GPT-4o-mini
gpt-4o-mini
OpenAI · chat · api · seen 9m ago
Context
128K
Max output
16K
Input $/1M
$0.15
Output $/1M
$0.60
Modalities
text
Released
16 Jul 2024
AI summary
● machine-written
OpenAI releases GPT-4o-mini, a compact multimodal model
GPT-4o-mini is OpenAI's smallest model in the GPT-4o family, supporting text and image inputs with text outputs. Released July 2024, it achieves 82% on MMLU while costing 60% less than GPT-3.5 Turbo. The model is designed for cost-sensitive applications requiring reasonable intelligence across reasoning and coding tasks.
What's new
- Supports both text and image inputs with text outputs
- 128K token context window with up to 16K token output capacity
- Priced at $0.15 per million input tokens, $0.60 per million output tokens
- Achieves 82% MMLU score, ranking higher than GPT-4 on chat preference leaderboards
Best for
Cost-sensitive production applicationsVision tasks requiring affordable multimodal processingReasoning and coding work at lower cost