Anthropic Python SDK v0.90.0 adds Claude Mythos preview support
Anthropic released version 0.90.0 of its Python SDK on April 7, 2026, adding support for the claude-mythos-preview model. The update also includes a bug fix for query parameter merging in the client.
Anthropic Python SDK v0.90.0 Adds Claude Mythos Preview Support
Anthropologic released version 0.90.0 of its Python SDK on April 7, 2026, introducing support for the claude-mythos-preview model and addressing a client-side bug.
What's New
Claude Mythos Preview Integration
The primary feature addition enables developers to call the claude-mythos-preview model through the Python SDK. This represents the first SDK-level support for the Mythos model variant, which Anthropic has not yet formally announced with full specifications or pricing.
Bug Fix
The update resolves an issue where hardcoded query parameters were not properly merged with user-provided parameters in the client. This fix ensures that internal SDK query parameters and custom user parameters can coexist without conflicts.
Technical Details
The release is a minor version bump (0.90.0 from 0.89.0), indicating backward compatibility. The change commits (fc7ddd8 and 32d35e0) are now available in the public repository.
What This Means
Developers using Anthropic's Python SDK can now integrate claude-mythos-preview into their applications, though details about the model's capabilities, context window, pricing, and performance benchmarks remain unavailable. The query parameter fix addresses a potential integration issue for users who rely on both SDK defaults and custom configurations. This SDK update typically precedes or accompanies formal model announcements, suggesting Mythos may receive broader availability soon.
Related Articles
Anthropic unveils Claude Mythos model, finds thousands of OS vulnerabilities via Project Glasswing
Anthropic has unveiled Claude Mythos, a new AI model designed for cybersecurity that has already discovered thousands of high-severity vulnerabilities in every major operating system and web browser. The model is being distributed as a preview to over 40 organizations and major technology partners including Apple, Google, Microsoft, and Amazon Web Services through Project Glasswing, a coordinated cybersecurity initiative.
Anthropic blocks Claude subscriptions for OpenClaw, citing capacity constraints
Anthropic has disallowed subscription-based pricing for users accessing Claude through open-source agentic tools like OpenClaw, effective April 4, 2026. The restriction comes as the company faces elevated service errors and struggles to balance capacity with demand. Third-party tool usage will now draw from pay-per-token rates instead of subscription limits.
Anthropic ends free Claude access through third-party tools like OpenClaw
Anthropic has ended free access to Claude through third-party applications like OpenClaw, effective April 4, 2025 at 3PM ET. Users of third-party tools integrating Claude must now purchase usage bundles or use an API key. The change stems from capacity constraints and usage patterns incompatible with subscription tiers.
Anthropic previews Mythos, claims it found thousands of zero-day vulnerabilities in cybersecurity initiative
Anthropic unveiled a preview of Mythos, a frontier model it claims is the most powerful in its Claude lineup, for use in Project Glasswing—a cybersecurity initiative with 40+ partner organizations. According to Anthropic, Mythos identified thousands of zero-day vulnerabilities, many critical and up to two decades old, during early testing. The model will not be made generally available and is restricted to defensive security work by vetted partners.
Comments
Loading...