openai/gpt-5 📝❓🖼️🔢 → 📝

⭐ Official ▶️ 364.7K runs 📅 Aug 2025 ⚙️ Cog 0.16.6

About

OpenAI's new model excelling at coding, writing, and reasoning.

Example Output

Prompt:

"Are you AGI?"

Output

No. I’m a narrow AI language model. I can generate and reason about text across many topics, but I don’t have general human-level intelligence, self-awareness, or open-ended autonomy. My abilities are bounded by my training data, design, and the information you provide in a conversation.

Performance Metrics

1.27s Prediction Time

1.27s Total Time

All Input Parameters

{
  "prompt": "Are you AGI?",
  "messages": [],
  "verbosity": "medium",
  "image_input": [],
  "reasoning_effort": "minimal"
}

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: minimal: Constrains effort on reasoning for GPT-5 models. Currently supported values are minimal, low, medium, and high. The minimal value gets answers back faster without extensive reasoning first. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 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).
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: array • Items Type: string

Example Execution Logs

Input token count: 11
Output token count: 68
Total token count: 79
TTFT: 0.81s
Finish reason: stop

Version Details

Version ID: 857113f52713e87828867975887fb4d369789052c5c63076933548b2720044da
Version Created: September 16, 2025

Run on Replicate →