# GPT-5.4 API Pricing

As of October 10, 2026, GPT-5.4 costs $2.50 per 1M input tokens and $15.00 per 1M output tokens on OpenAI, with cache reads at $0.25 per 1M tokens. Across 9 providers on LiteLLM, the input price ranges from $2.50 to $2.75. It has a 1,050,000-token context window and returns up to 128,000 tokens per response.

- Page: https://models.litellm.ai/models/gpt-5.4
- Lab: OpenAI
- LiteLLM model name: `gpt-5.4`
- Context window: 1,050,000 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` | $2.50 | $15.00 | $0.25 | – | – | 1M |
| OpenAI (snapshot 2026-03-05) | `gpt-5.4-2026-03-05` | $2.50 | $15.00 | $0.25 | – | – | 1M |
| Amazon Bedrock Mantle | `bedrock_mantle/openai.gpt-5.4` | $2.75 | $16.50 | $0.275 | – | – | 1M |
| Azure AI Foundry | `azure_ai/gpt-5.4` | $2.50 | $15.00 | $0.25 | – | – | 922K |
| Azure AI Foundry (snapshot 2026-03-05) | `azure_ai/gpt-5.4-2026-03-05` | $2.50 | $15.00 | $0.25 | – | – | 922K |
| Azure OpenAI | `azure/gpt-5.4` | $2.50 | $15.00 | $0.25 | – | – | 922K |
| Azure OpenAI (snapshot 2026-03-05) | `azure/gpt-5.4-2026-03-05` | $2.50 | $15.00 | $0.25 | – | – | 922K |
| ChatGPT Subscription | `chatgpt/gpt-5.4` | – | – | – | – | – | 1M |
| Databricks | `databricks/databricks-gpt-5-4` | $2.50 | $15.00 | $0.25 | – | – | 922K |
| GitHub Copilot | `github_copilot/gpt-5.4` | – | – | – | – | – | 272K |
| Perplexity | `perplexity/openai/gpt-5.4` | $2.50 | $15.00 | $0.25 | – | – | – |
| Amazon Bedrock (Global cross-region) | `global.openai.gpt-5.4` | $2.50 | $15.00 | $0.25 | – | – | 1M |
| Amazon Bedrock (US cross-region) | `us.openai.gpt-5.4` | $2.75 | $16.50 | $0.275 | – | – | 1M |
| Amazon Bedrock Mantle (us-gov-east-1) | `bedrock_mantle/us-gov-east-1/openai.gpt-5.4` | $3.30 | $19.80 | $0.33 | – | – | 1M |
| Amazon Bedrock Mantle (us-gov-west-1) | `bedrock_mantle/us-gov-west-1/openai.gpt-5.4` | $3.375 | $20.25 | $0.3375 | – | – | 1M |
| Azure OpenAI (eu) | `azure/eu/gpt-5.4` | $2.75 | $16.50 | $0.275 | – | – | 922K |
| Azure OpenAI (eu, snapshot 2026-03-05) | `azure/eu/gpt-5.4-2026-03-05` | $2.75 | $16.50 | $0.275 | – | – | 922K |
| Azure OpenAI (us) | `azure/us/gpt-5.4` | $2.75 | $16.50 | $0.275 | – | – | 922K |
| Azure OpenAI (us, snapshot 2026-03-05) | `azure/us/gpt-5.4-2026-03-05` | $2.75 | $16.50 | $0.275 | – | – | 922K |

## Cost examples

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

- OpenAI: $12.50
- Databricks: $12.50
- Azure AI Foundry: $12.50
- Azure OpenAI: $12.50
- OpenAI batch: $6.25

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

- OpenAI: $28.00
- Databricks: $28.00
- Azure AI Foundry: $28.00
- Azure OpenAI: $28.00

## 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",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT-5.4 cost?

GPT-5.4 costs $2.50 per 1M input tokens and $15.00 per 1M output tokens on OpenAI, with cache reads at $0.25 per 1M tokens. Batch requests cost $1.25 per 1M input tokens and $7.50 per 1M output tokens. Above 272K input tokens, input costs $5.00 and output costs $22.50 per 1M tokens. Across 9 providers on LiteLLM, the input price ranges from $2.50 to $2.75.

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

GPT-5.4 has a 1,050,000-token context window and returns up to 128,000 tokens per response.

### Which providers offer GPT-5.4?

GPT-5.4 is available from 9 providers through LiteLLM: OpenAI, Amazon Bedrock Mantle, Azure AI Foundry, Azure OpenAI, ChatGPT Subscription, Databricks, GitHub Copilot, Perplexity and Amazon Bedrock. The lowest price is on Databricks.

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

Use the LiteLLM Python SDK with model="gpt-5.4", 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 support?

GPT-5.4 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?

GPT-5.4 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