Skip to content
OpenKey

Claude Opus 4

AnthropicReleased May 22, 2025

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

Try in playground
Context window
200K tokens
Max output
32K tokens
Input
image, text, file
Output
text
Tokenizer
Claude
Knowledge cutoff
Jan 31, 2025
Released
May 22, 2025
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$15.00$0.450$15.45
Output$75.00$2.25$77.25
Cache read$1.50$0.045$1.54
Cache write$18.75$0.563$19.31

Benchmarks

Design Arena

CategoryEloWin rateRank
3Dmodels121657.7%#38
Codemodels121055.6%#49
Data vizmodels118957.9%#53
Game devmodels123659.9%#36
SVGmodels118557.7%#36
UI componentsmodels120959.2%#45
Websitesmodels120754.6%#51

Head-to-head preference voting. How we filter and rank

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • stop
  • temperature
  • tool_choice
  • tools
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model anthropic/claude-opus-4.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="anthropic/claude-opus-4",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "anthropic/claude-opus-4",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Claude Opus 4 cost via API?
Through OpenKey, Claude Opus 4 costs $15.45 per 1M input tokens and $77.25 per 1M output tokens. That is the provider price ($15.00 / $75.00) plus a flat 3% fee — nothing else.
What is Claude Opus 4's context window?
Claude Opus 4 accepts up to 200K tokens of context and returns up to 32K tokens per request.
Is Claude Opus 4 OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "anthropic/claude-opus-4" using any OpenAI SDK — only the base URL and API key change.
What inputs does Claude Opus 4 support?
Claude Opus 4 accepts image, text, file input and produces text output. Its knowledge cutoff is Jan 31, 2025.

More from Anthropic

All Anthropic models →