Anthropic/claude-opus-4-7/Released Apr 2026

Claude Opus 4.7

Agentic coding, 1M-token context

Commercial use
Text

About Claude Opus 4.7

Claude Opus 4.7 is a Multimodal LLM designed for complex reasoning, enterprise agents, and agentic coding. It delivers a step-change improvement in agentic coding over Claude Opus 4.6 and ships with a native 1M-token context window at standard pricing.

Other noteworthy features of Claude Opus 4.7 include adaptive thinking that adjusts reasoning effort by task complexity, image processing, server-side context compaction for extended conversations, and computer use for multi-step workflows. Opus 4.7 uses a new tokenizer and does not support extended thinking.

MetricValue
Context Length1,000,000 tokens
Max Output128,000 tokens
MultilingualYes

Ready to build with Claude Opus 4.7?

Try Claude Opus 4.7 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-4-7",
  "messages": [
    {
      "role": "user",
      "content": "Try sending a message."
    }
  ]
}'

API endpoint

See the API reference for request and response formats.

POSThttps://hub.oxen.ai/api/ai/chat/completions