How much does GPT-5.2 cost per million tokens?

$1.75 per million input tokens and $14.00 per million output tokens, as listed on OpenRouter on October 21, 2026.

Does GPT-5.2 support prompt caching?

Yes. OpenRouter lists cached input at $0.175 per million tokens, against $1.75 for uncached input.

Is there a cheaper model as good as GPT-5.2?

Ling 3.1 Flash scores 41.1 on the Artificial Analysis Intelligence Index, within two points of GPT-5.2 or above it, and costs $0.225 per million output tokens.

Has the price of GPT-5.2 changed?

Not since we started recording it daily on October 15, 2026.

GPT-5.2 API pricing

As of October 21, 2026, OpenAI GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens through OpenRouter, with cached input at $0.175 per million.

GPT-5.2 benchmarks and specs · Every OpenAI model's price

Input, per million tokens$1.75
Output, per million tokens$14.00
Cached input, per million$0.175
Context window400K tokens
Max output128K tokens
Output speedNot measured

What a request costs

Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.

Cost of three workloads on GPT-5.2
Workload	Tokens	One request	1,000 requests	Fits the context window
Chat turn	1K input + 500 output tokens	$0.0088	$8.75	Yes
Repository review	50K input + 3K output tokens	$0.130	$129.50	Yes
Agent loop	200K input + 10K output tokens	$0.490	$490.00	Yes
Solved coding task	One SWE-bench Verified attempt, divided by the share that succeed	$1.91	$1910.00

Price history

We read this price every day and have since October 15, 2026. It has not changed yet; any change will be listed here with its date.

October 15, 2026 First recorded: $1.75 input, $14.00 output

Cheaper models as good as GPT-5.2

Models within two points of GPT-5.2 or above it on the Artificial Analysis Intelligence Index, with a lower output price. Cheapest first.

GPT-5.2 pricing questions

How much does GPT-5.2 cost per million tokens?: $1.75 per million input tokens and $14.00 per million output tokens, as listed on OpenRouter on October 21, 2026.
Does GPT-5.2 support prompt caching?: Yes. OpenRouter lists cached input at $0.175 per million tokens, against $1.75 for uncached input.
Is there a cheaper model as good as GPT-5.2?: Ling 3.1 Flash scores 41.1 on the Artificial Analysis Intelligence Index, within two points of GPT-5.2 or above it, and costs $0.225 per million output tokens.
Has the price of GPT-5.2 changed?: Not since we started recording it daily on October 15, 2026.