GPT-4o pricing

The natively multimodal model that set the mid-market price for over a year. Now more expensive than newer models that outperform it, but still the default in a great deal of shipped code.

List prices checked

By OpenAI · Balanced tier

Token pricing

Per million tokens, from the official price list.

Token typePrice per 1MNotes
Input$2.50Everything you send, including the system prompt
Output$10.00Everything the model generates, reasoning tokens included
Cached input$1.25Repeated prefixes served from cache
Blended (3:1)$4.38One number for ranking, at three input tokens per output token

Source: OpenAI pricing (May 2026). Published list prices only — committed-use discounts, regional variation, and per-request charges are not included. Not yet independently re-checked against the vendor’s page.

Capabilities

PropertyValue
Context window128K tokens
Max output16K tokens
Inputs acceptedtext, image, audio
Cost to fill the context once$0.32

What it costs per month

Token prices applied to three workload shapes. Input-heavy and output-heavy workloads rank models very differently.

In-app chat assistant

A support or help assistant handling a few thousand conversations a month, with short prompts and short answers.

$100/mo

  • 20M input tokens$50
  • 5M output tokens$50
  • If fully cached$75

RAG over documents

Retrieval-augmented answering where each request stuffs several retrieved passages into the prompt, so input dominates.

$900/mo

  • 300M input tokens$750
  • 15M output tokens$150
  • If fully cached$525

Coding agent

An agentic loop that reads files and writes patches, generating heavy output and re-sending large context on every turn.

$2,000/mo

  • 400M input tokens$1,000
  • 100M output tokens$1,000
  • If fully cached$1,500

GPT-4o vs other balanced models

Same capability tier, ranked by blended token price.

ModelInputOutputContextCompare
GPT-4.1$2.00$8.001MHead to head
OpenAI o4-mini$1.10$4.40200KHead to head
Claude Haiku 4.5$1.00$5.00200KHead to head
Gemini 2.5 Flash$0.300$2.501MHead to head
Grok 3 mini$0.300$0.500131KHead to head
Codestral$0.300$0.900262KHead to head

Questions about pricing

How much does the GPT-4o API cost in 2026?
$2.50 per million input tokens and $10.00 per million output tokens, from OpenAI's published pricing. The table above converts that into a monthly figure for three common workloads.
What is the GPT-4o context window?
128K tokens, with up to 16K tokens of output per request. Filling the window costs whatever that many input tokens cost — at $2.50 per million, a single full-context request runs about $0.32.
Does GPT-4o support prompt caching?
Yes. Cached input is billed at $1.25 per million tokens, roughly 2× cheaper than uncached input. For an agent that resends the same system prompt and file context on every turn, that discount usually matters more than the headline rate does.
Is GPT-4o cheaper than the alternatives?
On a blended 3:1 input-to-output basis it works out at $4.38 per million tokens. The comparison table below ranks it against the other balanced models in the dataset, and the head-to-head pages model both against identical workloads.

Keep comparing