# Codex Mini API Pricing

As of October 10, 2026, Codex Mini costs $1.50 per 1M input tokens and $6.00 per 1M output tokens from Azure OpenAI, the lowest of 2 providers, with cache reads at $0.375 per 1M tokens. It has a 200,000-token context window and returns up to 100,000 tokens per response.

- Page: https://models.litellm.ai/models/codex-mini
- Lab: OpenAI
- LiteLLM model name: `azure/codex-mini`
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Added to LiteLLM: June 2025
- Deprecation date: November 15, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Azure OpenAI | `azure/codex-mini` | $1.50 | $6.00 | $0.375 | – | – | 200K |
| Azure AI Foundry | `azure_ai/codex-mini` | $1.50 | $6.00 | $0.375 | – | – | 200K |
| Azure OpenAI (eu) | `azure/eu/codex-mini` | $1.65 | $6.60 | $0.413 | – | – | – |
| Azure OpenAI (us) | `azure/us/codex-mini` | $1.65 | $6.60 | $0.413 | – | – | – |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Azure OpenAI: $6.00
- Azure AI Foundry: $6.00

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Azure OpenAI: $16.20
- Azure AI Foundry: $16.20

## Features

Supported: Function calling, Parallel tool calls, Structured output, Image input, PDF input, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="azure/codex-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Codex Mini cost?

Codex Mini costs $1.50 per 1M input tokens and $6.00 per 1M output tokens from Azure OpenAI, the lowest of 2 providers, with cache reads at $0.375 per 1M tokens.

### What is the context window of Codex Mini?

Codex Mini has a 200,000-token context window and returns up to 100,000 tokens per response.

### Which providers offer Codex Mini?

Codex Mini is available from 2 providers through LiteLLM: Azure OpenAI and Azure AI Foundry.

### How do I call Codex Mini with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure/codex-mini", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/responses from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Codex Mini support?

Codex Mini supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning and prompt caching.

### When did LiteLLM add Codex Mini?

Codex Mini was added to LiteLLM's model price file in June 2025.

### Is Codex Mini being deprecated?

Azure OpenAI lists a deprecation date of November 15, 2026 for azure/codex-mini.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json