BroadRouter

GPT-4o API pricing

Updated

Among the 2 providers we checked (prices read 2026-11-14), 2 tie for the lowest blended standard price for GPT-4o; OpenAI charges USD 2.50 per 1M input tokens and USD 10 per 1M output tokens. The median across 2 standard prices is USD 2.50 / USD 10. That is OpenAI's own API. Each price is read from the provider's own pricing page.

OpenAI · slug gpt-4o · 2 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 2024-06-01 (14 archived price points, 1 list-price change): LLM API price history.

What does OpenAI charge for GPT-4o?

Input
USD 2.50
Cached input
USD 1.25
Output
USD 10
Blended 3:1
USD 4.375

USD per 1M tokens on OpenAI, model gpt-4o, standard tier. Source, checked 2026-11-14.

Other OpenAI tiers: batch USD 1.25 / USD 5 · fast USD 4.25 / USD 17.

Is a host cheaper than OpenAI? They tie. DigitalOcean and OpenAI's own API both work out at USD 4.375 per 1M tokens on the 3:1 blend.

GPT-4o 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-4o API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1OpenAI tied cheapest maker
gpt-4o
Notes and source quote
“| gpt-4o | $2.50 | $10.00 | $1.25 |”
USD 2.50USD 1.25USD 10USD 4.375not statednot statedOpenAI page
checked 2026-11-14
re-checked 2026-11-16
2DigitalOcean tied cheapest
Notes and source quote
“GPT-4o — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.50$10.00$1.25”
USD 2.50USD 1.25USD 10USD 4.375not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
—OpenAI maker batch
gpt-4o
Notes and source quote

Batch API (asynchronous).

“| gpt-4o | $1.25 | $5.00 | - |”
USD 1.25not publishedUSD 5USD 2.188not statednot statedOpenAI page
checked 2026-11-14
re-checked 2026-11-16
—OpenAI maker fast
gpt-4o
Notes and source quote

Fast mode (formerly Priority processing).

“| gpt-4o | $4.25 | $17.00 | $2.125 |”
USD 4.25USD 2.125USD 17USD 7.438not statednot statedOpenAI page
checked 2026-11-14
re-checked 2026-11-16
—DigitalOcean fast
Notes and source quote
“GPT-4o — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$4.25$17.00$2.125”
USD 4.25USD 2.125USD 17USD 7.438not 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-4o 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-4o, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
OpenAI (maker)USD 337.50USD 660.00USD 3,488
DigitalOceanUSD 337.50USD 660.00USD 3,488

For the support chatbot, the cheapest price (OpenAI and 1 other, tied, USD 337.50 a month) saves USD 0 against the median (USD 337.50). For the coding agent the gap is USD 0 a month.

Which GPT-4o provider is cheapest for your traffic?

Both providers charge the same standard price, USD 2.50 input and USD 10 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.

GPT-4o: 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 4.375 cheapestUSD 3.906 cheapestUSD 3.531 cheapest
DigitalOceanUSD 4.375 cheapestUSD 3.906 cheapestUSD 3.531 cheapest

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.

Both providers publish a cached-input price below the input price: OpenAI (50% off), DigitalOcean (50% off).

No provider states a context window for GPT-4o on its pricing page.

What does GPT-4o cost in other languages?

The same text needs a different number of tokens in each language. With the GPT (o200k) tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for GPT-4o:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.533DigitalOcean
Arabic MSAUSD 0.798DigitalOcean
HindiUSD 0.805DigitalOcean
ChineseUSD 1.93DigitalOcean
CodeUSD 0.635DigitalOcean

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Estimate your own bill

The OpenAI models whose cheapest standard price is closest to GPT-4o's (USD 4.375 blended):

OpenAI models priced closest to GPT-4o
ModelCheapest inputCheapest outputMax contextProviders
GPT-5.6 TerraUSD 2USD 121,050,0006
GPT-6 SolUSD 2USD 101,050,0006
GPT-6.1 SolUSD 2USD 101,050,0006
GPT-5.2USD 1.75USD 14—3
GPT-5.3 CodexUSD 1.75USD 14—3
GPT-4.1 (2025-04-14)USD 2USD 8—3

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).

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-4o API cost per token?

From USD 2.50 per 1M input tokens (USD 0.0000025 per token) and USD 10 per 1M output tokens (USD 0.00001 per token) at the lowest standard prices we found. The median of 2 standard prices is USD 2.50 input and USD 10 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-4o?

Among the 2 providers we checked (prices read 2026-11-14), 2 are tied for the lowest price: OpenAI and DigitalOcean, each USD 4.375 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 2.50 (OpenAI and 1 other, tied); for output alone, USD 10 (OpenAI and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is GPT-4o cheaper from a host than from OpenAI?

They tie. DigitalOcean and OpenAI's own API both work out at USD 4.375 per 1M tokens on the 3:1 blend.

Does GPT-4o have cached input pricing?

All 2 standard prices include one. The lowest is USD 1.25 per 1M at OpenAI; the median is USD 1.25. 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-4o?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 3,488 a month at OpenAI, USD 3,488 at the median price and USD 3,488 at DigitalOcean. Try your own numbers.

Is there a batch, flex or priority price for GPT-4o?

Yes: batch from OpenAI at USD 1.25 / USD 5; fast from OpenAI at USD 4.25 / USD 17 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-4o free to use through an API?

No provider in our data lists a free price for GPT-4o 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