# GPT-5

The standard tier of the GPT-5 family, combining advanced reasoning with strong coding performance, multimodal input support, and a context window of 400K tokens.

- **Model ID:** `openai/gpt-5`
- **Type:** chat
- **Providers:** azure, openai
- **Context window:** 400,000
- **Maximum output tokens:** 128,000
- **Pricing:** $1.25/1M input tokens, $10.0/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gpt-5

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

## About

GPT-5 launched on August 7, 2025 as a generational leap over the GPT-4 family. Available through AI Gateway, it brings together advances in reasoning depth, coding proficiency, instruction following, and multimodal understanding in a single model.

The model supports a context window of 400K tokens, enabling developers to pass extensive codebases, long documents, or rich conversation histories in a single request. Combined with improved instruction adherence, GPT-5 follows complex multi-constraint specifications more reliably than its predecessors.

As the standard tier of the GPT-5 family, it sits alongside GPT-5 mini, GPT-5 nano, and GPT-5 pro, each targeting different points on the capability-cost spectrum. GPT-5 is the default choice when full GPT-5 family capability is the priority.

## What to consider

GPT-5 provides the full capability of the GPT-5 architecture. It's the right choice when you need high overall quality across reasoning, coding, and creative tasks and cost is secondary to capability.

For cost-sensitive deployments, consider GPT-5 mini or GPT-5 nano, which deliver much of the same architectural improvement at lower price points.

## When to use

### Best For

- **Complex multi-step reasoning:** Research analysis, strategic planning, and problems requiring extended deliberation
- **Advanced code generation:** Full-repository comprehension, architectural decisions, and complex refactoring
- **Multimodal workflows:** Processing images, documents, and text together in sophisticated analysis pipelines
- **High-stakes content generation:** Legal drafting, technical documentation, and precision-critical writing
- **Agentic systems:** Backbone model for autonomous agents that need the full capability of the GPT-5 family

### Consider Alternatives When

- **Cost-sensitive workloads:** GPT-5 mini offers strong capability at a lower price point
- **Lightweight tasks:** GPT-5 nano or GPT-4.1 nano handle classification and routing more efficiently
- **Specialized reasoning:** The o-series reasoning models may outperform on pure mathematical and scientific reasoning tasks
- **Speed-critical applications:** Smaller models provide faster time-to-first-token for real-time chat

## Best for

- **Complex multi-step reasoning:** Research analysis, strategic planning, and problems requiring extended deliberation
- **Advanced code generation:** Full-repository comprehension, architectural decisions, and complex refactoring
- **Multimodal workflows:** Processing images, documents, and text together in sophisticated analysis pipelines
- **High-stakes content generation:** Legal drafting, technical documentation, and precision-critical writing
- **Agentic systems:** Backbone model for autonomous agents that need the full capability of the GPT-5 family

## Consider alternatives

- **Cost-sensitive workloads:** GPT-5 mini offers strong capability at a lower price point
- **Lightweight tasks:** GPT-5 nano or GPT-4.1 nano handle classification and routing more efficiently
- **Specialized reasoning:** The o-series reasoning models may outperform on pure mathematical and scientific reasoning tasks
- **Speed-critical applications:** Smaller models provide faster time-to-first-token for real-time chat

## Frequently asked questions

### How does GPT-5 compare to GPT-4o?

GPT-5 represents a generational improvement over GPT-4o across reasoning, coding, instruction following, and multimodal capabilities.

### What context window does GPT-5 support?

GPT-5 supports a context window of 400K tokens, enabling full-codebase analysis and extended document processing in a single request.

### When should I use GPT-5 versus GPT-5 mini?

Use GPT-5 when you need the highest-tier capability in the GPT-5 family. Use GPT-5 mini when you need strong performance at lower cost, particularly for high-volume production workloads.

### Does GPT-5 support multimodal input?

Yes. It accepts text and image inputs, enabling vision-based analysis, document processing with figures, and mixed-modality workflows.

### How does AI Gateway handle authentication for GPT-5?

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 is the pricing for GPT-5?

See the pricing section on this page for today's rates. AI Gateway exposes each provider's pricing for GPT-5.

### 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)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5.1)
- [Provider pricing](https://platform.openai.com/docs/pricing)