# GPT 5.4 Nano

The smallest and fastest GPT-5.4 family model, delivering near-mini-tier performance at the lowest cost, built for high-volume sub-agent workflows.

- **Model ID:** `openai/gpt-5.4-nano`
- **Type:** chat
- **Providers:** openai, azure
- **Context window:** 400,000
- **Maximum output tokens:** 128,000
- **Pricing:** $0.20/1M input tokens, $1.25/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-5.4-nano

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'openai/gpt-5.4-nano',
  prompt: 'Why is the sky blue?'
})
```

## About

GPT 5.4 Nano became available on March 17, 2026 on AI Gateway as the smallest and most affordable model in the GPT-5.4 family. It performs close to GPT-5.4 Mini in evaluations while costing less per token, making it well-suited for high-volume use cases where cost scales with the number of parallel calls.

The model supports verbosity and reasoning level parameters, giving you control over how much the model reasons before answering. It's built for sub-agent workflows where multiple smaller models coordinate on parts of a larger task, and its price point makes per-request inference viable at the highest traffic levels.

With a context window of 400K tokens, GPT 5.4 Nano can process substantial inputs even when outputs remain short. For classification, routing, lightweight code checks, and batch processing at scale, it provides GPT-5.4 generation quality at the lowest cost in the family.

## What to consider

GPT 5.4 Nano performs close to GPT-5.4 Mini in evaluations at a lower price point. Choose it when cost scales with the number of parallel calls.

Like GPT-5.4 Mini, it supports verbosity and reasoning level parameters, giving you control over response detail and reasoning depth per request.

## When to use

### Best For

- **High-volume sub-agent workflows:** Parallel calls where cost scales with the number of agents
- **Classification and routing:** Sentiment analysis, intent detection, and request triage at high volume
- **Lightweight code tasks:** Simple code checks, unused import detection, and quick validations
- **Cost-sensitive batch processing:** Large-scale inference where per-call cost is the primary constraint
- **Pipeline preprocessing:** Fast filtering and extraction steps that feed into larger model calls

### Consider Alternatives When

- **Higher capability needed:** GPT-5.4 mini for agentic tasks that require more reliable multi-step completion
- **Maximum quality:** GPT-5.4 or GPT-5.4 pro for complex reasoning and analysis
- **Specialized coding:** GPT-5.3 codex for autonomous software engineering
- **Deep deliberation:** o3 for chain-of-thought reasoning on hard problems

## Best for

- **High-volume sub-agent workflows:** Parallel calls where cost scales with the number of agents
- **Classification and routing:** Sentiment analysis, intent detection, and request triage at high volume
- **Lightweight code tasks:** Simple code checks, unused import detection, and quick validations
- **Cost-sensitive batch processing:** Large-scale inference where per-call cost is the primary constraint
- **Pipeline preprocessing:** Fast filtering and extraction steps that feed into larger model calls

## Consider alternatives

- **Higher capability needed:** GPT-5.4 mini for agentic tasks that require more reliable multi-step completion
- **Maximum quality:** GPT-5.4 or GPT-5.4 pro for complex reasoning and analysis
- **Specialized coding:** GPT-5.3 codex for autonomous software engineering
- **Deep deliberation:** o3 for chain-of-thought reasoning on hard problems

## Frequently asked questions

### How does GPT 5.4 Nano compare to GPT-5.4 Mini?

It performs close to GPT-5.4 Mini in evaluations at a lower price point. Choose it when cost scales with the number of parallel calls.

### What context window does GPT 5.4 Nano support?

400K tokens, which is substantial for a model at this price tier.

### Does GPT 5.4 Nano support the verbosity parameter?

Yes. It supports verbosity and reasoning level parameters, giving you control over response detail and reasoning depth per request.

### What tasks is GPT 5.4 Nano designed for?

High-volume sub-agent workflows, classification, routing, lightweight code checks, and batch processing where per-call cost is the dominant concern.

### Can GPT 5.4 Nano handle complex reasoning?

For complex multi-step reasoning, GPT-5.4 Mini or the full GPT-5.4 will produce better results. GPT 5.4 Nano is optimized for simpler tasks at high volume.

### How does AI Gateway handle authentication for GPT 5.4 Nano?

AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.

### What are typical latency characteristics?

This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

## Links

- [Model page](https://vercel.com/ai-gateway/models/gpt-5.4-nano)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://developers.openai.com/api/docs/models/gpt-5.4-nano)
- [Provider pricing](https://developers.openai.com/api/docs/pricing)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.