GPT-4o-mini
OpenAI
OpenAI's most cost-efficient small model delivering intelligent performance at breakthrough pricing. Despite compact size, surpasses GPT-3.5 Turbo across academic benchmarks including 82% on MMLU (textual intelligence), 87% on MGSM (math reasoning), and 87.2% on HumanEval (coding). Features 128K context window and supports both text and vision inputs. Priced at 15 cents per 1M input tokens (60% cheaper than GPT-3.5 Turbo), making it ideal for high-volume applications requiring reliable intelligence without flagship costs.
Strengths
- Exceptional cost-efficiency at $0.15 per 1M input tokens (60% cheaper than GPT-3.5 Turbo)
- Outperforms GPT-3.5 Turbo across all academic benchmarks despite lower cost
- Strong coding performance - 87.2% on HumanEval (vs Gemini Flash 71.5%, Claude Haiku 75.9%)
- 128K context window handles large documents and extended conversations
- Vision support enables multimodal applications at low cost
- Math reasoning - 87% on MGSM (vs Gemini Flash 75.5%, Claude Haiku 71.7%)
- Ideal for high-volume production deployments where cost matters
Caveats
- Lower ceiling than GPT-4o for complex reasoning and creative tasks
- Knowledge cutoff October 2023 same as GPT-4o
- Not ideal for tasks requiring maximum intelligence or nuance
- Vision capabilities less sophisticated than flagship models
- 16K max output tokens standard for the tier
- Vendor
- OpenAI
- Context Window
- 128,000 tokens
- Max Output
- 16,384 tokens
- License
- Proprietary
- Release Date
- 2024-07-18
- Training Cutoff
- 2023-10-01
- Modalities
- textimage
| Benchmark | Score | Max |
|---|---|---|
| MMLU | 82.0 | - |
| MGSM | 87.0 | - |
| HumanEval | 87.2 | - |
| livebench_instruction_following | 69.7 | 100.0 |
| livebench_language | 32.5 | 100.0 |
| livebench_coding | 43.2 | 100.0 |
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
$0.15 per 1M input tokens, $0.60 per 1M output tokens (60% cheaper than GPT-3.5 Turbo)