← All Models
Claude Opus 5.5
Anthropic's model for long-running agentic coding and knowledge work. Text and image input, 1M context, 128K output, always-on adaptive thinking, and medium default effort. Lower token and cache-read costs than Opus 5. Custom function tools are supported on Chat Completions and Messages endpoints; forced tool choice is not supported.
Web Search
Code Execution
Specifications
| Provider | Anthropic |
| Category | Text |
| Context window | 1M tokens |
Pricing (Starter tier)
520.00 credits / 1M input tokens
26.00 credits / 1M cached input tokens
650.00 credits / 1M cache-write tokens (5 minutes)
2,600.00 credits / 1M output tokens
Higher tiers get volume discounts. See tiers
Quick Start
curl -N https://query.genx.sh/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-opus-5-5","messages":[{"role":"user","content":"Review this function for bugs: function median(a) { a.sort(); return a[a.length / 2]; }"}],"max_tokens":8192,"reasoning_effort":"medium","stream":true}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt |
string | required | — | The input text prompt |
system_prompt |
string | optional | — | System instructions |
image_url |
string | optional | — | Image URL to analyze |
max_tokens |
number | optional | 128000 |
Maximum output tokens, including thinking, up to 128000 |
effort |
string | optional | medium |
low, medium, high, xhigh, or max. Thinking cannot be disabled. |
thinking |
object | optional | — | Omit or use type adaptive. display: omitted (default), summarized, or updates. |
tools |
array | optional | — | Built-in web_search and code_execution. Code execution requires web_search version 20260209 or newer alongside it. Queue sessions do not support custom function tools. |
Availability
Claude Opus 5.5 is available in the GenX Pro App and via the GenX Router API.