Currently listed through these providers:
Model details
OpenAI GPT Mini Latest
OpenAI GPT Mini Latest functions as a dynamic alias rather than a standalone model, automatically routing requests to whichever release currently represents the newest entry in the GPT Mini family. This redirect behavior means developers do not need to update integration code each time a newer mini-tier variant ships, since the model identifier remains stable while the underlying target shifts behind the scenes. The pattern is useful for applications that want a lightweight, always-current option from OpenAI's smaller-model lineup without manual version tracking.
Because the entry inherits whatever capabilities and characteristics belong to the active GPT Mini release, it is best understood as a convenience layer over a broader family rather than a fixed snapshot. Teams selecting it through OpenRouter gain a 400,000-token context window and multimodal input handling along with reasoning and tool-calling support, making it a practical choice for cost-sensitive workloads that still need flexible document and image understanding. The redirect design also means that performance, pricing, and qualitative behavior can evolve as the family advances, so the strongest practical fit is for projects that want the small-model track's latest improvements delivered automatically.
Quick Info
Powered by- Provider
- OpenRouter
- Model key
- ~openai/gpt-mini-latest
- Release date
- Apr 27, 2026
- Last updated
- Apr 27, 2026
- Knowledge cutoff
- 2025-08-31
- Input modalities
- Output modalities
- Capabilities
Cost
- Input token cost
- $0.75
- Output token cost
- $4.50
Limits
- Output tokens
- 128,000 tokens
- Context window
- 400,000 tokens