GPT-4o API pricing
OpenAI's 2024 multimodal model, still available at $2.50 / $10 per 1M tokens as a legacy option. The gpt-4o-2024-05-13 snapshot shuts down on 23 October 2026.
GPT-4o
PreviousPrevious generation. The current replacement is GPT-6.1 Sol at $2.00 / $10.00 per 1M tokens.
What it costs in practice
GPT-4o at list prices, no batch discount.
| 1,000 chat replies1,500 tokens in and 300 out each | $6.75 |
|---|---|
| Summarising 100 long reports20,000 tokens in and 800 out each | $5.80 |
| A month of a coding agent400 tasks, 85% of input cached | $1,158 |
The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Work out AI agent cost on GPT-4o
Details
gpt-4o- The gpt-4o-2024-05-13 snapshot shuts down on 23 October 2026. Later snapshots have no announced shutdown.
Checked 27 Sep 2026 against OpenAI pricing and OpenAI deprecations .
Estimate your monthly cost
List prices, no batch discount
| Model | Input / output per 1M | Per month |
|---|---|---|
| GPT-4o | $2.50 / $10.00 | $45.00 |
Type amounts like 500K, 25M or 2B.
Price GPT-4o in: Token cost calculator · AI agent cost · Token counter
Cheapest in its class
No current general-purpose workhorse model from another family costs meaningfully less than GPT-4o.
Compare GPT-4o with
Side by side: prices, cached and batch rates, and the cost of the same workload.
Compare GPT-4o
No ready-made comparisons for this family yet.
Price history
All changesNo price changes recorded since we began tracking in June 2026.
Every dated price: price records · CSV. Cite as: AI Token Price, GPT-4o pricing, https://aitokenprice.com/pricing/gpt-4o#price-history
OpenAI pricing rules
- Batch and Flex processing cost 50% less.
- For GPT-5.4 and later, prompts longer than 272K tokens are billed at 2× the input price and 1.5× the output price.
- Cached input is billed at a tenth of the input price on most models, and a twentieth on GPT-6.1 Sol.
Questions
How much does GPT-4o cost?
As of 27 Sep 2026, GPT-4o costs $2.50 per million input tokens and $10 per million output tokens, and $1.25 per million cached input tokens. Batch requests cost 50% less. Prices checked 27 Sep 2026.
What is GPT-4o's context window?
128K tokens, with up to 16K tokens of output.
Does GPT-4o support prompt caching?
Yes. Repeated input read from the cache costs $1.25 per million tokens, 50% less than normal input.