GPT 4.1 Nano
OpenAI · text, image → text
Ultra-lightweight model with million-token context, optimized for speed and low latency, costing only $0.10 per million input tokens. It is suitable for edge computing and real-time interaction. The automatic caching mechanism offers a 75% cost reduction on cache hits.
Input$0.1 /M
Output$0.4 /M
Cache read$0.025 /M