anthropic
Anthropic: Claude Sonnet 4.6
The Anthropic: Claude Sonnet 4.6 is a large language model that supports multiple input modalities, including text, image, and file inputs, with a context length of up to 1 million tokens. It also enables users to interact with tools and perform reasoning tasks. Those looking for a robust model with good benchmark performance may want to consider the Anthropic: Claude Sonnet 4.6. With a blended benchmark score of 71.3 across three independent benchmarks, it demonstrates strong capabilities in various tasks. However, its price point is relatively high, with $15 per million output tokens, which may not be suitable for all users or projects.
Quality Score
100/100
price + capability + benchmarks
Input Price
$3.00
per 1M tokens · checked 2026-09-23
Output Price
$15.00
per 1M tokens · checked 2026-09-23
Context Window
1,000,000
tokens
Benchmark results
Independent, published benchmarks. Blended score 69.7 across 3 benchmarks, last refreshed 2026-09-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| Aider Polyglot | code editing across languages | 61.3 |
| AI Index | broad capability composite | 49.6 |
| EQ-Bench | emotional understanding in dialogue | 80.0 |
- Model ID
- anthropic/claude-sonnet-4.6
- Vendor
- anthropic
- Released
- February 2026
- Tokenizer
- Claude
- Input Modalities
- text, image, file
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- yes
What it costs in practice
Computed from the current $3.00/M input and $15.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.11 |
| Classify 1,000 customer emails | 500k in / 50k out | $2.25 |
| A month of a busy support chatbot | 5M in / 2M out | $45.00 |
Strong choice for
Code
SQL Generation
Writing correct, performant SQL from natural-language prompts.
Code
Code Review
Spotting bugs, security issues, and style problems in pull requests.
Code
Code Refactoring
Safely restructuring an existing codebase across many files.
Code
Bug Fixing
Diagnosing root cause and producing a working patch.
Code
Unit Test Generation
Generating thorough test suites for existing functions.
Code
Code Documentation
Writing clear docstrings and READMEs that match the code.
Category rankings
Where Anthropic: Claude Sonnet 4.6 places across the 60 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #2 | Code RefactoringCode · of 25 ranked | 162 |
| #2 | Unit Test GenerationCode · of 25 ranked | 144 |
| #2 | CI/CD PipelinesCode · of 25 ranked | 138 |
| #2 | Frontend Component DesignCode · of 25 ranked | 137 |
| #2 | ETL ScriptingData · of 25 ranked | 150 |
| #2 | OCR / Document ParsingData · of 25 ranked | 140 |
| #2 | Table Extraction from PDFsData · of 25 ranked | 140 |
| #2 | Medical Note SummarizationProfessional · of 25 ranked | 150 |
| #2 | Physics TutoringEducation · of 25 ranked | 143 |
| #2 | History TutoringEducation · of 25 ranked | 145 |
| #2 | Meeting NotesBusiness · of 25 ranked | 147 |
| #2 | RFP ResponseBusiness · of 25 ranked | 168 |
| #2 | Screenshot DebuggingVision · of 25 ranked | 137 |
| #2 | Chart & Graph ReadingVision · of 25 ranked | 143 |
| #2 | RAG PipelinesAgents · of 25 ranked | 162 |
| #2 | Long-Context Q&AAgents · of 25 ranked | 157 |
| #3 | SQL GenerationCode · of 25 ranked | 154 |
| #3 | Code ReviewCode · of 25 ranked | 161 |
