Verified 2025-12-12 ยท sourced from OpenAI
GPT-5.2 Token Calculator & Cost Guide
Estimate OpenAI GPT-5.2 API usage in dollars before you send a single request. Standard pricing is $1.75 per million input tokens and $14.00 per million output tokens with a 400K token context window.
Context window
400,000 tokens
Input price
$1.75 / 1M
Output price
$14.00 / 1M
Cached input
$0.175 / 1M
Usage scenarios
Compare standard and cached pricing (where available) across common workloads.
| Scenario | Tokens in | Tokens out | Total tokens | Standard cost | Cached cost |
|---|---|---|---|---|---|
Quick chat reply Single user question with a short assistant answer | 650 | 220 | 870 | $0.0042 | $0.0032 |
Coding assistant session Multi-turn pair programming exchange (โ6 turns) | 2,600 | 1,400 | 4,000 | $0.0241 | $0.0201 |
Knowledge base response Retrieval-augmented answer referencing multiple passages | 12,000 | 3,000 | 15,000 | $0.0630 | $0.0441 |
Near-max context run Large document processing approaching the 400K token limit | 352,000 | 48,000 | 400,000 | $1.29 | $0.734 |
Daily & monthly budgeting
Translate usage into predictable operating expenses across popular deployment sizes.
| Profile | Requests/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Team pilot | 25 | 75,000 | $0.438 | $13.13 | $0.359 | $10.76 |
| Product launch | 100 | 500,000 | $2.71 | $81.38 | $2.16 | $64.84 |
| Enterprise scale | 500 | 3,000,000 | $17.50 | $525.00 | $14.35 | $430.50 |
Pricing notes
- ๐ Latest GPT-5 flagship model (Dec 2025)
- 400K context window, 128K max output
- Cached input pricing: 90% discount at $0.175 per 1M tokens
- 40% higher price than GPT-5.1, but improved reasoning capabilities
Frequently asked questions
How much does GPT-5.2 cost per 1,000 tokens?
At the published rates of $1.75 per million input tokens and $14.00 per million output tokens, a typical 1,000 token request (โ70% input, 30% output) costs about $0.0054.
Does GPT-5.2 offer cached input discounts?
GPT-5.2 drops input costs to $0.175 per million cached tokens. Using cached contexts, that same 1,000 token call totals $0.0043, a significant saving for chatbots and RAG systems.
What is the context window for GPT-5.2?
GPT-5.2 supports up to 400,000 tokens (400K), allowing large prompts and retrieval-augmented payloads in a single call.
How fresh is the GPT-5.2 pricing data?
Pricing is sourced from https://platform.openai.com/docs/pricing and was last verified on 2025-12-12. The calculator updates automatically when models.json is refreshed.