openai/gpt-4.1-mini 🔢📝❓🖼️ → 📝
About
Fast, affordable version of GPT-4.1

Example Output
"Explain this image in excruciating detail"
Input Images

Output
This image depicts a digital painting of two individuals sitting on yellow chairs facing each other. The style of the artwork has a highly textured and brushstroke-rich appearance, giving it a classic oil painting effect.
The person on the left is an older man with distinctive features resembling the iconic image of Albert Einstein. He has white, wild, and voluminous hair that flows back from his head, along with a white mustache. His skin is light with detailed wrinkles, suggesting age. He wears dark aviator-style sunglasses that cover his eyes. His outfit consists of a black or dark charcoal jacket over a grey shirt. His posture is relaxed yet engaged; he is sitting with his legs crossed and his hands intertwined in front of him, leaning slightly forward as if involved in a deep conversation.
Opposite him, on the right, is a young woman also wearing sunglasses; hers are larger, black, and have a fashionable cat-eye shape. Her hair is long, light brown, and pulled back into a high ponytail secured with a black hair tie, revealing her neck and ears adorned with small pearl earrings. She wears a modern sporty outfit: a fitted black sleeveless crop top with white, red, and green horizontal stripes below the bust, showcasing her midriff, paired with high-waisted black leggings. Her makeup is notable with vivid red lipstick and subtle blush on her cheeks, enhancing her poised facial expression. Her body language is attentive, sitting upright with one arm resting on her leg, facing the man directly as if listening intently or engaged in serious discussion.
The background is muted, a gradient of soft, light greyish and beige tones with smooth texture and faint brush marks, which ensures the vibrant yellow chairs and the figures stand out prominently. The contrast between the elderly man dressed in classic, somber tones and the young woman in trendy athletic wear suggests a dialogue across generations or a fusion of intellect and modernity.
Overall, the image conveys an intimate, intense moment of exchange, blending timelessness with contemporary style, framed in a polished painterly technique that enhances the emotional depth and character of each subject.
Performance Metrics
All Input Parameters
{ "prompt": "Explain this image in excruciating detail", "image_input": [ "https://replicate.delivery/pbxt/MvoFggJfmpSOBa0TiiQbvxLc0eS7u6CpH2WHaq30FZCVIvFa/test.jpg" ], "temperature": 1, "system_prompt": "You are a helpful assistant." }
Input Parameters
- top_p
- Nucleus sampling parameter - the model considers the results of the tokens with top_p probability mass. (0.1 means only the tokens comprising the top 10% probability mass are considered.)
- prompt
- The prompt to send to the model. Do not use if using messages.
- messages
- A JSON string representing a list of messages. For example: [{"role": "user", "content": "Hello, how are you?"}]. If provided, prompt and system_prompt are ignored.
- image_input
- List of images to send to the model
- temperature
- Sampling temperature between 0 and 2
- system_prompt
- System prompt to set the assistant's behavior
- presence_penalty
- Presence penalty parameter - positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
- frequency_penalty
- Frequency penalty parameter - positive values penalize the repetition of tokens.
- max_completion_tokens
- Maximum number of completion tokens to generate
Output Schema
Output
Example Execution Logs
Image size: 278.7KB Generated response in 9.8sec /usr/local/lib/python3.12/site-packages/cog/server/scope.py:21: ExperimentalFeatureWarning: current_scope is an experimental internal function. It may change or be removed without warning. warnings.warn(
Version Details
- Version ID
2e47757e2b7aa34decf05335dc78ad7968386e8aacd345dd045b6dfeb622cd69
- Version Created
- September 16, 2025