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 type | Price per 1M | Notes |
|---|---|---|
| Input | $2.50 | Everything you send, including the system prompt |
| Output | $10.00 | Everything the model generates, reasoning tokens included |
| Cached input | $1.25 | Repeated prefixes served from cache |
| Blended (3:1) | $4.38 | One 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
| Property | Value |
|---|---|
| Context window | 128K tokens |
| Max output | 16K tokens |
| Inputs accepted | text, 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.
| Model | Input | Output | Context | Compare |
|---|---|---|---|---|
| GPT-4.1 | $2.00 | $8.00 | 1M | Head to head |
| OpenAI o4-mini | $1.10 | $4.40 | 200K | Head to head |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K | Head to head |
| Gemini 2.5 Flash | $0.300 | $2.50 | 1M | Head to head |
| Grok 3 mini | $0.300 | $0.500 | 131K | Head to head |
| Codestral | $0.300 | $0.900 | 262K | Head 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.