LiteLLMModels

GPT-5 Pro API Pricing

As of October 10, 2026, GPT-5 Pro costs $15.00 per 1M input tokens and $120.00 per 1M output tokens on OpenAI. It has a 400,000-token context window and returns up to 272,000 tokens per response.

By OpenAIModel ID gpt-5-proPrices updated Checked
Input
$15.00 / 1M tokens
Output
$120.00 / 1M tokens
Context window
400,000 tokens
Max output
272,000 tokens
Providers
2
Added to LiteLLM
October 2025

GPT-5 Pro pricing by provider

5 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputBatch inBatch outContext
OpenAIgpt-5-pro$15.00$120.00$7.50$60.00400K
OpenAIsnapshot 2025-10-06gpt-5-pro-2025-10-06$15.00$120.00$7.50$60.00400K
Azure OpenAIazure/gpt-5-pro$15.00$120.00$7.50$60.00272K
Azure OpenAIeuazure/eu/gpt-5-pro$16.50$132.00$8.25$66.00–
Azure OpenAIusazure/us/gpt-5-pro$16.50$132.00$8.25$66.00–

Other GPT-5 Pro prices on OpenAI

Web search$10.00 per 1K searches

What GPT-5 Pro costs in practice

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

OpenAI$90.00
Azure OpenAI$90.00
OpenAI batch$45.00

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

OpenAI$174.00
Azure OpenAI$174.00

GPT-5 Pro features

Input: text, image. Output: text.

Use GPT-5 Pro with LiteLLM

Call GPT-5 Pro through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/responses. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="gpt-5-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: gpt-5-pro
    litellm_params:
      model: gpt-5-pro
      api_key: os.environ/OPENAI_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-5-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GPT-5 Pro FAQ

How much does GPT-5 Pro cost?

GPT-5 Pro costs $15.00 per 1M input tokens and $120.00 per 1M output tokens on OpenAI. Batch requests cost $7.50 per 1M input tokens and $60.00 per 1M output tokens.

What is the context window of GPT-5 Pro?

GPT-5 Pro has a 400,000-token context window and returns up to 272,000 tokens per response.

Which providers offer GPT-5 Pro?

GPT-5 Pro is available from 2 providers through LiteLLM: OpenAI and Azure OpenAI.

How do I call GPT-5 Pro with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-5-pro", 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 GPT-5 Pro support?

GPT-5 Pro supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.

When did LiteLLM add GPT-5 Pro?

GPT-5 Pro was added to LiteLLM's model price file in October 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: OpenAI, Azure OpenAI.

Provider pages: OpenAI, Azure OpenAI.