TheRouter.aiTheRouter.ai
·New Model·中文版本 →

Claude Sonnet 5 Is Now Available on TheRouter.ai

Anthropic released Claude Sonnet 5, and it's live on TheRouter today as anthropic/claude-sonnet-5 — a frontier Sonnet-tier model with a 1M-token context window at standard pricing, 128K max output, and introductory pricing that lands below Claude Sonnet 4.6. Same OpenAI-compatible endpoint, same API key.

Is Claude Sonnet 5 available? Yes — it is live on TheRouter as anthropic/claude-sonnet-5 with day-one routing and automatic failover. 1M context window billed at the standard per-token rate (no long-context surcharge), 128K max output, text and image input, reasoning support. Anthropic introductory API pricing is $2/$10 per million input/output tokens through August 31, 2026, reverting to $3/$15 afterward — cheaper than Sonnet 4.6 during the introductory period. Drop-in via a single OpenAI-compatible API key.

Why Sonnet 5 Matters

  • 1M context at standard pricing — the full million-token window is billed at the base per-token rate. A 900K-token request costs the same per token as a 9K one; no long-context surcharge.
  • Cheaper than Sonnet 4.6 — Anthropic's introductory pricing puts Sonnet 5 below the 4.6 tier for the launch window (see pricing below).
  • 128K max output + reasoning — long structured generations and extended-thinking workloads in one model.
  • Vision built in — text and image input, ready for screenshots, diagrams, and document workflows.
  • Resilient, multi-route delivery — TheRouter serves Sonnet 5 across multiple upstreams with automatic failover, so a single upstream hiccup doesn't take your traffic down.

Pricing

Anthropic is running introductory pricing for Sonnet 5 through August 31, 2026, after which the standard rate takes effect:

PeriodInputOutput
Introductory (through Aug 31, 2026)$2/MTok$10/MTok
Standard (from Sep 1, 2026)$3/MTok$15/MTok

For your exact billed rate on TheRouter, see the Sonnet 5 model page. Note: Sonnet 5 uses a newer tokenizer that can produce roughly 30% more tokens for the same text, so re-baseline cost dashboards before shifting production traffic.

How to Use It

Use the standard model name anthropic/claude-sonnet-5 — TheRouter handles provider selection and failover for you:

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THE_ROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [{"role": "user", "content": "Draft a migration plan for this service"}],
    "max_tokens": 4096
  }'

Getting Started

Already on TheRouter? Just set the model name to anthropic/claude-sonnet-5 — no other changes needed.

Start for freeView all models

Questions? Reach out on GitHub.

Help & contact