# GPT 5.4 Mini

The cost-efficient variant of the GPT-5.4 family, built for agentic tasks that balance capability and cost, with strong code generation and tool orchestration.

- **Model ID:** `openai/gpt-5.4-mini`
- **Type:** chat
- **Providers:** openai, azure
- **Context window:** 400,000
- **Maximum output tokens:** 128,000
- **Pricing:** $0.75/1M input tokens, $4.50/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-5.4-mini

## 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-mini',
  prompt: 'Why is the sky blue?'
})
```

## About

GPT 5.4 Mini became available on March 17, 2026 on AI Gateway as the cost-efficient variant of the GPT-5.4 model family. It handles code generation, tool orchestration, and multi-step browser interactions more reliably than previous mini-tier models, making it a strong default for agentic tasks.

The model supports verbosity and reasoning level parameters, giving you control over response detail and how much the model reasons before answering. This is useful for tuning the cost-quality tradeoff per request. It's built for sub-agent workflows where multiple smaller models coordinate on parts of a larger task.

With a context window of 400K tokens and the full API feature set, GPT 5.4 Mini provides the capabilities production applications need at a price point that scales. If you're migrating from GPT-5 mini, it offers measurable improvements in agentic task completion.

## What to consider

GPT 5.4 Mini is a strong default for agentic tasks that need to balance capability and cost. It handles code generation, tool orchestration, and multi-step browser interactions more reliably than previous mini-tier models.

The model supports verbosity and reasoning level parameters, giving you control over response detail and how much the model reasons before answering.

## When to use

### Best For

- **Agentic production workloads:** Multi-step tasks involving tools, code, and browser interactions at sustainable cost
- **Code generation:** Reliable code output for development tools and agent pipelines
- **Sub-agent coordination:** Smaller model that coordinates on parts of a larger task alongside other agents
- **Tool orchestration:** Calling and composing external APIs and functions in multi-step sequences
- **Cost-efficient chat:** Capable conversational interface at a lower price than full GPT-5.4

### Consider Alternatives When

- **Maximum capability:** GPT-5.4 or GPT-5.4 pro when the task demands full GPT-5.4 quality
- **Lowest cost:** GPT-5.4 nano for high-volume sub-agent workflows where cost scales with parallel calls
- **Specialized coding:** GPT-5.3 codex for autonomous software engineering in sandboxed environments
- **Pure reasoning:** o3 for chain-of-thought mathematical and scientific reasoning

## Best for

- **Agentic production workloads:** Multi-step tasks involving tools, code, and browser interactions at sustainable cost
- **Code generation:** Reliable code output for development tools and agent pipelines
- **Sub-agent coordination:** Smaller model that coordinates on parts of a larger task alongside other agents
- **Tool orchestration:** Calling and composing external APIs and functions in multi-step sequences
- **Cost-efficient chat:** Capable conversational interface at a lower price than full GPT-5.4

## Consider alternatives

- **Maximum capability:** GPT-5.4 or GPT-5.4 pro when the task demands full GPT-5.4 quality
- **Lowest cost:** GPT-5.4 nano for high-volume sub-agent workflows where cost scales with parallel calls
- **Specialized coding:** GPT-5.3 codex for autonomous software engineering in sandboxed environments
- **Pure reasoning:** o3 for chain-of-thought mathematical and scientific reasoning

## Frequently asked questions

### How does GPT 5.4 Mini compare to GPT-5 mini?

It handles code generation, tool orchestration, and multi-step browser interactions more reliably. It also supports verbosity and reasoning level parameters for tunable output.

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

400K tokens, supporting extended inputs for agentic workflows.

### What are the verbosity and reasoning level parameters?

They give you control over response detail and how much the model reasons before answering, letting you tune the cost-quality tradeoff per request.

### Is GPT 5.4 Mini suitable for sub-agent workflows?

Yes. It's built for sub-agent architectures where multiple smaller models coordinate on parts of a larger task.

### When should I use GPT-5.4 Nano instead?

When cost is the dominant concern and you're running high-volume parallel calls. GPT-5.4 Nano performs close to mini in evaluations at a lower price point.

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

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