Last verified 2025-11-26 (left) · 2025-12-12 (right)

GPT-5.1 vs GPT-5.2 — Pricing & Capability Comparison

GPT-5.1 charges $1.25 per million input tokens and $10.00 per million output tokens. GPT-5.2 comes in at $1.75 / $14.00. Context windows span 200K vs 400K tokens respectively.

TL;DR — Quick Comparison

  • GPT-5.1 is cheaper overall: $11.25 per 1M tokens (in+out) vs $15.75 for GPT-5.2 — saves $4.50 per 1M tokens
  • Input pricing: GPT-5.1 $1.25/1M vs GPT-5.2 $1.75/1M
  • Output pricing: GPT-5.1 $10.00/1M vs GPT-5.2 $14.00/1M
  • Context window: GPT-5.2 offers more (400K vs 200K)
  • Use our calculator below to estimate costs for your specific usage pattern

Input price (per 1M)

GPT-5.1

$1.25

GPT-5.2

$1.75

GPT-5.1 leads here

Output price (per 1M)

GPT-5.1

$10.00

GPT-5.2

$14.00

GPT-5.1 leads here

Context window

GPT-5.1

200,000 tokens

GPT-5.2

400,000 tokens

GPT-5.2 leads here

Cached input

GPT-5.1

$0.125

GPT-5.2

$0.175

GPT-5.1 leads here

Cost comparison for 10K-token workloads

Side-by-side pricing for identical workloads (10,000 total tokens per request) across different distributions.

ScenarioGPT-5.1GPT-5.2GPT-5.1 cachedGPT-5.2 cached
Balanced conversation
50% input · 50% output
$0.0563$0.0788$0.0506$0.0709
Input-heavy workflow
80% input · 20% output
$0.0300$0.0420$0.0210$0.0294
Generation heavy
30% input · 70% output
$0.0738$0.103$0.0704$0.0985
Cached system prompt
90% cached input · 10% fresh output
$0.0212$0.0297$0.0111$0.0156

Frequently asked questions

Which is cheaper: GPT-5.1 or GPT-5.2?

GPT-5.1 is cheaper for input tokens at $1.25 per 1M tokens compared to $1.75. For output, GPT-5.1 costs $10.00 per 1M tokens versus $14.00 for GPT-5.2.

What is the cost per 1M tokens for GPT-5.1?

GPT-5.1 pricing: $1.25 per 1M input tokens and $10.00 per 1M output tokens. Context window: 200,000 tokens.

What is the cost per 1M tokens for GPT-5.2?

GPT-5.2 pricing: $1.75 per 1M input tokens and $14.00 per 1M output tokens. Context window: 400,000 tokens.

How much does it cost per 1K tokens?

Per 1K tokens: GPT-5.1 costs $0.0013 input / $0.0100 output. GPT-5.2 costs $0.0018 input / $0.0140 output. This is useful for calculating small-scale usage costs.

Which model supports a larger context window?

GPT-5.2 offers 400,000 tokens (400K) versus 200K for GPT-5.1.

What is the estimated monthly cost for typical usage?

For a typical workload of 10M input + 2M output tokens per month: GPT-5.1 would cost approximately $32.50, while GPT-5.2 would cost $45.50. GPT-5.1 is more economical for this usage pattern.

Do these models support prompt caching?

GPT-5.1 supports prompt caching at $0.125 per 1M cached tokens, reducing costs for repeated context by up to 90%. GPT-5.2 supports caching at $0.175 per 1M tokens, saving up to 90%.

Which model is best for my use case?

Choose GPT-5.1 for cost-sensitive applications with high input volume. Choose GPT-5.2 if you need 400K context for long documents or conversations. Consider prompt caching if you have repeated context. Use our token calculator to model your specific usage pattern.

Related resources

GPT-5.1 vs GPT-5.2 Pricing (2025) — Cost per 1M Tokens Comparison | LLM Practical Experience Hub