GPT-5.4 nano
GPT-5.4 nano — OpenAI multimodal model with an Intelligence Index of 38, a 922K-token context window and a blended price of $0.18/1M tokens.
Key specifications
| Intelligence Index | 38 |
|---|---|
| Coding Index | 56.1 |
| Agentic Index | 27.5 |
| Arena Elo | — |
| Context window (K tokens) | 922 |
| Blended price ($/1M tokens) | 0.2 |
| Output speed (tokens/s) | 157 |
About GPT-5.4 nano
The GPT-5.4 nano is a multimodal model from OpenAI with an Intelligence Index of 38.0, a Coding Index of 56.1 and a 922K-token context window. It runs at a blended price of $0.18 per million tokens and generates about 157 tokens/s. It is proprietary api. Leaderboard indices are a strong signal but only part of real-world quality, which also depends on tool use, latency and task fit.
The comparisons below show how GPT-5.4 nano stacks up against the alternatives people most often weigh against it, with the specific numbers laid out side by side.
Frequently asked questions
Is the GPT-5.4 nano any good?
GPT-5.4 nano — OpenAI multimodal model with an Intelligence Index of 38, a 922K-token context window and a blended price of $0.18/1M tokens.
What are the key specs of the GPT-5.4 nano?
See the specification table above for the full breakdown.