import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "anthropic/claude-opus-4", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "anthropic/claude-opus-4", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"anthropic/claude-opus-4","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Claude Opus 4 has documented prompt-caching pricing: 5-minute cache writes cost 1.25× base input pricing, 1-hour cache writes cost 2× base input pricing, and cache hits/refreshes are billed at a lower rate.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 20.6 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Math | 73.3 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Claude Opus 4 This page | Agentic workflows and structured output |
Claude Opus 4 has a 200,000 tokens context window and can return up to 32,000 tokens.
Claude Opus 4 takes image, text as input and returns text.
Use anthropic/claude-opus-4 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Claude Opus 4 became available on May 22, 2025.
Claude Opus 4 is priced at input $20.631 / 1M tokens, output $103.155 / 1M tokens, cached input $2.0631 / 1M tokens.
Yes, Claude Opus 4 can stream responses as they are generated.
Yes, Claude Opus 4 accepts image input alongside text.
Claude Opus 4 was built by Anthropic.
The specifications provided cover Claude Opus 4 only, not Claude Sonnet 4, so no comparison can be given.
It supports reasoning, vision, file input, web search, and tool use, making it suitable for tasks involving text, images, and multi-step tool-assisted workflows.
Yes, it supports parallel tool calls along with structured output formatting.