Claude Mythos 5

Anthropic's access-gated frontier model for approved Project Glasswing cybersecurity defenders and biomedical research organizations. Shares the same underlying architecture as Claude Fable 5 but operates with safety classifiers lifted in specific domains: cybersecurity safeguards are removed for all Glasswing participants, while biology safeguards are additionally removed for approved biology-track participants. Succeeds Claude Mythos Preview with significantly reduced pricing ($10/$50 per MTok input/output vs. $25/$125 for Mythos Preview), a 1M-token context window, 128k max output tokens, adaptive thinking always on (raw chain of thought never returned), vision, tool use, structured outputs, and the effort parameter for controlling thinking depth. Extended thinking with manual budget_tokens is not supported. Anthropic disabled Mythos 5 access for all customers on June 12, 2026 after a US export control directive. On June 27, 2026, the US Commerce Department partially lifted the restriction, permitting Mythos 5 deployment to approximately 100+ US organizations listed in government Annex A that operate and defend critical infrastructure. The model remains inaccessible to general commercial API customers as of June 28, 2026.

Claude Mythos 5 is a proprietary model in the Claude Mythos family. The structured metadata tracks a 1m-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Anthropic, AWS Bedrock, and GCP Vertex AI, with the cheapest tracked route listed at $10 input and $50 output per 1M tokens. Headline tracked benchmarks include Terminal-Bench 2.1 88.0 and Humanity's Last Exam 64.5.