Google: Gemini 2.5 Pro (batch)
The Google Gemini 2.5 Pro is a batch AI model that can handle multiple input modalities, including text, image, file, audio, and video. It has a context length of up to 1048576 tokens and supports both tools and reasoning capabilities. For users who need a robust and versatile model for complex tasks, the Google Gemini 2.5 Pro is worth considering. With a blended benchmark score of 94.2 across one independent benchmark, it demonstrates strong performance in relevant areas. However, its pricing may be a deterrent for those on a tight budget: $0.625 per million input tokens and $5.00 per million output tokens may be too steep for some users.
Benchmark results
Independent, published benchmarks. Blended score 94.2 across 1 benchmark, last refreshed 2026-09-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| Aider Polyglot | code editing across languages | 83.1 |
- Model ID
- google/gemini-2.5-pro:batch
- Vendor
- Released
- June 2025
- Tokenizer
- Gemini
- Input Modalities
- text, image, file, audio, video
- Output Modalities
- text
- Max Output
- 65,536 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- ✓ accepts audio
- Moderated
- no
What it costs in practice
Computed from the current $0.62/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 | $0.03 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.56 |
| A month of a busy support chatbot | 5M in / 2M out | $13.12 |
Strong choice for
JSON Extraction
Bulk Data Labeling
Customer Support
Function / Tool Calling
Dataset Annotation
Category rankings
Where Google: Gemini 2.5 Pro (batch) places across the 21 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #2 | JSON ExtractionData · of 25 ranked | 138 |
| #3 | Dataset AnnotationResearch · of 25 ranked | 137 |
| #4 | Function / Tool CallingAgents · of 25 ranked | 130 |
| #5 | Bulk Data LabelingData · of 25 ranked | 130 |
| #5 | Customer SupportBusiness · of 25 ranked | 128 |
| #10 | CSV / Spreadsheet CleanupData · of 25 ranked | 142 |
| #10 | SOP / Process DocsBusiness · of 25 ranked | 125 |
| #12 | Diagram ExtractionVision · of 25 ranked | 135 |
| #13 | SQL GenerationCode · of 25 ranked | 147 |
| #13 | OCR / Document ParsingData · of 25 ranked | 136 |
| #13 | Table Extraction from PDFsData · of 25 ranked | 136 |
| #13 | Audio SummarizationVoice · of 25 ranked | 147 |
| #14 | Data AnalysisData · of 25 ranked | 139 |
| #15 | Browser AutomationAgents · of 25 ranked | 141 |
| #15 | Experiment DesignResearch · of 25 ranked | 135 |
| #16 | Meeting NotesBusiness · of 25 ranked | 143 |
| #18 | Unit Test GenerationCode · of 25 ranked | 136 |
| #18 | Video SummarizationVideo · of 25 ranked | 147 |
| #19 | Financial AnalysisProfessional · of 25 ranked | 134 |
| #19 | Fitness CoachingPersonal · of 25 ranked | 121 |
| #20 | Math TutoringEducation · of 25 ranked | 128 |
Similar models
Google: Gemini 3.8 Flash
Google: Gemini 3.8 Flash (batch)
Google: Gemini 3.7 Flash
Google: Gemini 3.7 Flash (batch)
Google: Gemini 3.6 Flash
Google: Gemini 3.6 Flash (batch)
Quick answers
- How much does Google: Gemini 2.5 Pro (batch) cost?
- $0.62 per million input tokens and $5.00 per million output tokens.
- What is Google: Gemini 2.5 Pro (batch)'s context window?
- 1,048,576 tokens, roughly 1,572 pages of text in a single request.
- Does Google: Gemini 2.5 Pro (batch) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Google: Gemini 2.5 Pro (batch) process images?
- Yes, it accepts image input.