LiteLLMModels

GPT-4.5 Preview API Pricing

As of October 10, 2026, GPT-4.5 Preview costs $75.00 per 1M input tokens and $150.00 per 1M output tokens on Azure OpenAI, with cache reads at $37.50 per 1M tokens. It has a 128,000-token context window and returns up to 16,384 tokens per response.

By OpenAIModel ID azure/gpt-4.5-previewPrices updated Checked
Deprecated: Azure OpenAI lists July 14, 2025 as the deprecation date for azure/gpt-4.5-preview.
Input
$75.00 / 1M tokens
Output
$150.00 / 1M tokens
Cache read
$37.50 / 1M tokens
Context window
128,000 tokens
Max output
16,384 tokens
Providers
1
Added to LiteLLM
March 2025

GPT-4.5 Preview pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readBatch inBatch outContext
Azure OpenAIazure/gpt-4.5-preview$75.00$150.00$37.50$37.50$75.00128K

What GPT-4.5 Preview costs in practice

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

Azure OpenAI$225.00
Azure OpenAI batch$112.50

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

Azure OpenAI$780.00

GPT-4.5 Preview features

Use GPT-4.5 Preview with LiteLLM

Call GPT-4.5 Preview through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="azure/gpt-4.5-preview",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: gpt-4.5-preview
    litellm_params:
      model: azure/gpt-4.5-preview
      api_base: os.environ/AZURE_API_BASE
      api_key: os.environ/AZURE_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gpt-4.5-preview",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GPT-4.5 Preview FAQ

How much does GPT-4.5 Preview cost?

GPT-4.5 Preview costs $75.00 per 1M input tokens and $150.00 per 1M output tokens on Azure OpenAI, with cache reads at $37.50 per 1M tokens. Batch requests cost $37.50 per 1M input tokens and $75.00 per 1M output tokens.

What is the context window of GPT-4.5 Preview?

GPT-4.5 Preview has a 128,000-token context window and returns up to 16,384 tokens per response.

Which providers offer GPT-4.5 Preview?

GPT-4.5 Preview is available from Azure OpenAI through LiteLLM, using the model name azure/gpt-4.5-preview.

How do I call GPT-4.5 Preview with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure/gpt-4.5-preview", 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-4.5 Preview support?

GPT-4.5 Preview supports function calling, parallel tool calls, structured output, image input and prompt caching.

When did LiteLLM add GPT-4.5 Preview?

GPT-4.5 Preview was added to LiteLLM's model price file in March 2025.

Is GPT-4.5 Preview being deprecated?

Azure OpenAI deprecated azure/gpt-4.5-preview on July 14, 2025.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Azure OpenAI.

Provider pages: Azure OpenAI.