GPT-4o-mini
ModelActiveby OpenAI · family “gpto-mini”
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable... (description from the OpenRouter listing)
in: textin: imagein: fileout: textTool useStructured output
Epoch Capabilities Index
126.6 #172 of 268
90% CI 119.7 – 128.7
Released
18 Jul 2024
Context window
128K tokens
Max output
16K tokens
Input $ / 1M tokens
$0.15
Output $ / 1M tokens
$0.60
Cached input $ / 1M
$0.075
Each benchmark shown separately with its own source
Benchmark results (20)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 10.4% | 15% | — | — | External ↗ |
| DTBench | reasoning | 54.4% | 55% | — | — | External ↗ |
| Mystery Game Puzzles | games | 12.0% ±3.3 | 14% | — | 27 Aug 2026 | Epoch ↗ |
| FrontierMath-Tiers-1-3-v2-Private | math | 0.7% ±0.5 | 1% | — | 27 Aug 2026 | Eval log ↗ |
| Chess Puzzles | games | 0.0% | 0% | — | 15 Jul 2026 | Eval log ↗ |
| SimpleQA Verified | knowledge | 8.3% ±0.9 | 11% | — | 31 Aug 2026 | Eval log ↗ |
| ARC-AGI-2 | reasoning | 0.0% | 0% | — | — | External ↗ |
| GeoBench | multimodal | 64.0% | 73% | — | — | External ↗ |
| Lech Mazur Writing | other | 67.2% | 78% | — | — | External ↗ |
| VPCT | multimodal | 34.0% | 37% | — | — | External ↗ |
| WeirdML | coding | 11.8% ±0.0 | 13% | — | — | External ↗ |
| Aider polyglot | coding | 3.6% | 4% | — | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 6.9% ±2.7 | 7% | — | 30 Jul 2025 | Eval log ↗ |
| Balrog | games | 17.4% | 25% | — | — | External ↗ |
| SimpleBench | reasoning | 10.7% | 13% | — | — | External ↗ |
| GPQA diamond | science | 37.7% ±2.4 | 39% | — | 27 Jan 2025 | Eval log ↗ |
| GSM8K | math | 91.3% | 97% | — | — | External ↗ |
| MATH level 5 | math | 52.6% ±1.1 | 54% | — | 27 Jan 2025 | Epoch ↗ |
| MMLU | knowledge | 81.8% | 93% | — | — | External ↗ |
| PIQA | other | 88.7% | 100% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
13 recorded prices on 1 Oct 2025 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 7h ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates GPT-4o-miniEpoch AI Benchmarking Hub
- BenchmarkEpoch AI evaluates GPT-4o-miniEpoch AI Benchmarking Hub