| #3 | Bug FixingCode · of 25 ranked | 166 |
| #3 | Code DocumentationCode · of 25 ranked | 142 |
| #3 | CSV / Spreadsheet CleanupData · of 25 ranked | 145 |
| #3 | Long-Document SummarizationWriting · of 25 ranked | 161 |
| #3 | Blog Post WritingWriting · of 25 ranked | 137 |
| #3 | Creative WritingWriting · of 25 ranked | 155 |
| #3 | Screenwriting & DialogWriting · of 25 ranked | 155 |
| #3 | Academic WritingWriting · of 25 ranked | 155 |
| #3 | Legal DraftingProfessional · of 25 ranked | 155 |
| #3 | Legal ResearchProfessional · of 25 ranked | 167 |
| #3 | Contract ReviewProfessional · of 25 ranked | 173 |
| #3 | Scientific ResearchProfessional · of 25 ranked | 167 |
| #3 | Essay GradingEducation · of 25 ranked | 161 |
| #3 | OKRs & Strategic PlanningBusiness · of 25 ranked | 155 |
| #3 | Agent WorkflowsAgents · of 25 ranked | 171 |
| #3 | Coding AgentsAgents · of 25 ranked | 171 |
| #3 | Character RoleplayPersonal · of 25 ranked | 149 |
| #3 | Fiction CollaboratorPersonal · of 25 ranked | 167 |
| #3 | Trip PlanningPersonal · of 25 ranked | 137 |
| #3 | Math ProofsResearch · of 25 ranked | 155 |
| #3 | Scientific CodingResearch · of 25 ranked | 166 |
| #3 | Literature ReviewResearch · of 25 ranked | 167 |
| #4 | Data AnalysisData · of 25 ranked | 147 |
| #4 | Financial AnalysisProfessional · of 25 ranked | 142 |
| #4 | Math TutoringEducation · of 25 ranked | 137 |
| #4 | Browser AutomationAgents · of 25 ranked | 147 |
| #4 | Fitness CoachingPersonal · of 25 ranked | 126 |
| #4 | Experiment DesignResearch · of 25 ranked | 143 |
| #5 | Marketing CopyWriting · of 25 ranked | 125 |
| #5 | Standardized Test PrepEducation · of 25 ranked | 125 |
| #6 | Diagram ExtractionVision · of 25 ranked | 138 |
| #8 | Regex WritingCode · of 25 ranked | 129 |
| #8 | Language TranslationWriting · of 25 ranked | 129 |
| #8 | Transcript CleanupWriting · of 25 ranked | 144 |
| #8 | Resume WritingBusiness · of 25 ranked | 114 |
| #8 | Tutoring for KidsPersonal · of 25 ranked | 129 |
| #9 | SOP / Process DocsBusiness · of 25 ranked | 126 |
| #11 | Function / Tool CallingAgents · of 25 ranked | 127 |
| #24 | Sales / Cold EmailBusiness · of 25 ranked | 118 |
| #24 | Job Application DraftingBusiness · of 25 ranked | 118 |
| #24 | Journaling HelperPersonal · of 25 ranked | 118 |
| #24 | Recipe GenerationPersonal · of 25 ranked | 118 |
Similar models
anthropic
Anthropic: Claude Opus 5.5 (batch)
$2.00 in / $10.00 out
1,000,000 ctx
100
anthropic
Anthropic: Claude Opus 5 (batch)
$2.50 in / $12.50 out
1,000,000 ctx
100
anthropic
Anthropic: Claude Sonnet 5
$2.00 in / $10.00 out
1,000,000 ctx
100
anthropic
Anthropic: Claude Sonnet 5 (batch)
$1.00 in / $5.00 out
1,000,000 ctx
100
anthropic
Anthropic: Claude Opus 4.8 (batch)
$2.50 in / $12.50 out
1,000,000 ctx
100
anthropic
Anthropic: Claude Opus 4.7 (batch)
$2.50 in / $12.50 out
1,000,000 ctx
100
Quick answers
- How much does Anthropic: Claude Sonnet 4.6 cost?
- $3.00 per million input tokens and $15.00 per million output tokens.
- What is Anthropic: Claude Sonnet 4.6's context window?
- 1,000,000 tokens, roughly 1,500 pages of text in a single request.
- Does Anthropic: Claude Sonnet 4.6 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Anthropic: Claude Sonnet 4.6 process images?
- Yes, it accepts image input.