Claude Sonnet 5.5

anthropicanthropic/claude-sonnet-5-5

Anthropic's Sonnet-tier model released 2026-09-28 — successor to Claude Sonnet 5 with adaptive thinking and effort control; 1M context, 128K output.

Claude Sonnet 5.5 model page ↗What's new in Claude Sonnet 5.5 ↗Claude pricing documentation ↗

Claude Sonnet 5.5 is Anthropic's Sonnet-tier model released on 2026-09-28, the successor to Claude Sonnet 5. Anthropic describes it as "the best combination of speed and intelligence". In TheRouter it is cataloged as anthropic/claude-sonnet-5-5, with text and image input, text output, a 1M-token context window and up to 128K output tokens.

The list price is the same as Claude Sonnet 5 ($2 / $10 per million input / output tokens), but the API contract is not: Anthropic lists five breaking changes for code already running on Sonnet 5. The two that most often break existing clients are that forced tool use (tool_choice any / tool) returns a 400, and that setting temperature, top_p or top_k to a non-default value returns a 400.

Best for

• Production coding and agent traffic that wants the newest Sonnet at the same list price as Sonnet 5
• Long-context work up to 1M tokens, billed at the standard rate across the whole window

Reach for something else if

• Clients that force tool calls with tool_choice: any / tool (or OpenAI required / a named function) — these return a 400; keep auto and use strict tool use, or stay on Claude Sonnet 5 until migrated
• Latency- and cost-sensitive simple chat — route to Claude Haiku 4.5

Context Length

Max Output

128K

Input Priceper 1M tokens

$2.16/ 1M tokens

Output Priceper 1M tokens

$10.80/ 1M tokens

Modalities

textimage→text

Capabilities

Vision

Pricing Breakdown

Type	Rate
Input	$2.16 / 1M tokens
Output	$10.80 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatreasoningstop

Specifications

Release date	2026-09-28platform.claude.com ↗	verified
Anthropic model id	claude-sonnet-5-5platform.claude.com ↗	verified
Context window	1,000,000 tokensplatform.claude.com ↗	verified
Maximum output	128,000 tokensplatform.claude.com ↗	verified
Reliable knowledge cutoff	June 2026platform.claude.com ↗	verified
License	Anthropic Usage Policy (proprietary, API-only)www.anthropic.com ↗	verified
Pricing (input / output)	$2 / $10 per MTok list price; cache read $0.20, 5-minute cache write $2.50, 1-hour cache write $4platform.claude.com ↗	verified

Benchmarks

Benchmark	Distribution	Score	Source
Official benchmark table The cited model documentation publishes no benchmark table at curation time.	—	Not publicly disclosed	—

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

cURL

curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "anthropic/claude-sonnet-5-5",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'

API guide

Chat completion

Use the OpenAI-compatible chat completions endpoint. Leave temperature and top_p unset.

cURL

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

More from anthropic

anthropic/claude-sonnet-5Predecessor model anthropic/claude-fable-5-1Higher-capability Claude route for demanding reasoning anthropic/claude-haiku-4.5Faster, cheaper Claude route

Similar models

Cross-provider sibling models

openai/gpt-5.6-sol

Comparable general-purpose reasoning route

News & changes

2026-09-28

Anthropic releases Claude Sonnet 5.5

Successor to Claude Sonnet 5 at the same $2 / $10 list price, with a 1M-token context window, 128K output, adaptive thinking on by default, and five breaking API changes including no forced tool use.

re-authored by TheRouterplatform.claude.com ↗

Frequently asked

Can I keep sending temperature or top_p to Claude Sonnet 5.5?

Anthropic returns a 400 when temperature, top_p or top_k is set to a non-default value for this model. Leave them unset.

re-authored by TheRouter

Does Claude Sonnet 5.5 support tool_choice: any or tool_choice: tool?

No. Anthropic rejects both with a 400, and TheRouter rejects them before any upstream call. Use tool_choice: auto with strict tool use, or structured outputs.