Speed
Output tokens / second
Gemini Pro 2.5 Experimental overview
Gemini Pro 2.5 Experimental specs
- Developer
- Input
- Text, Image
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Overview
Gemini Pro 2.5 Experimental is designed to handle complex tasks requiring advanced reasoning and multimodal understanding. It supports inputs in text and images, providing text-based outputs. The model excels in coding, mathematical problem-solving, and analyzing large datasets.
Key Features
- Multimodal Input Support: Accepts text and images.
- Advanced Reasoning: Capable of complex problem-solving and logical reasoning.
- Coding Proficiency: Excels in understanding and generating code.
- Extended Context Window: Handles extensive input data effectively.
Intended Use
- Complex Problem Solving: Suitable for tasks requiring deep reasoning across various data types.
- Software Development: Assists in code generation and debugging.
- Data Analysis: Capable of processing and interpreting large datasets.
- Educational Applications: Enhances learning experiences through interactive content.
Code Samples:
The model is available on the AI/ML API platform as "Gemini Pro 2.5 Experimental" .
API Documentation:
Detailed API Documentation is available here.
Ethical Guidelines
Google DeepMind emphasizes ethical considerations in AI development by promoting transparency regarding the model's capabilities and limitations. The organization encourages responsible usage to prevent misuse or harmful applications of generated content.
Use cases
- Advanced AI assistants and chatbots
- Software development and code automation
- Scientific research and complex mathematical reasoning
- Creative multimedia content generation (images, video, audio)
- Enterprise workflows with agentic automation
- Educational tools with multimodal interactive capabilities
- Game development and interactive application generation
Capabilities
- Function calling
- Streaming
- Structured outputs
Gemini Pro 2.5 Experimental benchmarks by 
Artificial Analysis
See how Gemini Pro 2.5 Experimental compares in generation speed and latency. Data retrieved Nov 3, 2026.
Benchmark results
Compare 6 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
Terminal-Bench 4.0
Agentic tasks completed in a command-line environment.
AA-LCR
Reasoning across long documents of about 100k tokens.
SciCode
Python coding tasks drawn from scientific research.
Gemini Pro 2.5 Experimental API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $1.62 | 1M tokens |
| Output | $13 | 1M tokens |
Gemini Pro 2.5 Experimental is deprecated on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Gemini Pro 2.5 Experimental vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Gemini Pro 2.5 Experimental | $1.62 | $13 |
| Gemini 3.5 Flash Lite | $0.3 | $2.5 |
| Gemini 3.8 Flash | $0.75 | $3.75 |
| Gemini 3.7 Flash | $0.75 | $3.75 |
| Gemini 4 Argon | $2 | $10 |
Models similar to Gemini Pro 2.5 Experimental
Related articles
Gemini Pro 2.5 Experimental FAQ
Does Gemini Pro 2.5 Experimental support streaming?
Yes, Gemini Pro 2.5 Experimental can stream responses as they are generated.
Does Gemini Pro 2.5 Experimental support tool calling and structured outputs?
Yes, Gemini Pro 2.5 Experimental supports both function calling and structured outputs.
Who created Gemini Pro 2.5 Experimental?
Gemini Pro 2.5 Experimental was built by Google.
Which API endpoint does Gemini Pro 2.5 Experimental use?
It is available on the v1 endpoint.