Using Claude Mythos 5 on Anthropic

Quick Start

1. 1
   Create an account at Anthropic and generate an API key.
2. 2
   Use the Anthropic SDK or REST API to call claude-mythos-5 — see the documentation for request format.
3. 3
   You'll be billed $10.00/1M input, $50.00/1M output tokens. See full pricing.

Code Examples

import anthropic

client = anthropic.Anthropic()  # reads ANTHROPIC_API_KEY from env
message = client.messages.create(
    model="claude-mythos-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)
print(message.content[0].text)

About Anthropic

Creator of Claude AI models, accessed via the Anthropic API and the Anthropic Console (console.anthropic.com). The Console hosts the Workbench prompt playground, API keys, usage analytics, and team billing.

Anthropic is a safety-focused AI research company and creator of the Claude model family, offering API access through the Anthropic Console for text generation, analysis, and coding tasks.

Pricing on Anthropic

Capabilities

About Claude Mythos 5

Anthropic's access-gated frontier model, available exclusively through Project Glasswing to approved 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. For general-availability access to Mythos-class capability, see Claude Fable 5.