# GPT-4 Turbo

The DevDay 2023 release that lowered GPT-4 class costs while adding a context window of 128K tokens, native vision input, and JSON mode in a single model.

- **Model ID:** `openai/gpt-4-turbo`
- **Type:** chat
- **Providers:** openai
- **Context window:** 128,000
- **Maximum output tokens:** 4,096
- **Pricing:** $10.0/1M input tokens, $30.0/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-4-turbo

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

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

const result = streamText({
  model: 'openai/gpt-4-turbo',
  prompt: 'Why is the sky blue?'
})
```

## About

GPT-4 Turbo was announced at OpenAI's first DevDay conference on April 9, 2024. It introduced a context window of 128K tokens, enough to hold more than 300 pages of text in a single prompt. OpenAI also pushed the knowledge cutoff to April 2023, a meaningful update for applications dealing with events from the first half of that year.

Two features made GPT-4 Turbo immediately practical for production integrations. JSON mode let developers reliably request structured JSON output, simplifying downstream parsing without brittle prompt engineering. Vision input enabled image analysis directly within the Chat Completions API. Passing a URL or base64-encoded image let the model generate captions, extract data from photographs, and interpret diagrams or documents with figures.

Pricing was also reduced compared to the original GPT-4, with lower rates on both input and output tokens. This made GPT-4-class reasoning accessible to a much wider range of applications and unlocked use cases where the economics of the original GPT-4 had been prohibitive.

## What to consider

If you built integrations around GPT-4 Turbo's specific JSON mode behavior or vision API surface, verify provider-level feature parity before routing production traffic. Some capabilities behave consistently across providers while others may have provider-specific nuances.

## When to use

### Best For

- Long-document analysis, legal review, or research tasks that benefit from holding an entire lengthy document in context at once
- Applications requiring reliable JSON output through the built-in JSON mode
- Vision-capable pipelines: image captioning, document processing with figures, screenshot analysis
- Workflows that depend on knowledge of events up to April 2023
- Complex reasoning tasks where GPT-4 class depth is required at a cost tier below the original GPT-4

### Consider Alternatives When

- You need a context window beyond 128K tokens; GPT-4.1 supports up to 1M tokens
- Native audio input or output is required; GPT-4o handles audio natively
- You want model improvements including structured outputs guarantees or creative writing enhancements introduced in later GPT-4o snapshots
- Cost efficiency is the primary driver and GPT-4o or GPT-4o mini provide sufficient quality for your task

## Best for

- **Long-document analysis:** Legal review or research tasks that benefit from holding an entire lengthy document in context at once
- **Reliable JSON output:** Applications requiring structured responses through the built-in JSON mode
- **Vision-capable pipelines:** Image captioning, document processing with figures, and screenshot analysis
- **Current-events workflows:** Use cases that depend on knowledge of events up to April 2023
- **Cost-efficient GPT-4 reasoning:** Complex reasoning where GPT-4 class depth is required at a cost tier below the original GPT-4

## Consider alternatives

- **Larger context needed:** You need a window beyond 128K tokens and GPT-4.1 supports up to 1M tokens
- **Native audio required:** GPT-4o handles audio input and output natively
- **Later snapshot features:** You want structured outputs guarantees or creative writing enhancements introduced in later GPT-4o snapshots
- **Cost-driven workloads:** GPT-4o or GPT-4o mini provide sufficient quality at lower cost

## Frequently asked questions

### What made GPT-4 Turbo's context window significant?

At 128K tokens it holds roughly 300 pages of text, enabling workflows like full-codebase review, long legal document analysis, and extended multi-session conversation history without chunking.

### How does JSON mode in GPT-4 Turbo work?

Set `response_format` to `{ type: "json_object" }` and the model constrains itself to produce valid JSON. This differs from the stricter JSON Schema-based Structured Outputs introduced later with gpt-4o-2024-08-06.

### Does GPT-4 Turbo support image inputs?

Yes. You can pass image URLs or base64-encoded images alongside text in the messages array. The model can analyze photographs, diagrams, screenshots, and documents with embedded figures.

### What is GPT-4 Turbo's knowledge cutoff?

April 2023. This was an update from earlier GPT-4 models and makes the model aware of events from the first half of 2023.

### How does GPT-4 Turbo pricing compare to the original GPT-4?

Rates are listed on this page. They reflect the providers routing through AI Gateway and shift when providers update their pricing.

### Can I route GPT-4 Turbo requests through AI Gateway without storing provider API keys?

Yes. AI Gateway handles authentication using its own API key or OIDC token system, so you don't need to embed OpenAI credentials in your deployment environment.

### 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-4-turbo)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)
- [Provider pricing](https://platform.openai.com/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.