← All Models
Claude Opus 5
Anthropic's flagship for complex agentic coding and enterprise work. Step-change gains in deep reasoning, long-horizon tasks, and test-time compute scaling, with a 1M token context window and thinking on by default.
Web Search
Code Execution
Specifications
| Provider | Anthropic |
| Category | Text |
| Context window | 1M tokens |
Pricing (Starter tier)
650.00 credits / 1M input tokens
3,250.00 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","messages":[{"role":"user","content":"Implement this feature end-to-end and add tests"}],"max_tokens":2048,"stream":true}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt |
string | required | — | The input text prompt |
system_prompt |
string | optional | — | System instructions for the model |
max_tokens |
number | optional | 128000 |
Maximum tokens to generate (defaults to the model max, 128k, if omitted) |
effort |
string | optional | high |
Reasoning/token effort: low, medium, high, xhigh, or max |
image_url |
string | optional | — | URL of an image to analyze |
tools |
array | optional | — | Builtin tools: web_search, code_execution. code_execution must be paired with web_search (standalone is rejected); web_fetch is not available on Opus 5 |