# OpenAI: o4 Mini

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.

Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.

by [OpenAI](/content/openai/index.html)  
Input type: Output type  
Publish time: 2025-04-16

## Recent activity on o4 Mini

### Tokens processed per day

## Throughput

(tokens/s)

| Providers | Min (tokens/s) | Max (tokens/s) | Avg (tokens/s) |
| --- | --- | --- | --- |
| Azure | 39.1 | 119.31 | 92.05 |

## First Token Latency

(ms)

| Providers | Min (ms) | Max (ms) | Avg (ms) |
| --- | --- | --- | --- |
| Azure | 2322 | 12522 | 7419.67 |

## Uptime stats for o4 Mini

Uptime stats for o4 Mini across all providers

### Uptime

Azure | OpenAI

( Percent )

### Providers for o4 Mini

ZenMux Provider to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

## Price

| Type                        | Cost          |
|-----------------------------|---------------|
| Input                       | $ 1.1/ M tokens |
| Output                      | $ 4.4/ M tokens |
| Cache read                  | $ 0.275/ M tokens |
| Cache write 5m               | -             |
| Cache write 1h              | -             |
| Cache write                 | -             |
| Web search                  | -             |
| Image                       | -             |
| Image input                 | -             |
| Image output                | -             |
| Image cache                 | -             |
| reasoning                   | -             |
| Video                       | -             |
| Audio                       | -             |
| Audio cache read            | -             |
| Audio input                 | -             |
| Audio & Video               | -             |
| Image search                | -             |
| Web search image            | -             |

## Model limitation

| Type                       | Value         |
|----------------------------|---------------|
| Context                    | 200.00K       |
| Max output                 | 100.00K       |

### Supported Parameters

- max_completion_tokens
- temperature
- top_p
- frequency_penalty
- presence_penalty
- seed
- logit_bias
- logprobs
- top_logprobs
- response_format
- stop
- tools
- tool_choice
- parallel_tool_calls

## Model Protocol Compatibility

- OpenAI Chat Completions
- OpenAI Responses
- OpenAI Embeddings
- Anthropic Messages
- Google Gemini
- Google Imagen
- Google Video

## Sample code and API for o4 Mini

ZenMux normalizes requests and responses across providers for you.

```python
from openai import OpenAI

client = OpenAI(
  base_url="https://zenmux.ai/api/v1",
  api_key="<ZENMUX_API_KEY>",
)

# Chat Completion
completion = client.chat.completions.create(
  model="openai/o4-mini",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)
```