Claude-Sonnet-4 API

Q: What is the Claude-Sonnet-4 model ID?

Use anthropic/claude-sonnet-4 as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Try this model

Claude Sonnet 4 excels in coding, reasoning, and analytics. Anthropic’s model offers precise API solutions for developers and enterprises.

Modalities: Image, TextText
In / Out price: $3.17/$15.87per 1M
Context window: 1M tokens
Released: May 22, 2025

Claude-Sonnet-4 overview

Claude-Sonnet-4 by Anthropic

Anthropic’s Claude Sonnet 4 is a precise AI model for coding and reasoning. With a 200K-token context window, it excels in software development.

Claude-Sonnet-4 specs

Model ID: anthropic/claude-sonnet-4
Developer: Anthropic
Context window: 1,000,000 tokens
Max output: 64,000 tokens
Input: Image, Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Claude Sonnet 4 Description

Anthropic’s Claude Sonnet 4 is an efficient AI model for coding, reasoning, and analytics. With a 200K-token context window, it offers precise solutions.

Performance Benchmarks

Claude Sonnet 4 balances efficiency and performance for coding and reasoning.

Output Capacity: Up to 64K tokens per response.
Performance Benchmarks: SWE-bench: 72.7%, Terminal-bench: 35.5%.

Key Capabilities

Claude Sonnet 4 delivers reliable outputs for diverse workflows.

Advanced Coding: Excels in code reviews, bug fixes, and multi-file edits.
Advanced Reasoning: Strong in multi-step reasoning for analytics and problem-solving.
Tool Utilization: Supports function calling and JSON structuring for API automation.
API Features: Provides streaming and function calling for scalable applications.

Optimal Use Cases

Coding: Code reviews, bug fixes, and multi-file code edits.
Data Analysis: Processing business datasets.
Business Automation: Streamlining workflows with API integration.
Complex Problem-Solving: Tackling multi-step reasoning tasks.

Comparison with Other Models

Vs. Gemini 2.5 Flash: Superior coding accuracy (72.7% vs. 63.8% SWE-bench), ideal for software development.
Vs. OpenAI o3-mini: Stronger coding performance (72.7% vs. 69.1% SWE-bench), better for efficient coding tasks.
Vs. Qwen3-235B-A22B: Higher coding precision (72.7% vs. ~60% SWE-bench, estimated), optimized for code efficiency.

API Integration

Accessible via AI/ML API Documentation: available here.

Use cases

Autonomous coding and large software development projects
Customer support and enterprise AI agents
Research and long-form document analysis
AI-powered writing and content creation
Interactive AI assistants with enhanced memory and tool capabilities

Capabilities

File input
Reasoning
Streaming
Vision
Web search

Claude-Sonnet-4 benchmarks by Artificial Analysis

See how Claude-Sonnet-4 scores on independent evaluations. Data retrieved Nov 3, 2026.

Humanity's Last Exam#211 / 45810.7%Score GPQA Diamond#153 / 43977.7%Score AA-LCR#139 / 39170.3%Score IFBench#121 / 32554.7%Score

Benchmark results

Compare 16 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Claude-Sonnet-4 API pricing

Claude-Sonnet-4 pricing in US dollars
Usage	Price	Unit
Input	$3.17	1M tokens
Output	$15.87	1M tokens
Cached input	$0.3174	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Claude-Sonnet-4 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Claude-Sonnet-4	$3.17	$15.87
Claude Haiku 5.5	$0.1	$0.5
Claude Sonnet 5.5	$2	$10
Claude Opus 5.5	$4	$20
Claude Fable 5.1	$10	$50

How to use the Claude-Sonnet-4 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "anthropic/claude-sonnet-4",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "anthropic/claude-sonnet-4",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Claude-Sonnet-4 FAQ

How much does Claude-Sonnet-4 cost?

Claude-Sonnet-4 costs $3.17 input and $15.87 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Claude-Sonnet-4 support streaming?

Yes, Claude-Sonnet-4 can stream responses as they are generated.

Does Claude-Sonnet-4 support tool calling and structured outputs?

Yes, Claude-Sonnet-4 supports both function calling and structured outputs.

Who created Claude-Sonnet-4?

Claude-Sonnet-4 was built by Anthropic.

Can Claude-Sonnet-4 perform web searches?

Yes, Claude-Sonnet-4 includes web search capability.

What is the Claude-Sonnet-4 model ID?

Use anthropic/claude-sonnet-4 as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

What is the context window of Claude-Sonnet-4?

Claude-Sonnet-4 accepts up to 1,000,000 tokens of context and returns up to 64,000 output tokens.

Start building with Claude-Sonnet-4

Get API key

Claude-Sonnet-4 API

anthropic/claude-sonnet-4

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "anthropic/claude-sonnet-4",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "anthropic/claude-sonnet-4",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = 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",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Claude-Sonnet-4 API

Claude-Sonnet-4 overview

Claude-Sonnet-4 by Anthropic

Claude-Sonnet-4 specs

Claude Sonnet 4 Description

Performance Benchmarks

Key Capabilities

Optimal Use Cases

Comparison with Other Models

API Integration

Use cases

Capabilities

Claude-Sonnet-4 benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Claude-Sonnet-4 API pricing

Claude-Sonnet-4 vs other models: token prices

How to use the Claude-Sonnet-4 API

Build with your agent

1Get your API key

2Make your first request

Related articles

Claude-Sonnet-4 FAQ

Start building with Claude-Sonnet-4

Claude-Sonnet-4 API

Build with your agent

1Get your API key

2Make your first request

Claude-Sonnet-4 API

Claude-Sonnet-4 overview

Claude-Sonnet-4 by Anthropic

Claude-Sonnet-4 specs

Claude Sonnet 4 Description

Performance Benchmarks

Key Capabilities

Optimal Use Cases

Comparison with Other Models

API Integration

Use cases

Capabilities

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Claude-Sonnet-4 API pricing

Claude-Sonnet-4 vs other models: token prices

How to use the Claude-Sonnet-4 API

Build with your agent

1Get your API key

2Make your first request

Models similar to Claude-Sonnet-4

Claude Haiku 5.5

Claude Sonnet 5.5

Claude Opus 5.5

Aion-3.0

Aion-3.5

Ember-1

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Claude-Sonnet-4 FAQ

Start building with Claude-Sonnet-4