Claude Sonnet 4.5 API pricing

What does Claude Sonnet 4.5 cost per request?

A typical request of 5,000 input tokens and 1,500 output tokens costs about $0.037 at list price. A thousand of those requests costs about $37.50.

Model usage is drawn from your balance at the upstream list price of each model. Figures above are indicative and exclude any plan fee; the console is the source of truth for live pricing.

Where Claude Sonnet 4.5 fits

Claude Sonnet 4.5 sits in the middle of the Anthropic range at $3.00 per 1M input tokens, and it is the model most Claude Code users keep as their default.

Pick it when

• You are running an Anthropic-style coding agent and want one model for both planning and editing.
• You want stronger instruction-following on long documents than a small model gives you, without Opus pricing.
• Your workload mixes chat, code and tool calls, and you would rather not split models by task type.

What to watch

• At $15.00 per 1M output tokens it costs five times what GPT-5 mini costs, so it rewards workloads with short answers.
• The 200K context window is smaller than the 400K and 1M windows elsewhere in the catalogue, so very large inputs need chunking or a different model.

Best for: Claude Code sessions, long-document editing and tool-calling agents that need reliable instruction following.

How to call Claude Sonnet 4.5 through the gateway

Point your client at https://api.quickrouter.homes/v1 with a QuickRouter key and pass claude-sonnet-4-5 as the model name. Nothing else in an OpenAI-style client changes.

curl https://api.quickrouter.homes/v1/chat/completions \
  -H "Authorization: Bearer sk-qr-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

The console lists the model ids your key can reach - use the id exactly as it appears there.