BroadRouter

GPT-5.2 API pricing

Updated

Among the 3 providers we checked (prices read 2026-11-14), 3 tie for the lowest blended standard price for GPT-5.2; OpenAI charges USD 1.75 per 1M input tokens and USD 14 per 1M output tokens. The median across 3 standard prices is USD 1.75 / USD 14. That is OpenAI's own API. Each price is read from the provider's own pricing page.

OpenAI · slug gpt-5.2 · 3 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-14. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2026-01-02 (4 archived price points, 0 list-price changes): LLM API price history.

What does OpenAI charge for GPT-5.2?

Input
USD 1.75
Cached input
USD 0.175
Output
USD 14
Blended 3:1
USD 4.813

USD per 1M tokens on OpenAI, model gpt-5.2, standard tier. Source, checked 2026-11-14.

Other OpenAI tiers: batch USD 0.875 / USD 7 · flex / spot USD 0.875 / USD 7 · fast USD 3.50 / USD 28.

Is a host cheaper than OpenAI? They tie. DigitalOcean and OpenAI's own API both work out at USD 4.813 per 1M tokens on the 3:1 blend.

GPT-5.2 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

GPT-5.2 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1OpenAI tied cheapest maker
gpt-5.2
Notes and source quote
“| gpt-5.2 | $1.75 | $14.00 | $0.175 |”
USD 1.75USD 0.175USD 14USD 4.813not statednot statedOpenAI page
checked 2026-11-14
re-checked 2026-11-16
2DigitalOcean tied cheapest
Notes and source quote
“GPT-5.2 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.75$14.00$0.175”
USD 1.75USD 0.175USD 14USD 4.813not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
3Microsoft Azure tied cheapest
Notes and source quote

Azure OpenAI Global (global standard) deployment.

“GPT-5.2 Global Input: $1.75 | Cached Input: $0.18 | Output: $14”
USD 1.75USD 0.18USD 14USD 4.813not statednot statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16
—OpenAI maker batch
gpt-5.2
Notes and source quote

Batch API (asynchronous).

“| gpt-5.2 | $0.875 | $7.00 | $0.0875 |”
USD 0.875USD 0.0875USD 7USD 2.406not statednot statedOpenAI page
checked 2026-11-14
re-checked 2026-11-16
—OpenAI maker flex / spot
gpt-5.2
Notes and source quote

Flex processing.

“| gpt-5.2 | $0.875 | $7.00 | $0.0875 |”
USD 0.875USD 0.0875USD 7USD 2.406not statednot statedOpenAI page
checked 2026-11-14
re-checked 2026-11-16
—DigitalOcean flex / spot
Notes and source quote
“GPT-5.2 — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$0.875$7.00$0.0875”
USD 0.875USD 0.0875USD 7USD 2.406not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
—Microsoft Azure priority
Notes and source quote

Azure OpenAI Global deployment, "Priority Processing (1M Tokens)" column.

“GPT-5.2 Global Input: $3.50 | Cached Input: $0.35 | Output: $28”
USD 3.50USD 0.35USD 28USD 9.625not statednot statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16
—OpenAI maker fast
gpt-5.2
Notes and source quote

Fast mode (formerly Priority processing).

“| gpt-5.2 | $3.50 | $28.00 | $0.35 |”
USD 3.50USD 0.35USD 28USD 9.625not statednot statedOpenAI page
checked 2026-11-14
re-checked 2026-11-16
—DigitalOcean fast
Notes and source quote
“GPT-5.2 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$3.50$28.00$0.35”
USD 3.50USD 0.35USD 28USD 9.625not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does GPT-5.2 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on GPT-5.2, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
OpenAI (maker)USD 324.45USD 516.60USD 2,000
DigitalOceanUSD 324.45USD 516.60USD 2,000
Microsoft AzureUSD 324.72USD 516.96USD 2,008

For the support chatbot, the cheapest price (OpenAI and 1 other, tied, USD 324.45 a month) saves USD 0 against the median (USD 324.45). For the coding agent the gap is USD 0 a month.

Which GPT-5.2 provider is cheapest for your traffic?

All 3 providers charge the same standard price, USD 1.75 input and USD 14 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.

GPT-5.2: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
OpenAI (maker)USD 4.813 cheapestUSD 4.222 cheapestUSD 3.749 cheapest
DigitalOceanUSD 4.813 cheapestUSD 4.222 cheapestUSD 3.749 cheapest
Microsoft AzureUSD 4.813 cheapestUSD 4.224USD 3.753

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

All 3 providers publish a cached-input price below the input price: OpenAI (90% off), DigitalOcean (90% off), Microsoft Azure (90% off).

No provider states a context window for GPT-5.2 on its pricing page.

Estimate your own bill

The OpenAI models whose cheapest standard price is closest to GPT-5.2's (USD 4.813 blended):

OpenAI models priced closest to GPT-5.2
ModelCheapest inputCheapest outputMax contextProviders
GPT-5.3 CodexUSD 1.75USD 14—3
GPT-5.6 TerraUSD 2USD 121,050,0006
GPT-4oUSD 2.50USD 10—2
GPT-5.4USD 2.50USD 151,050,0004
GPT-6 SolUSD 2USD 101,050,0006
GPT-6.1 SolUSD 2USD 101,050,0006

Priced closest from other makers: Gemini 3.1 Pro Preview (Google, USD 4.50) · Claude Sonnet 5 (Anthropic, USD 4) · Claude Sonnet 5.5 (Anthropic, USD 4).

Compare GPT-5.2 with

Also compared: vs GPT-5.4 · vs GPT-5 (2025-08-07).

Every GPT-5.2 price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the GPT-5.2 API cost per token?

From USD 1.75 per 1M input tokens (USD 0.00000175 per token) and USD 14 per 1M output tokens (USD 0.000014 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 1.75 input and USD 14 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for GPT-5.2?

Among the 3 providers we checked (prices read 2026-11-14), 3 are tied for the lowest price: OpenAI, DigitalOcean and Microsoft Azure, each USD 4.813 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 1.75 (OpenAI and 2 others, tied); for output alone, USD 14 (OpenAI and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is GPT-5.2 cheaper from a host than from OpenAI?

They tie. DigitalOcean and OpenAI's own API both work out at USD 4.813 per 1M tokens on the 3:1 blend.

Does GPT-5.2 have cached input pricing?

All 3 standard prices include one. The lowest is USD 0.175 per 1M at OpenAI; the median is USD 0.175. Providers without one bill cached input at the input price. What cached input means.

How much does a coding agent cost per month on GPT-5.2?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 2,000 a month at OpenAI, USD 2,000 at the median price and USD 2,008 at Microsoft Azure. Try your own numbers.

Is there a batch, flex or priority price for GPT-5.2?

Yes: batch from OpenAI at USD 0.875 / USD 7; flex / spot from OpenAI at USD 0.875 / USD 7; priority from Microsoft Azure at USD 3.50 / USD 28; fast from OpenAI at USD 3.50 / USD 28 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is GPT-5.2 free to use through an API?

No provider in our data lists a free price for GPT-5.2 as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity