About Claude Opus 5
Claude Opus 5 is Anthropic's Opus-tier Multimodal LLM for complex agentic coding and enterprise work. It is strongest on deep reasoning, long-horizon agentic tasks, and work that benefits from more thinking at higher effort, and it is a drop-in upgrade for Claude Opus 4.8 at the same price. Claude Opus 5.5 has since succeeded it at a lower price.
Adaptive thinking is on by default and steered by the effort parameter (low through max, default high); the raw chain of thought is never returned. Sampling parameters such as temperature are not supported. Safety classifiers may decline requests in sensitive domains such as cybersecurity, returning a refusal stop reason. It accepts text and images and has a reliable knowledge cutoff of May 2026.
| Metric | Value |
|---|---|
| Context Length | 1,000,000 tokens |
| Max Output | 128,000 tokens |
| Multilingual | Yes |
Ready to build with Claude Opus 5?
Try Claude Opus 5 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "claude-opus-5",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'API endpoint
See the API reference for request and response formats.
https://hub.oxen.ai/api/ai/chat/completions