anthropic
Anthropic: Claude Sonnet 4.6 (batch)
Anthropic Claude Sonnet 4.6 is designed to process vast amounts of text with a context length of 1 million tokens and supports image and file inputs, making it versatile for multimedia tasks. It excels in reasoning and can utilize tools for enhanced functionality. While it lacks structured output support, its benchmark score of 81.4 across five independent evaluations indicates strong performance in areas like polyglot assistance and coding. This model is suitable for those who need robust text handling with flexible input modalities but are looking to balance cost with capability; at $1.5 per million input tokens and $7.5 per million output tokens, it offers a competitive price point despite its premium status.
Quality Score
100/100
price + capability + benchmarks
Input Price
$1.50
per 1M tokens
Output Price
$7.50
per 1M tokens
Context Window
1,000,000
tokens
Benchmark results
Independent, published benchmarks. Blended score 81.4 across 5 benchmarks, last refreshed 2026-08-07. 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:batch
- 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 $1.50/M input and $7.50/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.06 |
| Classify 1,000 customer emails | 500k in / 50k out | $1.12 |
| A month of a busy support chatbot | 5M in / 2M out | $22.50 |
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 (batch) places across the 63 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #2 | SQL GenerationCode · of 25 ranked | 185 |
| #2 | Code DocumentationCode · of 25 ranked | 151 |
| #2 | Regex WritingCode · of 25 ranked | 142 |
| #2 | CSV / Spreadsheet CleanupData · of 25 ranked | 164 |
| #2 | Long-Document SummarizationWriting · of 25 ranked | 175 |
| #2 | Blog Post WritingWriting · of 25 ranked | 150 |
| #2 | Marketing CopyWriting · of 25 ranked | 137 |
| #2 | Language TranslationWriting · of 25 ranked | 142 |
| #2 | Transcript CleanupWriting · of 25 ranked | 148 |
| #2 | Standardized Test PrepEducation · of 25 ranked | 137 |
| #2 | Sales / Cold EmailBusiness · of 25 ranked | 126 |
| #2 | Resume WritingBusiness · of 25 ranked | 121 |
| #2 | Job Application DraftingBusiness · of 25 ranked | 126 |
| #2 | SOP / Process DocsBusiness · of 25 ranked | 144 |
| #2 | Character RoleplayPersonal · of 25 ranked | 162 |
| #2 | Journaling HelperPersonal · of 25 ranked | 126 |
| #2 | Recipe GenerationPersonal · of 25 ranked | 126 |
| #2 | Trip PlanningPersonal · of 25 ranked | 150 |
| #2 | Tutoring for KidsPersonal · of 25 ranked | 142 |
| #3 | Code ReviewCode · of 25 ranked | 185 |
| #3 | Code RefactoringCode · of 25 ranked | 181 |
| #3 | Unit Test GenerationCode · of 25 ranked | 167 |
| #3 | CI/CD PipelinesCode · of 25 ranked | 156 |
| #3 | Frontend Component DesignCode · of 25 ranked | 155 |
| #3 | ETL ScriptingData · of 25 ranked | 169 |
| #3 | OCR / Document ParsingData · of 25 ranked | 153 |
| #3 | Table Extraction from PDFsData · of 25 ranked | 153 |
| #3 | Creative WritingWriting · of 25 ranked | 173 |
| #3 | Screenwriting & DialogWriting · of 25 ranked | 173 |
| #3 | Academic WritingWriting · of 25 ranked | 173 |
| #3 | Legal DraftingProfessional · of 25 ranked | 173 |
| #3 | Legal ResearchProfessional · of 25 ranked | 186 |
| #3 | Financial AnalysisProfessional · of 25 ranked | 172 |
| #3 | Medical Note SummarizationProfessional · of 25 ranked | 169 |
| #3 | Scientific ResearchProfessional · of 25 ranked | 186 |
| #3 | Math TutoringEducation · of 25 ranked | 159 |
| #3 | Physics TutoringEducation · of 25 ranked | 161 |
| #3 | History TutoringEducation · of 25 ranked | 157 |
| #3 | Essay GradingEducation · of 25 ranked | 185 |
| #3 | Meeting NotesBusiness · of 25 ranked | 160 |
| #3 | RFP ResponseBusiness · of 25 ranked | 193 |
| #3 | OKRs & Strategic PlanningBusiness · of 25 ranked | 173 |
| #3 | Diagram ExtractionVision · of 25 ranked | 156 |
| #3 | Screenshot DebuggingVision · of 25 ranked | 149 |
| #3 | Chart & Graph ReadingVision · of 25 ranked | 161 |
| #3 | Browser AutomationAgents · of 25 ranked | 181 |
| #3 | Function / Tool CallingAgents · of 25 ranked | 160 |
| #3 | RAG PipelinesAgents · of 25 ranked | 181 |
| #3 | Long-Context Q&AAgents · of 25 ranked | 170 |
| #3 | Fiction CollaboratorPersonal · of 25 ranked | 186 |
| #3 | Fitness CoachingPersonal · of 25 ranked | 143 |
| #3 | Math ProofsResearch · of 25 ranked | 173 |
| #3 | Literature ReviewResearch · of 25 ranked | 186 |
| #3 | Experiment DesignResearch · of 25 ranked | 171 |
| #4 | Bug FixingCode · of 25 ranked | 198 |
| #4 | Data AnalysisData · of 25 ranked | 184 |
| #4 | Contract ReviewProfessional · of 25 ranked | 197 |
| #4 | Agent WorkflowsAgents · of 25 ranked | 210 |
| #4 | Coding AgentsAgents · of 25 ranked | 210 |
| #4 | Scientific CodingResearch · of 25 ranked | 198 |
| #13 | Trivia & General KnowledgePersonal · of 25 ranked | 121 |
| #20 | Email DraftingWriting · of 25 ranked | 126 |
| #20 | Language LearningEducation · of 25 ranked | 126 |
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
$3.00 in / $15.00 out
1,000,000 ctx
100
Quick answers
- How much does Anthropic: Claude Sonnet 4.6 (batch) cost?
- $1.50 per million input tokens and $7.50 per million output tokens.
- What is Anthropic: Claude Sonnet 4.6 (batch)'s context window?
- 1,000,000 tokens, roughly 1,500 pages of text in a single request.
- Does Anthropic: Claude Sonnet 4.6 (batch) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Anthropic: Claude Sonnet 4.6 (batch) process images?
- Yes, it accepts image input.