 GPT-5 Image Mini |  Mercury | |
|---|---|---|
Model Provider The organization behind this AI's development | OpenAI | Inception |
Input Context Window Maximum input tokens this model can process at once | 400K tokens | 128K tokens |
Output Token Limit Maximum output tokens this model can generate at once | 128K tokens | 16.4K tokens |
Release Date When this model first became publicly available | October 16, 2025 27 days ago October 16th, 2025 | June 26, 2025 4 months ago June 26th, 2025 |
GPT-5 Image Mini | Mercury | |
|---|---|---|
Input Types Supported input formats | 📁File🖼️Image📝Text | 📝Text |
Output Types Supported output formats | 🖼️Image📝Text | 📝Text |
Tokenizer Text encoding system | GPT | Other |
Key Features Advanced capabilities | ✓Function Calling✓Structured Output✓Reasoning Mode✓Content Moderation | ✓Function Calling✓Structured OutputReasoning ModeContent Moderation |
| GPT-5 Image Mini | Mercury | |
|---|---|---|
Input Token Cost Cost per million input tokens | $2.50 per million tokens | $0.25 per million tokens |
Output Token Cost Cost per million outut tokens | $2.00 per million tokens | $1.00 per million tokens |
| GPT-5 Image Mini | Mercury | |
|---|---|---|
MMLU Measures knowledge across 57 subjects like law, math, history, and science | Benchmark not available. | Benchmark not available. |
MMMU Measures understanding of combined text and images across various domains | Benchmark not available. | Benchmark not available. |
HellaSwag Measures common sense reasoning by having models complete sentences about everyday situations | Benchmark not available. | Benchmark not available. |
GPT-5 Image Mini by OpenAI understands both text and images, can use external tools and APIs, offers advanced reasoning, generates structured data. It can handle standard conversations with its 400K token context window. Reasonably priced at $2.50/M input and $2.00/M output tokens. Includes built-in content moderation for safer outputs. Released October 16th, 2025.Mercury by Inception can use external tools and APIs, generates structured data. It can handle standard conversations with its 128K token context window. Very affordable at $0.25/M input and $1.00/M output tokens. Released June 26th, 2025.Compare your models with top performers across different categories
Best models for coding and development
Models optimized for creative writing
Content creation and marketing tasks
Technical analysis and explanations
Scientific research and analysis
Multilingual translation tasks
Best models for coding and development
Models optimized for creative writing
Content creation and marketing tasks
Technical analysis and explanations
Scientific research and analysis
Multilingual translation tasks
