# GPT-5.4 Mini API Pricing

As of October 10, 2026, GPT-5.4 Mini costs $0.75 per 1M input tokens and $4.50 per 1M output tokens on OpenAI, with cache reads at $0.075 per 1M tokens. It has a 272,000-token context window and returns up to 128,000 tokens per response.

- Page: https://models.litellm.ai/models/gpt-5.4-mini
- Lab: OpenAI
- LiteLLM model name: `gpt-5.4-mini`
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Added to LiteLLM: March 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 |
|---|---|---|---|---|---|---|---|
| OpenAI | `gpt-5.4-mini` | $0.75 | $4.50 | $0.075 | – | – | 272K |
| OpenAI (snapshot 2026-03-17) | `gpt-5.4-mini-2026-03-17` | $0.75 | $4.50 | $0.075 | – | – | 272K |
| AIHubMix | `aihubmix/gpt-5.4-mini` | $0.75 | $4.50 | $0.075 | – | – | 400K |
| Azure AI Foundry | `azure_ai/gpt-5.4-mini` | $0.75 | $4.50 | $0.075 | – | – | 272K |
| Azure AI Foundry (snapshot 2026-03-17) | `azure_ai/gpt-5.4-mini-2026-03-17` | $0.75 | $4.50 | $0.075 | – | – | 272K |
| Azure OpenAI | `azure/gpt-5.4-mini` | $0.75 | $4.50 | $0.075 | – | – | 272K |
| Azure OpenAI (snapshot 2026-03-17) | `azure/gpt-5.4-mini-2026-03-17` | $0.75 | $4.50 | $0.075 | – | – | 272K |
| Databricks | `databricks/databricks-gpt-5-4-mini` | $0.75 | $4.50 | $0.07497 | – | – | 272K |
| GitHub Copilot | `github_copilot/gpt-5.4-mini` | – | – | – | – | – | 272K |
| Perplexity | `perplexity/openai/gpt-5.4-mini` | $0.75 | $4.50 | $0.075 | – | – | – |
| Azure OpenAI (eu) | `azure/eu/gpt-5.4-mini` | $0.825 | $4.95 | $0.0825 | – | – | – |
| Azure OpenAI (us) | `azure/us/gpt-5.4-mini` | $0.825 | $4.95 | $0.0825 | – | – | – |

## Cost examples

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

- OpenAI: $3.75
- Databricks: $3.75
- AIHubMix: $3.75
- Azure AI Foundry: $3.75
- OpenAI batch: $1.875

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

- OpenAI: $8.40
- Databricks: $8.40
- AIHubMix: $8.40
- Azure AI Foundry: $8.40

## Features

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

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gpt-5.4-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT-5.4 Mini cost?

GPT-5.4 Mini costs $0.75 per 1M input tokens and $4.50 per 1M output tokens on OpenAI, with cache reads at $0.075 per 1M tokens. Batch requests cost $0.375 per 1M input tokens and $2.25 per 1M output tokens.

### What is the context window of GPT-5.4 Mini?

GPT-5.4 Mini has a 272,000-token context window and returns up to 128,000 tokens per response.

### Which providers offer GPT-5.4 Mini?

GPT-5.4 Mini is available from 7 providers through LiteLLM: OpenAI, AIHubMix, Azure AI Foundry, Azure OpenAI, Databricks, GitHub Copilot and Perplexity. The lowest price is on Databricks.

### How do I call GPT-5.4 Mini with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-5.4-mini", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does GPT-5.4 Mini support?

GPT-5.4 Mini supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.

### When did LiteLLM add GPT-5.4 Mini?

GPT-5.4 Mini was added to LiteLLM's model price file in March 2026.

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