Models from Partners and Community

• Developed and supported by external partners and community contributors.
• Diverse range of specialized models catering to niche or broad use cases.
• Typically validated by providers themselves, with integration guidelines provided by Azure.
• Community-driven innovation and rapid availability of cutting-edge models.
• Standard Azure AI integration, with support and maintenance managed by the respective providers.

Key capabilities

About this model

Key model capabilities

• Adaptive thinking is an upgrade to extended thinking that gives Claude the freedom to think as much or as little as needed depending on the task and effort level.
• Image & text input: With strong vision capabilities, Claude Mythos Preview can process images and return text outputs to analyze and understand charts, graphs, technical diagrams, reports, and other visual assets.

Use cases

Key use cases

• Cybersecurity: Claude Mythos Preview is the world's best model for defensive security. It is capable of finding and suggesting fixes for real vulnerabilities in production codebases, then helping prove the fixes hold.
• Autonomous coding: Claude Mythos Preview is able to handle the full engineering cycle more effectively than any prior model. It investigates, implements, and tests across large codebases from objective to shipped.
• Long-running agents: Claude Mythos Preview sets a new bar for long-horizon agentic work. It can sustain coherent execution over extended, multi-hour tasks, adapting as conditions change and driving work forward with fewer interventions.

Out of scope use cases

Pricing

Technical specs

Training cut-off date

Input formats

Supported language

Supported Azure regions

Sample JSON response

Input

{"model":"claude-mythos-preview","max_tokens":4096,"messages":[{"role":"user","content":"Hi, who are you?"}]}

Output

200: {"model":"claude-mythos-preview","id":"msg_01XivxT7GeJ5C2rrJZP2174N","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"The user is asking a simple identity question. I should be clear, friendly, and concise. I'll introduce myself as Claude, mention I'm made by Anthropic, and briefly describe what I can do. I shouldn't be overly verbose for such a simple greeting.","signature":"<base64-encoded cryptographic signature>"},{"type":"text","text":"Hi there! I'm Claude, an AI assistant made by Anthropic. I'm here to help with a wide range of tasks—answering questions, writing, analysis, coding, brainstorming, math, and much more.\n\nWhat can I help you with today?"}],"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":69,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"iterations":[{"input_tokens":69,"output_tokens":185,"cache_read_input_tokens":0,"cache_creation_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"type":"message"}],"output_tokens":185,"service_tier":"standard","inference_geo":"global"}}

4XX: {"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: Field required"},"request_id":"req_011CZfRSX1xudxHbTnPvjSaQ"}

Model architecture

Long context

Optimizing model performance

Additional assets

• Claude Documentation : Visit Claude documentation for a wealth of resources on model capabilities, prompting techniques, use case guidelines, and more.
• Adaptive Thinking Guide : Understand how best to use extended thinking with Claude.
• Claude Prompting Resources : Check out Anthropic's prompting tools and guides to learn how to craft prompts that elicit more helpful, nuanced responses.
• Claude Cookbooks : Check out example code for a variety of complex tasks, such as RAG from various web sources, making SQL queries, function calling, multimodal prompting, and more.

Distribution channels

More information

Data handling