openai/o4-mini 📝❓🖼️🔢 → 📝

⭐ Official ▶️ 408.8K runs 📅 May 2025 ⚙️ Cog 0.16.9 ⚖️ License
code-generation image-analysis image-captioning image-to-text text-generation visual-understanding

About

OpenAI's fast, lightweight reasoning model

Example Output

Prompt:

"What is the theme of the Iliad?"

Output

Let us encode the main theme in purely mathematical terms.

  1. Basic objects
    • Let t ∈ [0,T] be “narrative time.”
    • Let R(t) ∈ ℝ₊ be Achilles’ wrath‐intensity at time t.
    • Let D(t) ∈ ℝ₊ be the cumulative death‐count (“destruction”) up to time t.
    • Let H(t) ∈ ℝ₊ be Achilles’ honor (kleos) at time t.
    • Let F be a fixed vector of “fate‐parameters” determined by the gods (constant w.r.t. t).

  2. Governing relations
    (i) dD/dt = α⋅R(t) + β⋅G(t)
    – here G(t) models discrete divine interventions; α,β>0.
    (ii) dH/dt = γ⋅R(t) – δ⋅D(t)
    – honor rises with wrath but is eroded by mounting destruction; γ,δ>0.
    (iii) R(0)=R₀>0, H(0)=H₀≥0, D(0)=0, F fixed.

  3. Central result (thematic “theorem”)
    Under these conditions the solution satisfies
    ∂D/∂R > 0 for all t>0,
    i.e. D(t) is a strictly increasing function of R(t).

  4. Interpretation
    The epic thus examines the map
    R(·) ↦ D(·)
    under the boundary/fate constraints F. Its “theme” is exactly that Achilles’ wrath R inexorably drives up the human cost D, despite any gains in honor H, all within a framework of immutable divine fate F.

Performance Metrics

19.98s Prediction Time
19.99s Total Time
All Input Parameters
{
  "prompt": "What is the theme of the Iliad?",
  "system_prompt": "You only speak in mathematical terms.",
  "reasoning_effort": "high",
  "max_completion_tokens": 4096
}
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.
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: medium
Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
max_completion_tokens Type: integerDefault: 4096
Maximum number of completion tokens to generate
Output Schema

Output

Type: arrayItems Type: string

Example Execution Logs
Generated response in 20.0sec
Version Details
Version ID
04ce1dc5eea6a7dd3ef53f69c65f7933bd70ce76dedda7e9fbb8cdf316214cf7
Version Created
January 22, 2026
Run on Replicate →