Anthropic: Claude Sonnet 4.5
Anthropic: Claude Sonnet 4.5 is an AI model designed for extensive text, image, and file processing with a context length of one million tokens. It supports reasoning and tool usage but does not generate structured output. The model's performance is robust across benchmarks, with a blended score of 65.2 across four independent evaluations. Claude Sonnet 4.5 should be considered by those needing comprehensive support for text, image, and file inputs; its tools and reasoning capabilities are particularly useful. However, at $3.0 per million input tokens and $15.0 per million output tokens, it may not be the most economical choice unless you require its extensive context length and broad modalities, making it a strong contender for projects demanding high versatility and performance.
Benchmark results
Independent, published benchmarks. Blended score 64.8 across 4 benchmarks, last refreshed 2026-07-27. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 48.3 |
| AI Index Coding | software engineering tasks | 86.0 |
| AI Index Agentic | multi-step tool-using tasks | 40.6 |
| EQ-Bench | emotional understanding in dialogue | 72.2 |
- Model ID
- anthropic/claude-sonnet-4.5
- Vendor
- anthropic
- Released
- September 2025
- Tokenizer
- Claude
- Input Modalities
- text, image, file
- Output Modalities
- text
- Max Output
- 64,000 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 |
Category rankings
Where Anthropic: Claude Sonnet 4.5 places across the 40 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #10 | Meeting NotesBusiness · of 25 ranked | 150 |
| #12 | Transcript CleanupWriting · of 25 ranked | 141 |
| #12 | Long-Context Q&AAgents · of 25 ranked | 155 |
| #15 | Code RefactoringCode · of 25 ranked | 163 |
| #15 | OCR / Document ParsingData · of 25 ranked | 145 |
| #15 | Table Extraction from PDFsData · of 25 ranked | 145 |
| #15 | Long-Document SummarizationWriting · of 25 ranked | 159 |
| #15 | History TutoringEducation · of 25 ranked | 143 |
| #15 | RAG PipelinesAgents · of 25 ranked | 163 |
| #16 | RFP ResponseBusiness · of 25 ranked | 172 |
| #17 | Code DocumentationCode · of 25 ranked | 141 |
| #17 | CSV / Spreadsheet CleanupData · of 25 ranked | 152 |
| #18 | Legal ResearchProfessional · of 25 ranked | 165 |
| #18 | Scientific ResearchProfessional · of 25 ranked | 165 |
| #18 | Fiction CollaboratorPersonal · of 25 ranked | 165 |
| #18 | Literature ReviewResearch · of 25 ranked | 165 |
| #19 | ETL ScriptingData · of 25 ranked | 152 |
| #19 | Blog Post WritingWriting · of 25 ranked | 136 |
| #19 | Medical Note SummarizationProfessional · of 25 ranked | 152 |
| #19 | Character RoleplayPersonal · of 25 ranked | 148 |
| #19 | Trip PlanningPersonal · of 25 ranked | 136 |
| #22 | Code ReviewCode · of 25 ranked | 163 |
| #22 | Unit Test GenerationCode · of 25 ranked | 150 |
| #22 | CI/CD PipelinesCode · of 25 ranked | 141 |
| #22 | Contract ReviewProfessional · of 25 ranked | 174 |
| #22 | Essay GradingEducation · of 25 ranked | 163 |
| #23 | Frontend Component DesignCode · of 25 ranked | 141 |
| #23 | Creative WritingWriting · of 25 ranked | 154 |
| #23 | Screenwriting & DialogWriting · of 25 ranked | 154 |
| #23 | Academic WritingWriting · of 25 ranked | 154 |
| #23 | Legal DraftingProfessional · of 25 ranked | 154 |
| #23 | Physics TutoringEducation · of 25 ranked | 143 |
| #23 | OKRs & Strategic PlanningBusiness · of 25 ranked | 154 |
| #23 | Math ProofsResearch · of 25 ranked | 154 |
| #24 | Diagram ExtractionVision · of 25 ranked | 144 |
| #24 | Agent WorkflowsAgents · of 25 ranked | 181 |
| #24 | Coding AgentsAgents · of 25 ranked | 181 |
| #25 | Bug FixingCode · of 25 ranked | 172 |
| #25 | Chart & Graph ReadingVision · of 25 ranked | 146 |
| #25 | Scientific CodingResearch · of 25 ranked | 172 |
Similar models
Anthropic: Claude Sonnet 5
Anthropic: Claude Sonnet 4.6
Anthropic: Claude Haiku 4.5
Anthropic: Claude Sonnet 4
Claude Opus 5
Anthropic: Claude Opus 4.8
Quick answers
- How much does Anthropic: Claude Sonnet 4.5 cost?
- $3.00 per million input tokens and $15.00 per million output tokens.
- What is Anthropic: Claude Sonnet 4.5's context window?
- 1,000,000 tokens, roughly 1,500 pages of text in a single request.
- Does Anthropic: Claude Sonnet 4.5 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Anthropic: Claude Sonnet 4.5 process images?
- Yes, it accepts image input.