What can GPT-5.2 Chat do?

GPT-5.2 Chat is a multimodal AI model in the gpt-codex family with a 128K token context window. It supports reasoning. It supports tool calling and function calling. It supports structured output (JSON mode).

How much does GPT-5.2 Chat cost?

Input pricing starts at $1.75 per million tokens. Output is $14.00 per million tokens. Cached input is $0.17 per million tokens. 8 provider(s) currently offer this model.

Where can I access GPT-5.2 Chat?

GPT-5.2 Chat is developed by OpenAI and available through 8 provider(s), including Azure, Merge Gateway. The model has closed weights. Verified: Source-linked

How fast is GPT-5.2 Chat?

GPT-5.2 Chat has a reported throughput of 61.0 tokens per second. Context length: 128000 tokens.

Models / OpenAI

GPT-5.2 Chat

openai/gpt-5.2-chat-latest

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

Input modalitiesT

Output modalitiesT

Source-linkedgpt-codexClosed weightsReleased 2025-12-11

Report data

Context window128K

Maximum output16.384K

Provider offers8

Knowledge cutoff2025-08-31

Capabilities

What this model supports

ReasoningYes

Tool callingYes

Structured outputYes

AttachmentsYes

Temperature controlNo

Open weightsNo

Creator: OpenAI
Family: gpt-codex
Modalities: Image, Text
License: Not documented
Release date: 2025-12-11
Model ID: openai/gpt-5.2-chat-latest

Market availability

Provider pricing

Report price →

Providers offering GPT-5.2 Chat
Provider	Provider model ID	Context	Input / 1M	Output / 1M	Cached / 1M	Features	All pricing
Azure	`gpt-5.2-chat`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	R T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }
Merge Gateway	`openai/gpt-5.2-chat-latest`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	R T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }
OrcaRouter	`openai/gpt-5.2-chat-latest`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	R T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }
LLM Gateway	`gpt-5.2-chat-latest`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	R T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }
OpenAI	`gpt-5.2-chat-latest`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	R T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }
Requesty	`openai/gpt-5.2-chat`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	R T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }
OpenRouter	`openai/gpt-5.2-chat`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	· T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }
Azure Cognitive Services	`gpt-5.2-chat`	128K	$1.75 if offer.cost.input is defined else '—'}}	$14 if offer.cost.output is defined else '—'}}	$0.175 if offer.cost.cache_read is defined else '—'}}	R T S	View { "cache_read": 0.175, "input": 1.75, "output": 14 }