GPT-4o
API ID gpt-4o
gpt-4o is an OpenAI model, released May 2024. It has a 128,000-token context window and up to 16,384 output tokens. It takes image input and supports function calling and structured outputs. Standard price: from $2.50 input and from $10.00 output per 1M tokens.
- Status
- Active
- Released
- May 2024
- Shutdown
- none announced
- Replacement
- —
No deprecation or shutdown date has been announced as of October 15, 2026.
Benchmarks
Scores as each source published themComparing with GPT-4 1106 Vision Preview, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features
Arena
| Arena | GPT-4o | GPT-4 1106 Vision Preview | Change | Rank | Date | Source |
|---|---|---|---|---|---|---|
TextBy category
| 1336 ±4 | not rated | 239 of 415 45,499 votes | Oct 13, 2026 | source | |
| Text: Coding | 1360 ±8 | not rated | 258 of 410 7,318 votes | Oct 13, 2026 | source | |
| Vision | 1118 ±12 | not rated | 132 of 165 3,376 votes | Oct 9, 2026 | source |
Rated as gpt-4o-2024-08-06. Ratings come from people voting between two anonymous answers; Text and Vision are style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.
Epoch AI
| Benchmark | GPT-4o | GPT-4 1106 Vision Preview | Change | Setting | Run | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tiers 1-3 | 0.4% | not run | Aug 27, 2026 | source | ||
| GPQA Diamond | 49.2% | not run | Jan 27, 2025 | source | ||
| MATH Level 5 | 53.3% | not run | Jan 27, 2025 | source | ||
| OTIS Mock AIME 2024-2025 | 6.4% | not run | Feb 25, 2025 | source | ||
| SimpleQA Verified | 26.0% | not run | Aug 31, 2026 | source |
Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
On cloud platforms
All platform dates| Platform | Platform ID | State | Shutdown | Time left | Replacement | Source |
|---|---|---|---|---|---|---|
| Microsoft Foundryversion 2024-08-06 | gpt-4o | Deprecated | Apr 14, 2027 | 181 days | GPT-5.1gpt-5.1 | source |
| Microsoft Foundryversion 2024-11-20 | gpt-4o | Legacy | Apr 14, 2027 | 181 days | GPT-5.1gpt-5.1 | source |
Read daily from each platform's own pages. The shutdown date and countdown on this page use OpenAI's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.
Alias
All aliasesCurrently points to gpt-4o-2024-08-06 (in place when tracking began (October 7, 2026)).
Features
Compare models| Feature | Value | Since | Source |
|---|---|---|---|
| Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup. | Supported | in place when tracking began (October 6, 2026) | source |
| Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result. | Supported | in place when tracking began (October 6, 2026) | source |
| Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests. | Supported | in place when tracking began (October 6, 2026) | source |
| Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read. | Supported | in place when tracking began (October 6, 2026) | source |
| Fine-tuningYou can train your own version of the model on your examples through the company's API, then call it like any other model. | Supported | in place when tracking began (October 6, 2026) | source |
| Built-in web searchThe company's API can search the web for the model during a request and cite its sources; you don't need a search service of your own. | Supported | in place when tracking began (October 6, 2026) | source |
| Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word. | 128,000 tokens | in place when tracking began (October 6, 2026) | source |
| Max output tokensThe longest reply the model can write in one response, in tokens. A token is about three-quarters of an English word. | 16,384 tokens | in place when tracking began (October 6, 2026) | source |
Not published by OpenAI: Prompt caching, PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.
Price history
USD per 1M tokens, standard tierWe started recording this model's prices on Oct 1, 2026. The history grows with each daily check.
Show as a table
| From | Type | Price |
|---|---|---|
| Oct 1, 2026 | Input | $2.50 |
| Oct 1, 2026 | Output | $10.00 |
Prices
USD per 1M tokens, every type and band, by tier| Type | Band | Price $/1M | In effect |
|---|---|---|---|
| Standard | |||
| input | short context | $2.50 | |
| cached input | short context | $1.25 | |
| output | short context | $10.00 | |
| Batch | |||
| input | short context | $1.25 | |
| output | short context | $5.00 | |
| Fast | |||
| input | short context | $4.25 | |
| cached input | short context | $2.125 | |
| output | short context | $17.00 | |
Changelog
Changes we detected on OpenAI's pagesNo changes recorded yet.
Email alerts
Get an email if gpt-4o changes
We'll email you the same morning we spot a deprecation notice, a new or moved shutdown date, a price change, or the model leaving OpenAI's model list.
No password: one email to confirm, and you can unsubscribe any time. Privacy
Last checked · Sources: OpenAI deprecations, OpenAI pricing, OpenAI models