openai/gpt-5.4-nano
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Azure | $0.200 | $1.25 | 400K | 100% |
| OpenAI | $0.200 | $1.25 | 400K | 87.6% |
GPT-5.4 Nano costs $0.200 per million input tokens and $1.25 per million output tokens via OpenRouter, making it 95th cheapest of 298 paid models.
GPT-5.4 Nano scores 44.0 on the Artificial Analysis Intelligence Index, ranking 25th of 178 benchmarked models, with a GPQA Diamond score of 82%.
GPT-5.4 Nano generates around 60 tokens per second with 552ms time-to-first-token (p50), the 138th fastest tracked model.
GPT-5.4 Nano supports a 400K-token context window and can output up to 128K tokens. It accepts file, image, text input.