Claude Opus 4.1 API

Claude 4.1 Opus is an enhanced version of Claude 4 Opus with improved reasoning and instruction-following capabilities.
Context
200K tokens
Input
$19.5 / 1M
Output
$97.5 / 1M

How to use Claude Opus 4.1 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to anthropic/claude-opus-4.1.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "anthropic/claude-opus-4.1",
      "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-4.1",
    "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-4.1","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Claude Opus 4.1 API Pricing

TypePrice
Input
$19.5 / 1M tokens
Output
$97.5 / 1M tokens

Claude Opus 4.1 Benchmarks

BenchmarkScoreWhat it measures
Tau-bench
56%
Tool-use agents in realistic customer-service tasks
AIME 2025
78%
Competition mathematics (AIME), 2025
GPQA Diamond
80.9%
Google-proof graduate science questions (hardest subset)
SWE-bench Verified
74.5%
Resolving verified real GitHub issues

Claude Opus 4.1 vs other models

ModelInputOutputContextBest for
$19.5 / 1M
$97.5 / 1M
200K tokens
Chat + assistants
$6.5 / 1M
$39 / 1M
1.05M tokens
Reasoning + agents
$2.6 / 1M
$13 / 1M
1M tokens
Balanced coding + agents
$3.9 / 1M
$19.5 / 1M
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M
$3.9 / 1M
1.05M tokens
Reasoning + agents

Start building with Claude Opus 4.1

Get API Key
1000+ models, one API.