Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios. Read more at the [blog post here](https://www.anthropic.com/news/claude-4)
curl -X POST https://api.neuralhub.xyz/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "anthropic/claude-sonnet-4",
"messages": [
{ "role": "system", "content": "You are a helpful assistant." },
{ "role": "user", "content": "" }
],
"temperature": 0.7,
"max_tokens": 500,
"top_p": 0.9
}'{
"id": "chatcmpl-<uuid>",
"object": "chat.completion",
"created": 1768831129,
"model": "anthropic/claude-sonnet-4",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The answer to life, the universe, and everything is famously 42..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 26,
"completion_tokens": 169,
"total_tokens": 195
}
}