GPT-4o (2024-08-06)
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format.
text + image + file → text · made by OpenAI
Sold by 5 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | standard | $2.75per Mtok in$11per Mtok out$1.38per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| ElectronHub aggregator | standard | $2per Mtok in$8per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Nous Research aggregator | standard | $2.5per Mtok in$10per Mtok out$1.25per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter aggregator | standard | $2.5per Mtok in$10per Mtok out$1.25per Mtok cachedopenrouter.ai · read 2026-08-24 |
| Requesty aggregator | openai | $2.5per Mtok in$10per Mtok out$1.25per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
Measured 20 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 7thof 50 | Video mme — Epoch AI | Overall (no subtitles) | 0.719 |
| 12thof 15 | Cad eval — Epoch AI | Overall pass (%) | 0.26 |
| 16thof 217 | Mmlu — Epoch AI | EM | 0.843 |
| 22ndof 54 | Live bench — Epoch AI | Global average | 55.33 |
| 24thof 28 | LiveCodeBench Leaderboard (default window 8/1/2024–5/1/2025, 454 problems) | Pass@1 | 29.5 |
| 42ndof 50 | Metr time horizons — Epoch AI | average_score | 0.338 |
| 53rdof 69 | Aider polyglot coding leaderboard | Percent correct | 23.1 |
| 54thof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 9.6 |
| 56thof 72 | Aider polyglot — Epoch AI | Percent correct | 23.1 |
| 58thof 108 | Math level 5 — Epoch AI | mean_score | 53.276 |
| 62ndof 80 | Simpleqa verified — Epoch AI | mean_score | 26 |
| 96thof 101 | FrontierMath (Tiers 1-3) | mean_score | 0.345 |
| 100thof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.178 |
| 105thof 106 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score | 0.351 |
| 118thof 152 | LMArena · Vision | Score (Elo) | 1119 |
| 119thof 222 | Chess puzzles — Epoch AI | mean_score | 13 |
| 228thof 402 | LMArena · Text | Score (Elo) | 1335 |
| 230thof 313 | GPQA Diamond | mean_score | 49.211 |
| 252ndof 290 | OTIS Mock AIME 2024-2025 | mean_score | 6.389 |
| 535thof 656 | Epoch capabilities index — Epoch AI | ECI Score | 128.78 |
About
GPT-4o (2024-08-06) — a text model from OpenAI, sold by 5 companies from $2 in and $8 out per million tokens, placed 16th of 217 on Mmlu — Epoch AI.
It takes text, images and files and returns text, with a context window of 128,000 tokens. It was published in August 2024, trained on material up to September 2023. Its sellers say it can call a tool. The catalogue files it under reasoning, code and agents. Five companies sell it. The cheapest is $2 in and $8 out per million tokens at ElectronHub. Beside the standard rate there is a separately routed lane. It has been measured on 20 boards, and stands best at 16th of 217 on Mmlu — Epoch AI.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 128,000 tokens
- Longest answer
- 16,384 tokens
- Published
- August 2024
- Knowledge to
- September 2023
- Licence
- not read
- Sellers
- 5
- Maker's own price
- not read
- Price
- $2 in and $8 out per million tokens — ElectronHub
- Boards
- 20
- Best place
- 16th of 217 — Mmlu — Epoch AI
Known as 2 names
GPT-4O-2024-08-06openai/gpt-4o-2024-08-06