LLM Reference
Anthropic

Using Claude Mythos 5 on Anthropic

Implementation guide · Claude Mythos · Anthropic

Serverless

Anthropic exposes Claude Mythos 5 through model ID claude-mythos-5. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-26. Next refresh: weekly.

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

Install
pip install anthropic
API key
ANTHROPIC_API_KEY
Model ID
claude-mythos-5

Use the versioned model ID, e.g. "claude-sonnet-4-6" or "claude-opus-4-7-20251101".

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)

Pricing on Anthropic

TypePrice (per 1M)
Input tokens$10.00
Output tokens$50.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode Execution

About 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.

Model Specs

Released2026-06-09
Context1m
ArchitectureDecoder Only

Provider

Anthropic
Anthropic

San Francisco, California, United States