Skip to content
Anthropicclaude-opus-4-8

Claude Opus 4.8

Anthropic's flagship for hard, long-running work.

Opus 4.8 is built for the toughest coding, reasoning, and agentic tasks — the work you reach for when quality matters more than anything else.

Complex codingAgentsDeep reasoning

Specs

Context window1M tokens
Max output128K tokens
InterfaceOpenAI-style Chat Completions · Anthropic-style Messages
Price / 1M$3.75 / $18.75was $5 / $25

Capabilities

  • ReasoningSupported
  • VisionSupported
  • Tool callingSupported
  • StreamingSupported
  • JSON output

Why teams pick it

  • State-of-the-art coding and multi-step reasoning
  • Handles long, tool-heavy agent runs without losing the thread
  • 1M-token context for whole-repo and long-document work

Call Claude Opus 4.8

Claude Opus 4.8 answers on either API below — pick the one your code already speaks and just swap in your Inferray key.

/v1/chat/completions · OpenAI-style Chat Completions · openai SDK or plain HTTP

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "messages": [{"role": "user", "content": "ship it"}]
  }'

/v1/messages · Anthropic-style Messages · @anthropic-ai/sdk SDK or plain HTTP

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "ship it"}]
  }'

More from Anthropic