GPT-4o (2024-05-13)
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.
text + image + file → text · made by OpenAI
Sold by 8 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | batch | $2.75per Mtok in$8.25per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| OpenAI api | standard | $5per Mtok in$15per Mtok outdevelopers.openai.com · read 2026-08-24 |
| Microsoft Azure AI cloud | standard | $5.5per Mtok in$16.5per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| ElectronHub aggregator | standard | $2.5per Mtok in$10per Mtok outapi.electronhub.ai · read 2026-11-01 |
| Requesty aggregator | openai | $2.5per Mtok in$10per Mtok out$2.5per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Nous Research aggregator | standard | $5per Mtok in$15per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 2 ways | $5per Mtok in$15per Mtok out | |
| OpenRouter aggregator | standard | $5per Mtok in$15per Mtok outopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | azure | $5per Mtok in$15per Mtok outopenrouter.ai · read 2026-11-01 |
Measured 13 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 2ndof 26 | Science qa — Epoch AI | Score | 88.5 |
| 17thof 217 | Mmlu — Epoch AI | EM | 0.842 |
| 19thof 41 | Balrog — Epoch AI | Average progress | 0.323 |
| 35thof 49 | Metr time horizons — Epoch AI | average_score | 0.408 |
| 61stof 108 | Math level 5 — Epoch AI | mean_score | 51.048 |
| 73rdof 92 | Forecastbench — Epoch AI | Overall score | 61.2 |
| 108thof 165 | LMArena · Vision | Score (Elo) | 1162 |
| 128thof 163 | Artificial Analysis · Coding Index | Index | 24.2 |
| 172ndof 197 | Lmca — Epoch AI | Score | 16.59 |
| 174thof 235 | Dtbench — Epoch AI | Accuracy | 64.53 |
| 223rdof 414 | LMArena · Text | Score (Elo) | 1346 |
| 248thof 326 | GPQA Diamond | mean_score | 48.895 |
| 269thof 306 | OTIS Mock AIME 2024-2025 | mean_score | 6.25 |
About
GPT-4o (2024-05-13) — a text model from OpenAI, sold by 6 companies from $2.5 in and $10 out per million tokens, placed 2nd of 26 on Science qa — Epoch AI.
It takes text, images and files and returns text, with a context window of 128,000 tokens. It was published in May 2024, trained on material up to September 2023. Its sellers say it can call a tool. The catalogue files it under reasoning and agents. Six companies sell it. The cheapest is $2.5 in and $10 out per million tokens at ElectronHub. Beside the standard rate there are batch and separately routed lanes. It has been measured on 13 boards, and stands best at 2nd of 26 on Science qa — Epoch AI.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 128,000 tokens
- Longest answer
- 4,096 tokens
- Published
- May 2024
- Knowledge to
- September 2023
- Licence
- not read
- Sellers
- 6
- Price
- $2.5 in and $10 out per million tokens — ElectronHub
- Boards
- 13
- Best place
- 2nd of 26 — Science qa — Epoch AI
Known as 3 names
gpt 4o 0513openai/gpt-4o-2024-05-13gpt-4o-2024-05-13