Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Balance
Subscription
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Text
  3. Anthropic

Claude Sonnet 5.5 Thinking

Claude Sonnet 5.5 with adaptive thinking for complex coding, multi-step tool use, visual analysis, and detailed planning. Supports a 1M-token context window and five reasoning effort levels, with stronger thinking available when a task needs it.

  • Reasoning
  • Vision
  • Native PDF input
  • Tool Calling
  • Structured Output

Added Sep 28, 2026

Pricing

Auto routing · per 1M tokens
Input
$2.00
Output
$10.00
Cache read
$0.10
Compare provider prices

Specifications

Context window
1M
Max output
128K
Avg output (7d)
1.8K tokens
Longer than 91% of models

Benchmarks

Sourced from LMArena.

Arena Score

1472.9

Overall Rank

#45 / 419

Votes

13,410

Confidence Interval

1466.7 - 1479.1

Category Scores

Coding

#33 / 414

3,190 votes

1521.3

Math

#32 / 404

637 votes

1488.0

Longer Query

#30 / 397

5,844 votes

1490.5

Creative Writing

#28 / 417

3,081 votes

1462.7

Instruction Following

#21 / 419

4,611 votes

1481.0

Hard Prompts

#36 / 419

8,410 votes

1498.8

Additional Categories
22

Chinese

#12 / 395

1,128 votes

1541.7

Industry Mathematical

#17 / 402

681 votes

1507.9

Polish

#23 / 244

211 votes

1491.6

Expert

#24 / 369

1,337 votes

1516.0

Industry Entertainment And Sports And Media

#27 / 417

3,546 votes

1454.8

Industry Writing And Literature And Language

#27 / 418

3,899 votes

1468.8

Hard Prompts English

#28 / 417

3,213 votes

1505.8

Japanese

#29 / 288

238 votes

1470.5

French

#30 / 301

503 votes

1497.1

English

#31 / 419

4,982 votes

1484.8

Industry Software And It Services

#33 / 419

4,696 votes

1512.0

Industry Life And Physical And Social Science

#34 / 417

2,248 votes

1493.1

Industry Legal And Government

#41 / 392

1,078 votes

1478.7

Industry Business And Management And Financial Operations

#42 / 412

2,260 votes

1471.1

Exclude Ties

#44 / 419

9,934 votes

1481.9

Non English

#49 / 419

8,428 votes

1457.0

Russian

#54 / 383

1,950 votes

1465.8

Industry Medicine And Healthcare

#61 / 390

939 votes

1478.8

Korean

#63 / 290

212 votes

1418.8

Multi Turn

#64 / 417

1,994 votes

1469.2

Spanish

#68 / 302

459 votes

1454.4

German

#72 / 320

215 votes

1452.7

Published 2026-11-06 · Matched as Claude Sonnet 5.5 (xHigh)

LMArena Dataset

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Cache write /M
Auto
Auto
Recommended
$2.00$10.00$0.10$2.50N/AN/A
Batch API
ProviderInputOutputCached inputCache write
Anthropic
Anthropicclaude-sonnet-5-5-thinking
$1.00/M$5.00/M$0.05/M$1.25/M

Reliability

Related text models

Compare Claude Sonnet 5.5 Thinking with similar models from the same provider or model family.

Claude Sonnet 5.5

anthropic/claude-sonnet-5.5

Claude Sonnet 5.5 handles everyday coding, tool-based workflows, visual analysis, and polished writing with a 1M-token context window. This version skips up-front thinking and can reason between tool calls for faster responses; use Thinking for deeper planning and complex problems.

Claude Sonnet 5

anthropic/claude-sonnet-5

Claude Sonnet 5 supports coding, agentic workflows, long-context reasoning, computer use, and practical knowledge work.

Claude Sonnet 5 Thinking

anthropic/claude-sonnet-5:thinking

Claude Sonnet 5 with adaptive thinking enabled for complex coding, planning, and agentic work.

Claude Sonnet Latest

anthropic/claude-sonnet-latest

Compatibility alias that routes to the newest version of Claude Sonnet. Currently routes to Claude Sonnet 5.5 Thinking.

Claude Sonnet 4.6

anthropic/claude-sonnet-4.6

Claude Sonnet 4.6 is Anthropic's most capable Sonnet yet — a full upgrade across coding, computer use, long-context reasoning, agent planning, and design. Supports up to a 1M-token context window at Sonnet pricing.

Claude Sonnet 4.6 Thinking

anthropic/claude-sonnet-4.6:thinking

Claude Sonnet 4.6 with extended thinking enabled for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows and complex problem solving.