claude-opus-4-8
Claude Opus 4.8 is our most intelligent Opus model and the best generally available model for coding and agents, with deeper reasoning for enterprise workflows.
Anthropic
AnthropicVersion: 1
Claude Opus 4.8 is our most intelligent Opus model and the best generally available model for coding and agents, with deeper reasoning for enterprise workflows.
Please refer to the Claude Opus 4.8 System Card .
Training cut-off date
January 2026Input formats
Image & text input: With powerful vision capabilities, Claude Opus 4.8 can process images and return text outputs to analyze and understand charts, graphs, technical diagrams, reports, and other visual assets. Text output: Claude Opus 4.8 can output text of a variety of types and formats, such as prose, lists, Markdown tables, JSON, HTML, code in various programming languages, and more.Supported language
Claude Opus 4.8 can understand and output a wide variety of languages, such as English, French, Standard Arabic, Mandarin Chinese, Japanese, Korean, Spanish, and Hindi. Performance will vary based on how well-resourced the language is.Supported Azure regions
Global StandardSample JSON response
Input
{
"model": "claude-opus-4-8",
"max_tokens": 4096,
"messages": [
{
"role": "user",
"content": "Analyze this code for security vulnerabilities and suggest fixes."
}
]
}
Output
{
"content": [
{
"text": "I'll analyze this code for security vulnerabilities...",
"type": "text"
}
],
"id": "msg_example",
"model": "claude-opus-4-8",
"role": "assistant",
"stop_reason": "end_turn",
"type": "message",
"usage": {
"input_tokens": 42,
"output_tokens": 256
}
}
Model architecture
Please refer to the Claude Opus 4.8 System Card .Quick facts
Model providerAnthropic
TypeMessages
LifecycleGenerally available (GA)
Input typetext, image, code
Output typetext, image, code
Context window1000k
Token limits128k output
PricingView pricing