HomeVastLLM Catalog › Claude Sonnet 4.5

Claude Sonnet 4.5

by Anthropic · Language Models

Context 200K tokens

Overview

Claude Sonnet 4.5 is an Anthropic model released September 2025, positioned at launch as among the best in the world for real-world agents, coding and computer use. It was state-of-the-art on SWE-bench Verified and was observed maintaining focus for more than 30 hours on complex, multi-step tasks. It launched alongside the Claude Agent SDK, giving developers the building blocks behind Claude Code, at $3 per million input and $15 per million output tokens. Best for long-duration autonomous agents, coding, finance and cybersecurity workloads.

Context window200K tokens
Max output66K tokens
Input → Outputtext, image → text

Pricing

$3.885 in · $19.425 out / 1M

UsageRate (USD)Unit
Input tokens$3.88per 1M tokens
Cached input (cache hit)$0.39per 1M tokens
Output tokens$19.43per 1M tokens

TuneRouter live platform pricing · currency: USD · pre-deduction settled by actual usage

Call it in 30 seconds

OpenAI-compatible · base URL https://api.tunerouter.com/v1/

POST/chat/completions
curl https://api.tunerouter.com/v1/chat/completions \
  -H "Authorization: Bearer $TUNEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-4-5-20250929", "messages": [{"role": "user", "content": "Hello!"}]}'

Model ID: claude-sonnet-4-5-20250929 · works with OpenAI SDKs — just point base_url at api.tunerouter.com

More from Anthropic

← Back to full catalog (101 models)