OpenAI: gpt-5.2

proprietary

GPT-5.2 is our previous flagship model for complex professional work. We recommend using the latest GPT-6 Astra. Learn more on the Model guidance page. Reasoning.effort supports: none (default), low, medium, high and xhigh.

Intelligence
Reasoning
Speed
Context
400K
Max output
128K
Input price
$1.75/1M tokens
Output price
$14/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Model IDopenai/gpt-5.2
Creator OpenAI
Familygpt-5.2
Licenseproprietary
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window400K tokens
Max input—
Max output128K tokens
Reasoning tokensYes
Knowledge cutoff
Release date
Sourceofficial

Pricing

Input
$1.75
Output
$14
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: gpt-5.2

ModelContextMax outPricing
Azure OpenAI: gpt-5.2-chat——$1.75$14
Azure OpenAI: gpt-5.2-codex——$1.75$14
Azure OpenAI: gpt-5.2——$1.75$14
OpenAI: gpt-5.2-20251211400K128K$1.75$14
OpenAI: gpt-5.2-chat-20251211——$1.75$14
OpenAI: gpt-5.2-chat-latest128K16K$1.75$14
OpenAI: gpt-5.2-chat——$1.75$14
OpenAI: gpt-5.2-codex-20260114——$1.75$14
OpenAI: gpt-5.2-codex400K128K$1.75$14
OpenAI: gpt-5.2400K128K$1.75$14
OpenRouter: openai/gpt-5.2-20251211——$1.75$14
OpenRouter: openai/gpt-5.2-chat-20251211——$1.75$14
OpenRouter: openai/gpt-5.2-chat-latest——$1.75$14
OpenRouter: openai/gpt-5.2-chat——$1.75$14
OpenRouter: openai/gpt-5.2-codex-20260114——$1.75$14
OpenRouter: openai/gpt-5.2-codex——$1.75$14
OpenRouter: openai/gpt-5.2——$1.75$14
OpenAI: gpt-5.2-pro-20251211400K128K$21$168
OpenAI: gpt-5.2-pro400K128K$21$168
OpenRouter: openai/gpt-5.2-pro-20251211——$21$168
OpenRouter: openai/gpt-5.2-pro——$21$168

API

GET/v1/models/cloudflare-ai-gateway/openai/gpt-5.2

OpenAI: gpt-5.2

openai/gpt-5.2

GPT-5.2 is our previous flagship model for complex professional work. We recommend using the latest GPT-6 Astra. Learn more on the Model guidance page. Reasoning.effort supports: none (default), low, medium, high and xhigh.

Changes · 3 entries
openai/gpt-5.2update1cd659eMar 24, 2026, 04:19 AM
modalitiesinput["text"]output["text"]
openai/gpt-5.2update2b100acMar 23, 2026, 05:30 AM
model_typechat
openai/gpt-5.2create7a4f1f6Mar 22, 2026, 05:43 AM