anthropic
Anthropic: Claude Sonnet 4.6
Claude Sonnet 4.6 by Anthropic is a versatile AI model capable of handling text, image, and file inputs with a context length of one million tokens. It supports reasoning and tools, making it adaptable for various tasks. While it offers structured output, this feature isn't detailed in the specifications. This model could be worth considering if you require a robust AI that can process multiple input modalities and integrate external tools; its blended benchmark score of 81.4 across five benchmarks indicates strong performance. However, with pricing at $3.0 per million input tokens and $15.0 per million output tokens, it may not be the most economical choice for everyone, especially those prioritizing cost-effectiveness.
Quality Score
100/100
price + capability + benchmarks
Input Price
$3.00
per 1M tokens
Output Price
$15.00
per 1M tokens
Context Window
1,000,000
tokens
Benchmark results
Independent, published benchmarks. Blended score 81.4 across 5 benchmarks, last refreshed 2026-08-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| Aider Polyglot | code editing across languages | 61.3 |
| AI Index | broad capability composite | 79.8 |
| AI Index Coding | software engineering tasks | 100.0 |
| AI Index Agentic | multi-step tool-using tasks | 69.4 |
| 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 ReviewCode · of 25 ranked | 185 |
| #2 | Code RefactoringCode · of 25 ranked | 181 |
| #2 | Unit Test GenerationCode · of 25 ranked | 167 |
| #2 | CI/CD PipelinesCode · of 25 ranked | 156 |
| #2 | Frontend Component DesignCode · of 25 ranked | 155 |
| #2 | ETL ScriptingData · of 25 ranked | 169 |
| #2 | OCR / Document ParsingData · of 25 ranked | 153 |
| #2 | Table Extraction from PDFsData · of 25 ranked | 153 |
| #2 | Creative WritingWriting · of 25 ranked | 173 |
| #2 | Screenwriting & DialogWriting · of 25 ranked | 173 |
| #2 | Academic WritingWriting · of 25 ranked | 173 |
| #2 | Legal DraftingProfessional · of 25 ranked | 173 |
| #2 | Legal ResearchProfessional · of 25 ranked | 186 |
| #2 | Financial AnalysisProfessional · of 25 ranked | 172 |
| #2 | Medical Note SummarizationProfessional · of 25 ranked | 169 |
| #2 | Scientific ResearchProfessional · of 25 ranked | 186 |
| #2 | Math TutoringEducation · of 25 ranked | 159 |
| #2 | Physics TutoringEducation · of 25 ranked | 161 |
| #2 | History TutoringEducation · of 25 ranked | 157 |
| #2 | Essay GradingEducation · of 25 ranked | 185 |
| #2 | Meeting NotesBusiness · of 25 ranked | 160 |
| #2 | RFP ResponseBusiness · of 25 ranked | 193 |
| #2 | OKRs & Strategic PlanningBusiness · of 25 ranked | 173 |
| #2 | Diagram ExtractionVision · of 25 ranked | 156 |
| #2 | Screenshot DebuggingVision · of 25 ranked | 149 |
| #2 | Chart & Graph ReadingVision · of 25 ranked | 161 |
| #2 | Browser AutomationAgents · of 25 ranked | 181 |
| #2 | Function / Tool CallingAgents · of 25 ranked | 160 |
| #2 | RAG PipelinesAgents · of 25 ranked | 181 |
| #2 | Long-Context Q&AAgents · of 25 ranked | 170 |
| #2 | Fiction CollaboratorPersonal · of 25 ranked | 186 |
| #2 | Fitness CoachingPersonal · of 25 ranked | 143 |
| #2 | Math ProofsResearch · of 25 ranked | 173 |
| #2 | Literature ReviewResearch · of 25 ranked | 186 |
| #2 | Experiment DesignResearch · of 25 ranked | 171 |
| #3 | SQL GenerationCode · of 25 ranked | 184 |
| #3 | Bug FixingCode · of 25 ranked | 198 |
| #3 | Code DocumentationCode · of 25 ranked | 149 |
| #3 | Regex WritingCode · of 25 ranked | 140 |
| #3 | Data AnalysisData · of 25 ranked | 184 |
| #3 | CSV / Spreadsheet CleanupData · of 25 ranked | 164 |
| #3 | Long-Document SummarizationWriting · of 25 ranked | 174 |
| #3 | Blog Post WritingWriting · of 25 ranked | 149 |
| #3 | Marketing CopyWriting · of 25 ranked | 136 |
| #3 | Language TranslationWriting · of 25 ranked | 140 |
| #3 | Contract ReviewProfessional · of 25 ranked | 197 |
| #3 | Standardized Test PrepEducation · of 25 ranked | 136 |
| #3 | Resume WritingBusiness · of 25 ranked | 120 |
| #3 | SOP / Process DocsBusiness · of 25 ranked | 143 |
| #3 | Agent WorkflowsAgents · of 25 ranked | 210 |
| #3 | Coding AgentsAgents · of 25 ranked | 210 |
| #3 | Character RoleplayPersonal · of 25 ranked | 161 |
| #3 | Trip PlanningPersonal · of 25 ranked | 149 |
| #3 | Tutoring for KidsPersonal · of 25 ranked | 140 |
| #3 | Scientific CodingResearch · of 25 ranked | 198 |
| #5 | Transcript CleanupWriting · of 25 ranked | 146 |
| #6 | Sales / Cold EmailBusiness · of 25 ranked | 124 |
| #6 | Job Application DraftingBusiness · of 25 ranked | 124 |
| #6 | Journaling HelperPersonal · of 25 ranked | 124 |
| #6 | Recipe GenerationPersonal · of 25 ranked | 124 |
Similar models
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
anthropic
Anthropic: Claude Sonnet 4.6 (batch)
$1.50 in / $7.50 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.