Anthropic: Claude Sonnet 5 (batch)
Claude Sonnet 5 from Anthropic is a powerful AI model capable of handling text, images, and files, with a context length of up to one million tokens. It supports reasoning and tool integration, making it versatile for various tasks; however, structured output support remains unimplemented. This model stands as a solid choice for those needing robust AI capabilities at a blended benchmark score of 91.6 across three independent assessments. Given its pricing-$1.0 per million input tokens and $5.0 per million output tokens-it offers a competitive solution for businesses requiring advanced AI functionalities, though the low benchmark coverage might limit its appeal for specialized use cases.
Benchmark results
Independent, published benchmarks. Blended score 91.6 across 3 benchmarks, last refreshed 2026-08-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 91.2 |
| AI Index Coding | software engineering tasks | 100.0 |
| AI Index Agentic | multi-step tool-using tasks | 82.0 |
- Model ID
- anthropic/claude-sonnet-5:batch
- Vendor
- anthropic
- Released
- June 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 $1.00/M input and $5.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.04 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.75 |
| A month of a busy support chatbot | 5M in / 2M out | $15.00 |
Category rankings
Where Anthropic: Claude Sonnet 5 (batch) places across the 32 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #13 | Sales / Cold EmailBusiness · of 25 ranked | 123 |
| #13 | Job Application DraftingBusiness · of 25 ranked | 123 |
| #13 | Function / Tool CallingAgents · of 25 ranked | 155 |
| #13 | Journaling HelperPersonal · of 25 ranked | 123 |
| #13 | Recipe GenerationPersonal · of 25 ranked | 123 |
| #16 | Resume WritingBusiness · of 25 ranked | 118 |
| #18 | SOP / Process DocsBusiness · of 25 ranked | 138 |
| #19 | Diagram ExtractionVision · of 25 ranked | 150 |
| #19 | Browser AutomationAgents · of 25 ranked | 173 |
| #20 | Regex WritingCode · of 25 ranked | 136 |
| #20 | Frontend Component DesignCode · of 25 ranked | 147 |
| #20 | Marketing CopyWriting · of 25 ranked | 131 |
| #20 | Language TranslationWriting · of 25 ranked | 136 |
| #20 | Standardized Test PrepEducation · of 25 ranked | 131 |
| #20 | Screenshot DebuggingVision · of 25 ranked | 143 |
| #20 | Chart & Graph ReadingVision · of 25 ranked | 153 |
| #20 | Tutoring for KidsPersonal · of 25 ranked | 136 |
| #21 | SQL GenerationCode · of 25 ranked | 172 |
| #21 | OCR / Document ParsingData · of 25 ranked | 147 |
| #21 | Table Extraction from PDFsData · of 25 ranked | 147 |
| #22 | Code DocumentationCode · of 25 ranked | 143 |
| #23 | Data AnalysisData · of 25 ranked | 172 |
| #23 | CSV / Spreadsheet CleanupData · of 25 ranked | 154 |
| #23 | Financial AnalysisProfessional · of 25 ranked | 160 |
| #23 | Fitness CoachingPersonal · of 25 ranked | 135 |
| #24 | Bug FixingCode · of 25 ranked | 182 |
| #24 | Blog Post WritingWriting · of 25 ranked | 141 |
| #24 | Trip PlanningPersonal · of 25 ranked | 141 |
| #24 | Scientific CodingResearch · of 25 ranked | 182 |
| #25 | Agent WorkflowsAgents · of 25 ranked | 194 |
| #25 | Coding AgentsAgents · of 25 ranked | 194 |
| #25 | Character RoleplayPersonal · of 25 ranked | 151 |
Similar models
Claude Opus 5 (batch)
Anthropic: Claude Sonnet 5
Anthropic: Claude Opus 4.8 (batch)
Anthropic: Claude Opus 4.7 (batch)
Anthropic: Claude Sonnet 4.6
Anthropic: Claude Sonnet 4.6 (batch)
Quick answers
- How much does Anthropic: Claude Sonnet 5 (batch) cost?
- $1.00 per million input tokens and $5.00 per million output tokens.
- What is Anthropic: Claude Sonnet 5 (batch)'s context window?
- 1,000,000 tokens, roughly 1,500 pages of text in a single request.
- Does Anthropic: Claude Sonnet 5 (batch) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Anthropic: Claude Sonnet 5 (batch) process images?
- Yes, it accepts image input.