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.

OpenAI

GPT-4 Turbo

GPT-4 Turbo launched at OpenAI DevDay 2023 with a context window of 128K tokens, built-in vision, JSON mode, and a knowledge cutoff of April 2023, all at reduced input prices compared to the original GPT-4.

View API reference

Input and output price: Input $10, Output $30, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

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

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out GPT-4 Turbo by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

GPT-4 Turbo

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

OpenAI

Legal:Terms•Privacy

128K

1.4 s

30 tps

$10/M

$30/M

—

04/09/2024

Getting started

Call GPT-4 Turbo through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-4-turbo',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same GPT-4 Turbo request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-4-turbo',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
    temperature: 0.5,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `openai/gpt-4-turbo`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. GPT-4 Turbo supports up to `4,096` output tokens.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 128K-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK openai provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-4-turbo',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['openai'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-4-turbo',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-4-turbo',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by OpenAI

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

openai/gpt-6-astra

1.1M

2.9 s

56 tps

$10/M+2 more

$50/M+2 more

Read$1/M

Write$12.50/M

$10/K

09/04/2026

openai/gpt-5.6-luna

1.1M

2.4 s

156 tps

$0.20/M+2 more

$1.20/M+2 more

Read$0.02/M

Write$0.25/M

$10/K

07/09/2026

openai/gpt-5.6-sol

1.1M

2.6 s

69 tps

$2/M+2 more

$10/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

openai/gpt-5.6-terra

1.1M

2.6 s

94 tps

$2/M+2 more

$12/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

openai/gpt-5.4

1.1M

3.5 s

88 tps

$2.50/M+2 more

$15/M+2 more

Read$0.25/M

$10/K

03/05/2026

openai/gpt-5-nano

400K

4.4 s

208 tps

$0.05/M

$0.40/M

Read$0.005/M

$14/K

08/07/2025

Copy link to headingAbout GPT-4 Turbo

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.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: 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.
Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use GPT-4 Turbo

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 when

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

Copy link to headingConclusion

GPT-4 Turbo marked the point where GPT-4 class reasoning became broadly economical, pairing a context window of 128K tokens and vision input with reduced pricing for production deployment. For document-heavy, vision-enabled, or JSON-structured workloads that were designed around its specific feature set, it remains a well-understood and reliable option through AI Gateway.

Copy link to headingFrequently 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.

Your use is subject to OpenAI's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

GPT-4 Turbo

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Image input

Tool calling

Copy link to headingMore models by OpenAI

Copy link to headingAbout GPT-4 Turbo

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use GPT-4 Turbo

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions