Model Terminal
GPT-5 Image Mini
GPT-5 Image Mini is OpenAI's cost-efficient multimodal model combining text and image understanding with lightweight image generation capabilities. It is designed for speed- and cost-sensitive visual workflows such as image captioning, visual Q&A, and image editing where maximal fidelity is not required. Source: supabase.
Value score
Not scored
Context
—
tokens
Max output
—
tokens
Price
—
Identity
- Developer
- OpenAI
- Openness
- —
- Modalities
- —
- Release
- —
- Knowledge cutoff
- —
- Deprecation
- —
- API docs
- —
Benchmarks
No benchmark scores yet.