Claude Opus 5.5 (batch)

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up. The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

ChatAnthropic1M tokens$2.1801 / $10.9006 · 1M

anthropic/claude-opus-5.5:batch

Context
1M tokens
Completion cap
128,000
Tools
Yes
JSON
Yes
Released
2026-09-22

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-5.5:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Claude Opus 5.5 (batch)?
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up. The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads. Claude Opus 5.5 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: anthropic/claude-opus-5.5:batch.
Is Claude Opus 5.5 (batch) free?
No. Input is $2.1801 per 1M tokens and output is $10.9006 per 1M tokens on Geek Hub (markup included).
What is the context length of Claude Opus 5.5 (batch)?
Claude Opus 5.5 (batch) has a 1M tokens context window. It supports up to 128,000 completion tokens.
Does Claude Opus 5.5 (batch) support tool calling and structured outputs?
Claude Opus 5.5 (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Claude Opus 5.5 (batch) released?
Claude Opus 5.5 (batch) was released on 2026-09-22.

More models from Anthropic