Anthropic / anthropic/claude-opus-5.5
Claude Opus 5.5 - access through LLMTR
Claude Opus 5.5 is Anthropic's current Opus model for long-running agentic coding, codebase-wide migrations, code review, and enterprise knowledge work. It offers a 1M context window, 128K max output, always-on adaptive thinking, vision input, tool calling, and prompt caching. Effort is configurable from low through max and defaults to medium. Prices are lower than Opus 5, and cache reads cost one twentieth of the input price.
Technical specifications
| Canonical ID | anthropic/claude-opus-5.5 |
|---|---|
| Provider | Anthropic |
| Context window | 1,000,000 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $4.00 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.200000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $20.00 |
| CHAT_COMPLETIONS | CACHE_WRITE | PER_1M_TOKENS | $5.00 |
| CHAT_COMPLETIONS | CACHE_WRITE | PER_1M_TOKENS | $8.00 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"anthropic/claude-opus-5.5","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Claude Opus 5 5-minute and 1-hour cache-write prices: which one pays off when - Claude Opus 5's pricing card carries two separate cache-write prices: a 5-minute and a 1-hour TTL. This article explains the difference, how to send the marker through LLMTR, and, with a worked example, which TTL pays off given the time between your requests.
- Claude Fable 5: reading the model page's three-way decision tree - Claude Fable 5's model page does something rare: it directly compares two alternatives (5.1 and Opus 5.5) with concrete numbers. This article unpacks this three-way decision tree and covers when each branch is correct.
Related models
- Claude Fable 5.1 anthropic/claude-fable-5.1
- Claude Fable 5 anthropic/claude-fable-5
- Claude Opus 5 anthropic/claude-opus-5
- Claude Opus 4.8 anthropic/claude-opus-4.8
- Claude Opus 4.7 anthropic/claude-opus-4.7
- Claude Opus 4.6 anthropic/claude-opus-4.6
- Claude Opus 4.5 anthropic/claude-opus-4.5
- Claude Sonnet 5 anthropic/claude-sonnet-5