Post-Cutoff
Search For AI agents

AnthropicClaude 5 familyCurrentReasoning modelReleased 28 Sep 2026

Claude Sonnet 5.5

Everyday coding, agents and enterprise workloads at Sonnet pricing; successor to Claude Sonnet 5 at the same price.

Model idclaude-sonnet-5-5

Price$2 in, $10 out per 1M tokens

Checked8 October 2026

Knows up to June 2026

1,795events after its cutoff

81 historic, 409 major. 136 days of news.

It launched on 28 September 2026, already missing 470 of them.

Five things it has never heard of

How to call it

7 ways to use Claude Sonnet 5.5, with the model id each provider expects.

Providers, model ids, endpoints and docs for Claude Sonnet 5.5
ProviderModel idEndpointDocs
Anthropic API (Claude API) claude-sonnet-5-5 https://api.anthropic.com/v1/messages platform.claude.com
AWS Bedrock (Messages API / Mantle) anthropic.claude-sonnet-5-5 platform.claude.com
Google Cloud Vertex AI claude-sonnet-5-5 platform.claude.com
Microsoft Foundry (Azure) claude-sonnet-5-5 platform.claude.com
Claude Platform on AWS claude-sonnet-5-5 platform.claude.com
OpenRouter anthropic/claude-sonnet-5.5 openrouter.ai
Web app claude.ai

Pricing

Prices for Claude Sonnet 5.5
Input$2 per 1M tokens
Output$10 per 1M tokens
Cache read$0.10 per 1M tokens

As published: “per 1M tokens (USD); Batch API 50% off”.

Source: platform.claude.com, checked 8 October 2026.

Specs

Input
Text, images and PDF
Output
Text
Context window
1,000,000 tokens
Max output
128,000 tokens
Open weights
No
Licence
Proprietary
Training cutoff
June 2026
Released
28 September 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Opus-level knowledge work at Sonnet price

    Scores nearly level with Opus 5.5 on GDPval-AA (1844 vs 1846 Elo), at $2/$10 per MTok.

    Source: anthropic.com

  • Large agentic-coding jump

    Anthropic reports 70.6% on Terminal-Bench 4.0, up from 10.3% for Sonnet 5, and up to 30% lower cost per task.

    Source: anthropic.com

  • Beat Pokemon Red from screenshots

    First

    Anthropic says it is the first Sonnet model to finish Pokemon Red using only screenshots.

    Source: anthropic.com

  • between_tools thinking mode

    First

    New thinking type that turns off up-front thinking while still reasoning between tool calls; it replaces thinking: disabled.

    Source: platform.claude.com

  • Token efficiency

    A Balyasny test used 121k tokens per task, versus 497k for Sonnet 5.

    Source: anthropic.com

Four assistants, one scale

Claude Sonnet 5.5 is added as a fifth row. Each row runs from what the model knows (graphite) through the months between its cutoff and its launch (hatched) to today (pink).

  1. GPT-6 Astra 271 at launch, 1,863 today
  2. Claude Opus 5.5 372 at launch, 1,795 today
  3. Gemini 4 Hydrogen 1,863 at launch, 1,889 today
  4. Grok 4.7 387 at launch, 1,829 today
  5. Claude Sonnet 5.5 470 at launch, 1,795 today
Show as a table
ModelCutoffReleasedMissing at launchMissing today
GPT-6 AstraApril 20263 September 20262711,863
Claude Opus 5.5June 202622 September 20263721,795
Gemini 4 HydrogenMarch 202612 November 20261,8631,889
Grok 4.7May 202621 September 20263871,829
Claude Sonnet 5.5June 202628 September 20264701,795

Notes

Best speed/intelligence balance. Adaptive thinking on by default (effort default high); thinking {type: disabled} returns 400, use {type: between_tools} at effort high or below; forced tool_choice any/tool returns 400; non-default temperature/top_p/top_k return 400. Batch $1/$5. Cache-read price cut from $0.20 to $0.10 per MTok on Oct 7, 2026 (5% of base input).

curl https://api.anthropic.com/v1/messages \
 -H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" -H "content-type: application/json" \
 -d '{"model":"claude-sonnet-5-5","max_tokens":16000,"messages":[{"role":"user","content":"Hello"}]}'

Sources: