Anthropic: Claude Sonnet 4.5 (batch)
The Anthropic: Claude Sonnet 4.5 (batch) is a large language model that can handle text, image, and file inputs up to a context length of 100,000 tokens. It supports tools, reasoning, and outputting unstructured text, but does not provide structured output. For those seeking a robust tool for generating text from various inputs, this model might be worth considering due to its ability to process images and files alongside text. Its blended benchmark score of 56.2 across two independent benchmarks is respectable, although not exceptional in the field. With pricing at $1.5 per input token and $7.5 per output token, it may suit users who require frequent but moderately-sized outputs.
Benchmark results
Independent, published benchmarks. Blended score 54.9 across 2 benchmarks, last refreshed 2026-09-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 31.9 |
| EQ-Bench | emotional understanding in dialogue | 72.2 |
- Model ID
- anthropic/claude-sonnet-4.5:batch
- 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 $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 |
Category rankings
Where Anthropic: Claude Sonnet 4.5 (batch) places across the 7 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #19 | Code DocumentationCode · of 25 ranked | 138 |
| #21 | Transcript CleanupWriting · of 25 ranked | 142 |
| #24 | Code RefactoringCode · of 25 ranked | 150 |
| #24 | Long-Document SummarizationWriting · of 25 ranked | 151 |
| #24 | RAG PipelinesAgents · of 25 ranked | 150 |
| #24 | Long-Context Q&AAgents · of 25 ranked | 146 |
| #25 | Character RoleplayPersonal · of 25 ranked | 140 |
Similar models
Anthropic: Claude Opus 5.5 (batch)
Anthropic: Claude Opus 5 (batch)
Anthropic: Claude Sonnet 5
Anthropic: Claude Sonnet 5 (batch)
Anthropic: Claude Opus 4.8 (batch)
Anthropic: Claude Opus 4.7 (batch)
Quick answers
- How much does Anthropic: Claude Sonnet 4.5 (batch) cost?
- $1.50 per million input tokens and $7.50 per million output tokens.
- What is Anthropic: Claude Sonnet 4.5 (batch)'s context window?
- 1,000,000 tokens, roughly 1,500 pages of text in a single request.
- Does Anthropic: Claude Sonnet 4.5 (batch) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Anthropic: Claude Sonnet 4.5 (batch) process images?
- Yes, it accepts image input.