# GPT 5.2

The standard tier of the GPT-5.2 family, advancing general-purpose AI with improvements in reasoning, coding, and instruction following over GPT-5.

- **Model ID:** `openai/gpt-5.2`
- **Type:** chat
- **Providers:** azure, openai
- **Context window:** 400,000
- **Maximum output tokens:** 128,000
- **Pricing:** $1.75/1M input tokens, $14/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-5.2

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

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

const result = streamText({
  model: 'openai/gpt-5.2',
  prompt: 'Why is the sky blue?'
})
```

## About

GPT 5.2 became available on December 11, 2025 on AI Gateway as the GPT-5.2 generation of OpenAI's general-purpose model series. It builds on the GPT-5 and GPT-5.1 generations with further improvements across reasoning depth, coding capability, instruction following, and multimodal understanding.

As the standard tier in the GPT-5.2 family, it provides the balance of capability and accessibility that most demanding applications require. The context window of 400K tokens supports extensive inputs, and the model handles text, image, and mixed-modality inputs with GPT-5.2 generation quality.

If you already use GPT-5 or GPT-5.1, GPT 5.2 offers an upgrade path with measurable improvements across key benchmarks.

## What to consider

GPT 5.2 builds on the GPT-5 and GPT-5.1 generations with further improvements across reasoning, coding, and instruction following.

It launches alongside chat, codex, and pro variants, each specialized for different workloads while sharing the same generational improvements.

## When to use

### Best For

- **Complex reasoning:** Analytical and strategic tasks that benefit from GPT-5.2 generation improvements
- **Advanced code generation:** Strong coding performance for development tools and agents
- **Multimodal applications:** Vision, text, and mixed-modality workflows with GPT-5.2 generation improvements
- **Research and analysis:** Deep document analysis, research synthesis, and complex question answering
- **New projects:** Applications that benefit from GPT-5.2 generation capability over GPT-5 or GPT-5.1

### Consider Alternatives When

- **Cost optimization:** GPT-5 mini or GPT-5.1 instant for production workloads where cost efficiency matters
- **Specialized coding:** GPT-5.2 codex for autonomous software engineering workflows
- **Pure reasoning:** o3 for chain-of-thought mathematical and scientific reasoning
- **High-volume lightweight tasks:** Nano-tier models for classification and routing

## Best for

- **Complex reasoning:** Analytical and strategic tasks that benefit from GPT-5.2 generation improvements
- **Advanced code generation:** Strong coding performance for development tools and agents
- **Multimodal applications:** Vision, text, and mixed-modality workflows with GPT-5.2 generation improvements
- **Research and analysis:** Deep document analysis, research synthesis, and complex question answering
- **New projects:** Applications that benefit from GPT-5.2 generation capability over GPT-5 or GPT-5.1

## Consider alternatives

- **Cost optimization:** GPT-5 mini or GPT-5.1 instant for production workloads where cost efficiency matters
- **Specialized coding:** GPT-5.2 codex for autonomous software engineering workflows
- **Pure reasoning:** o3 for chain-of-thought mathematical and scientific reasoning
- **High-volume lightweight tasks:** Nano-tier models for classification and routing

## Frequently asked questions

### How does GPT 5.2 improve over GPT-5.1?

It advances reasoning, coding, and multimodal capabilities over GPT-5.1, representing a generational improvement in the GPT series.

### What context window does GPT 5.2 support?

400K tokens, supporting extensive document and codebase processing.

### Should I migrate from GPT-5 to GPT 5.2?

If your application benefits from improved reasoning and coding quality, yes. Test with your specific workloads to confirm the improvement justifies any pricing differences.

### Does GPT 5.2 support function calling and structured outputs?

Yes. It supports the full API feature set including function calling, structured outputs, vision, and system messages.

### How does AI Gateway handle authentication for GPT 5.2?

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-5.2)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service)
- [Provider pricing](https://openai.com/api/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.