Fast responses

Claude Sonnet 5 API

Lowest latency for high-volume tasks: classification, extraction, summaries and simple chat.

Try in chat Open playground

1M context
33K max output
All plans

Specifications

Model ID: claude-sonnet-5
Context window: 1M tokens
Max output: 33K tokens
Availability: All plans
Released: Sep 2026

Streaming
Reasoning
Vision
Tool use
JSON mode

Pricing

Input / 1M: $0.50
Cached input / 1M: $0.010
Output / 1M: $1.90

A request with 10,000 input tokens and 1,000 output tokens costs $0.0069. Repeated prompt prefixes are billed at the cached rate.

Paid from a prepaid balance. See pricing, the cost calculator and price comparison.

API

Call Claude Sonnet 5

The same key works in both request formats. API access unlocks after your first purchase.

OpenAI format

POST /v1/chat/completions

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

Anthropic format

POST /v1/messages

curl https://api.claudech.com/v1/messages \
  -H "x-api-key: $CLAUDECH_API_KEY" \
  -H "anthropic-version: 2026-10-04" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'