input tokens and $25 per million output tokens.

    AI & LLMs· Announcement

  • Article:Anthropic

    Anthropic Introduces Claude Opus 4.8

    Anthropic has released Claude Opus 4.8, delivering across-the-board benchmark improvements for coding, reasoning, and agentic workflows at unchanged base pricing. The launch is accompanied by dynamic workflows in Claude Code and a granular effort control setting.

    AI & LLMs· Announcement

  • Link:Anthropic

    Anthropic Introduces Claude Fable 5.1

    Anthropic has released Claude Fable 5.1, designed for demanding software engineering tasks and multi-day agentic workflows with automatic fallbacks for sensitive domains.

    AI & LLMs· Announcement

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.