openai/gpt-5.1 📝❓🖼️🔢 → 📝

⭐ Official ▶️ 194.4K runs 📅 Nov 2025 ⚙️ Cog 0.16.9
image-captioning image-to-text text-generation

About

The best model for coding and agentic tasks with configurable reasoning effort.

Example Output

Prompt:

"How many fingers are in this photo?"

Input Images

Input image 1
Input 1

Output

There are 7 fingers in the photo.

Performance Metrics

17.96s Prediction Time
18.06s Total Time
All Input Parameters
{
  "prompt": "How many fingers are in this photo?",
  "messages": [],
  "verbosity": "medium",
  "image_input": [
    "https://replicate.delivery/pbxt/O3rVFFvkwFCIWUFmtXz2VLjhVfLOaBNQSrkRlIJUkipN0zjR/fingies.jpg"
  ],
  "reasoning_effort": "high"
}
Input Parameters
prompt Type: string
The prompt to send to the model. Do not use if using messages.
messages Type: arrayDefault:
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.
verbosity Default: medium
Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high. GPT-5 supports this parameter to help control whether answers are short and to the point or long and comprehensive.
image_input Type: arrayDefault:
List of images to send to the model
system_prompt Type: string
System prompt to set the assistant's behavior
reasoning_effort Default: none
Constrains effort on reasoning for GPT-5.1. Supported values are none, low, medium, and high.
max_completion_tokens Type: integer
Maximum number of completion tokens to generate. For higher reasoning efforts you may need to increase your max_completion_tokens to avoid empty responses (where all the tokens are used on reasoning).
Output Schema

Output

Type: arrayItems Type: string

Example Execution Logs
Model variant: gpt-5.1
Input token count: 644
Output token count: 757
 - Reasoning tokens: 742
Total token count: 1401
TTFT: 0.22s
Version Details
Version ID
6fefc0acd5f42b1112d3e5dd57b42823e68b2ce68cad753eed05d24a96e2d35b
Version Created
November 14, 2025
Run on Replicate →