Claude Sonnet 5.5
Claude Sonnet 5.5Rankingat max effort?
Full ranking →Alternatives?
CheaperGPT-6.1 Solmaxsame-87%$0.72Remove unsupported parameters+5
OpenDeepSeek V4 Pro 0813max-1%-88%$0.67No image input+6CheaperGPT-6 Solmaxsame-81%$1.04CheaperGPT-5.6 Solmaxsame-64%$1.99
CheaperGemini 4 Argonhighsame-64%*$1.99Synchronous output stops at 65,536+2GPT-6.1 Solmaxsame-87%$0.72Remove unsupported parameters+5GPT-6 Solmaxsame-81%$1.04GPT-5.6 Solmaxsame-64%$1.99Gemini 4 Argonhighsame-64%*$1.99Synchronous output stops at 65,536+2GPT-6 Astramaxsame-40%$3.26Monitoring can return HTTP 403+2DeepSeek V4 Pro 0813maxOpen-1%-88%$0.67No image input+6
Kimi K3maxOpen-3%-63%$2.00Sampling parameters are fixed+3Kimi K2.6unstatedOpen-4%-57%$0.95 / $4Context: 1M → 256KKimi K2.7 CodeunstatedOpen-4%-57%$0.95 / $4Context: 1M → 256K+1
GLM 5.3 FlashmaxOpen-6%-95%$0.28Defaults to max · Self-hosted+4Claude Opus 5.5maxsame+10%$5.98No forced tool use+5Claude Fable 5.1maxsame+40%$7.63Replace forced tool_choice+5Claude Fable 5maxsame+60%$8.75Claude Haiku 5.5xhigh-1%-98%$0.12Remove sampling parameters+5Claude Opus 5max-1%+7%$5.86Claude Opus 4.8max-2%-25%$4.08Claude Opus 4.6max-9%—$5 / $25Claude Opus 4.7max-13%—$5 / $25All Anthropic models →History
7 versionsBenchmarks
in Chat & KnowledgeWatch out 6
No forced tool use›
Forced tool_choice any or tool returns HTTP 400; remove the forced choice. Source ↗
Replace disabled thinking›
Disabled thinking returns HTTP 400; use between_tools for the lowest thinking setting. Source ↗
No manual thinking budgets›
Manual thinking budgets and extra between_tools fields return HTTP 400; remove manual budgets and send between_tools without display, budget_tokens or block_binding. Source ↗
Remove sampling parameters›
Non-default temperature, top_p or top_k returns HTTP 400; remove these parameters. Source ↗
No assistant prefill›
A prefilled final assistant turn returns HTTP 400; remove that prefill. Source ↗
Old computer tool rejected · Claude API / Google Cloud›
The computer_20251124 tool returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there. Source ↗
FAQ
How much does Claude Sonnet 5.5 cost?›
$2 per 1M input tokens and $10 per 1M output tokens; cached input $0.10 per 1M. A typical benchmark task costs about $5.46 at max effort.
Is Claude Sonnet 5.5 free to use?›
There is no free API; the cheapest paid price is $2 per 1M input tokens.
How good is Claude Sonnet 5.5, and what is it best at?›
#5 of 334 in Chat & Knowledge, #1 of 132 in Coding, #3 of 133 in Agents & Tool Use, #15 of 195 in Writing & Language, #9 of 133 in Vision & Documents. Strongest at: Coding, Agents & work tasks, Reasoning, Long context, Knowledge.
Is Claude Sonnet 5.5 better than Claude Sonnet 4.5?›
On OTIS Mock AIME 2024 2025, Claude Sonnet 5.5 scores 100 vs 35.6 — higher.
How can I use Claude Sonnet 5.5?›
Through the API of Amazon Bedrock, Anthropic, Azure, Claude Platform on AWS, DeepInfra and 1 more.
What is the context window of Claude Sonnet 5.5?›
1M tokens, with up to 128K output tokens.
When was Claude Sonnet 5.5 released? Is there a newer version?›
Released 2026-09-28. It is the current version in its line.
Is Claude Sonnet 5.5 open source?›
No, Claude Sonnet 5.5 is a closed model available through an API. The closest open-weights option here is DeepSeek V4 Pro 0813.
Can Claude Sonnet 5.5 read images?›
It accepts text and images, PDF files as input.
What is Claude Sonnet 5.5?›
Claude Sonnet 5.5 is a closed language model from Anthropic, released Sep 2026, the successor to Claude Sonnet 4.5.
What are the best alternatives to Claude Sonnet 5.5?›
GPT-6.1 Sol (cheaper), DeepSeek V4 Pro 0813 (open weights).