Name: Claude 4.5 Sonnet API
Brand: Anthropic

Overview

What is Claude 4.5 Sonnet API?

Claude 4.5 Sonnet offers a balance of intelligence and speed for diverse enterprise and coding tasks.

Technical Specifications
- Supported inputs: Text
- Output: Text
- Context window: 200,000 tokens / Max output: 64,000 tokens
- Endpoint: /chat/completions

Performance Benchmarks
[embed]

Claude 4.5 Sonnet API Pricing
- Input: $3.9 / 1M tokens
- Output: $19.5 / 1M tokens

Where to Use Claude 4.5 Sonnet

Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.

Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.

Code Sample
[embed]

Uptime and performance

Uptime (24h): 100%
Uptime (7d): 99.0%
Availability (24h): 100%
Error rate (24h): 0%
End-to-end latency (24h median): 4.7s
Throughput (24h median): 20.6 tok/s

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Claude Sonnet 4.5 is documented as suited to coding, including long-horizon software projects and everyday development tasks. It is also suited to computer use, such as browser-based work and other tasks that involve interacting with software interfaces. Anthropic and its cloud partners describe it as useful for agents and autonomous workflows, including long-running tasks that coordinate tools or multiple agents. It is additionally described as useful for research and financial analysis, including handling office files, monitoring regulatory changes, and producing actionable insights.

How to use Claude 4.5 Sonnet API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to anthropic/claude-sonnet-4.5.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "anthropic/claude-sonnet-4.5",
      "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-sonnet-4.5",
    "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-sonnet-4.5","messages":[{"role":"user","content":"Hello!"}]}'

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