GPT-5.4 Nano
GPT-5.4 Nano is a lightweight, cost-efficient model developed by OpenAI, released on March 17, 2026. It is designed for high-volume, speed-critical tasks and supports both text and image inputs with built-in reasoning and tool-calling capabilities.
GPT-5.4 Nano specs and pricing
- Provider: OpenAI
- Released: March 17, 2026
- Context window: 400K tokens
- Max output: 128K tokens
- Input: files, images, text
- Output: text
- Price: $0.20 input / $1.25 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5.4 Nano is good at
- Processing high volumes of text and image data
- Time-sensitive tasks requiring low latency
- Complex workflows involving tool execution and reasoning
To-dos to try with GPT-5.4 Nano
- Analyze a series of product images and generate descriptive text for a catalog
- Use the reasoning capability to troubleshoot a technical process described in a document
- Automate data extraction from multiple files using tool-calling functions
FAQ
- What types of input can GPT-5.4 Nano process? The model accepts text, image, and file inputs.
- What is the primary purpose of this model? It is optimized for speed-critical and high-volume tasks as the most lightweight variant of the GPT-5.4 family.
- How much does GPT-5.4 Nano cost? GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.74 credits ($1 = 100 credits).
- What is the context window of GPT-5.4 Nano? GPT-5.4 Nano can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5.4 Nano without coding? Yes. In todo.is you pick GPT-5.4 Nano as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.