Claude Sonnet 5.5: price, context window and capabilities
Claude Sonnet 5.5 is a model from Anthropic (anthropic/claude-sonnet-5.5). It supports reasoning. It supports tool use. It costs $2.00 per million input tokens and $10.00 per million output tokens, with a 1M-token context window.
What it costs in practice
Using the listed prices: a chat turn of 2,000 input and 500 output tokens costs about $0.0090, so 10,000 such turns cost about $90.00. Summarising a 100,000-token document into 2,000 tokens costs about $0.220. A long agent run that reads 1 million tokens and writes 50,000 costs about $2.50.
How it compares
Among the 40 models we track, Claude Sonnet 5.5 ranks #29 by input price and #33 by output price (1 is cheapest), and #19 by context window (1 is largest). Models with the same tool and reasoning support that cost less per output token: DeepSeek V4 Pro 0423 ($0.418), Qwen3.8 Omni Flash ($0.470), Qwen3.8 Flash ($0.470), GPT-6 Luna Pro ($0.500). Models with a larger context window at the same or lower output price: Llama 4 Scout (1.3M), GPT-6.1 Sol Pro (1.1M), GPT-6.1 Sol (1.1M), GPT-6 Luna Pro (1.1M).
More from Anthropic
- Claude Opus 5.5: $4.00 in / $20.00 out, 1M context
- Claude Fable 5.1: $10.00 in / $50.00 out, 1M context
- Claude Opus 5: $5.00 in / $25.00 out, 1M context
In the news
- Anthropic Releases Claude Sonnet 5.5: Mid-Tier Speed, Frontier Agent Coding October 1, 2026
- Claude Sonnet 5.5 Arrives: Terminal-Bench at 70.6% and a Massive Free-Tier Upgrade September 29, 2026
Prices and limits come from OpenRouter's public model catalogue, last synced 4 Oct 2026. Provider pricing can differ from OpenRouter's and changes often; confirm on the provider's own page before you commit. See the guide to choosing a model or the full comparison.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.