LiteLLMModels

GPT-5.2 API Pricing

As of October 10, 2026, GPT-5.2 costs $1.75 per 1M input tokens and $14.00 per 1M output tokens on OpenAI, with cache reads at $0.175 per 1M tokens. It has a 272,000-token context window and returns up to 128,000 tokens per response.

By OpenAIModel ID gpt-5.2Prices updated Checked
Input
$1.75 / 1M tokens
Output
$14.00 / 1M tokens
Cache read
$0.175 / 1M tokens
Context window
272,000 tokens
Max output
128,000 tokens
Providers
6
Added to LiteLLM
December 2025

GPT-5.2 pricing by provider

10 listings across 6 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeBatch inBatch outContext
OpenAIgpt-5.2$1.75$14.00$0.175–$0.875$7.00272K
OpenAIsnapshot 2025-12-11gpt-5.2-2025-12-11$1.75$14.00$0.175–$0.875$7.00272K
Azure OpenAIazure/gpt-5.2$1.75$14.00$0.175–$0.875$7.00272K
Azure OpenAIsnapshot 2025-12-11azure/gpt-5.2-2025-12-11$1.75$14.00$0.175–$0.875$7.00272K
ChatGPT Subscriptionchatgpt/gpt-5.2––––––128K
Databricksdatabricks/databricks-gpt-5-2$1.75$14.00$0.175$1.75––272K
GMI Cloudgmi/openai/gpt-5.2$1.75$14.00––––400K
Perplexityperplexity/openai/gpt-5.2$1.75$14.00$0.175––––
Azure OpenAIeuazure/eu/gpt-5.2$1.925$15.40$0.1925–$0.9625$7.70–
Azure OpenAIusazure/us/gpt-5.2$1.925$15.40$0.1925–$0.9625$7.70–

Other GPT-5.2 prices on OpenAI

Priority input$3.50 per 1M tokens
Priority output$28.00 per 1M tokens
Flex input$0.875 per 1M tokens
Flex output$7.00 per 1M tokens
Web search$10.00 per 1K searches

What GPT-5.2 costs in practice

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

OpenAI$10.50
Azure OpenAI$10.50
Databricks$10.50
GMI Cloud$10.50
OpenAI batch$5.25

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

OpenAI$20.30
Azure OpenAI$20.30
Databricks$20.30
GMI Cloud$20.30

GPT-5.2 features

Input: text, image. Output: text, image.

Use GPT-5.2 with LiteLLM

Call GPT-5.2 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="gpt-5.2",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: gpt-5.2
    litellm_params:
      model: gpt-5.2
      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-5.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GPT-5.2 FAQ

How much does GPT-5.2 cost?

GPT-5.2 costs $1.75 per 1M input tokens and $14.00 per 1M output tokens on OpenAI, with cache reads at $0.175 per 1M tokens. Batch requests cost $0.875 per 1M input tokens and $7.00 per 1M output tokens.

What is the context window of GPT-5.2?

GPT-5.2 has a 272,000-token context window and returns up to 128,000 tokens per response.

Which providers offer GPT-5.2?

GPT-5.2 is available from 6 providers through LiteLLM: OpenAI, Azure OpenAI, ChatGPT Subscription, Databricks, GMI Cloud and Perplexity.

How do I call GPT-5.2 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-5.2", 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-5.2 support?

GPT-5.2 supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.

When did LiteLLM add GPT-5.2?

GPT-5.2 was added to LiteLLM's model price file in December 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, ChatGPT Subscription, Databricks, GMI Cloud, Perplexity.

Provider pages: OpenAI, Azure OpenAI, ChatGPT Subscription, Databricks, GMI Cloud, Perplexity.