download dots

Anthropic · not tested yet

Claude Sonnet 5.5 in Taskade

Claude Sonnet 5.5 from Anthropic runs on Pro and up, with your own API key. We have not run TSK-1, our app-building test, on it yet.

Status
Own key
Plan
Pro and up, with your own API key (BYOK)
Where to pick it
Agent settings
Your own key
Anthropic
Context window
1Mtokens
Max output
128Ktokens
Released
Knowledge cutoff
Where it runs
7services

Published scores

Benchmark scores that Anthropic and test sites published for Claude Sonnet 5.5. Taskade did not re-run them. Lab-reported marks a score from Anthropic itself.

Published benchmark scores for Claude Sonnet 5.5, with sources
BenchmarkScore
Terminal-Benchv4.0 · AnthropicLab-reported70.6
OSWorldpartial score · v2.1 · AnthropicLab-reported80.1
Humanity's Last Examwith tools · AnthropicLab-reported64.5
More published scores (3)
Published benchmark scores for Claude Sonnet 5.5, with sources: More published scores (3)
BenchmarkScore
FrontierCodev1.1 · max effort · Main · AnthropicLab-reported46.2
CursorBenchv4.0 · AnthropicLab-reported55.5
GDPval-AAElo · v2.1 · AnthropicLab-reported1,844

LMArena scores

LMArena scores for Claude Sonnet 5.5
BenchmarkScore
WebDev arena±10 · 5,105 votes · Rank 6 of 145 · LMArena1,709

Scores from the LMArena leaderboard dataset (CC BY 4.0). People vote between two answers, and the votes set the score. Taskade picked the Overall category and the default setting of each model.

TSK-1, our own app-building test

Scores collected by models.dev (MIT). Each source links the page that published the score.

Versions tested

Not tested yet

See how other Anthropic models build apps

Model facts

The token limits are the most the model accepts. Taskade can run it with lower limits.

Last updated
Input types
Text, Images, PDF
Output types
Text
Reasoning
Yes
Tool calling
Yes
File attachments
Yes
Structured output
Yes
Open weights
No
Reasoning effort
LowMediumHighExtra highMax

Published specs from the model maker, via models.dev (MIT).

Run Claude Sonnet 5.5 with your own key

Pick it with your own key in a custom agent.

Key providers for Claude Sonnet 5.5, and the plan each one needs
Key providerPlan
AnthropicPro and up

Where it runs

Services outside Taskade that serve Claude Sonnet 5.5, from models.dev. Each link opens in a new tab. In Taskade, your own key works only through the key providers on this page.

How to choose Claude Sonnet 5.5

  1. Open the agent settings.
  2. Under AI Model, choose the model.
  3. Under Bring Your Own Key, add or select your provider key.

Claude in the docs

Compare Claude

Claude vs ChatGPTDeepSeek vs ClaudeGemini vs ClaudeGLM vs ClaudeGPT vs ClaudeGrok vs Claude

Other Anthropic models

Claude Haiku 4.5Claude Opus 5Claude Opus 5.5Claude Sonnet 5Claude Sonnet 4.5

FAQ

Which Taskade plans include Claude Sonnet 5.5?

Claude Sonnet 5.5 runs on Pro and up, with your own API key. Your provider bills the model use to your own account.

Has Taskade tested Claude Sonnet 5.5?

Not yet. Claude Sonnet 5.5 has no TSK-1 app test yet. The Claude results page shows how other Anthropic models build apps.

How do I choose Claude Sonnet 5.5 in Taskade?

Open the agent settings. Under AI Model, choose Claude Sonnet 5.5. Under Bring Your Own Key, select your provider key.

Can I use my own API key for Claude Sonnet 5.5?

Yes. In a custom agent, you can pick Claude Sonnet 5.5 with your own key from Anthropic (Pro and up). Your provider bills the model use to your own account.

Who makes Claude Sonnet 5.5?

Anthropic makes Claude Sonnet 5.5. Taskade runs it on Pro and up, with your own API key, beside frontier models from other top AI labs.