How much does GPT-4 Turbo cost?

GPT-4 Turbo costs $10 per million input tokens and $30 per million output tokens on standard pricing. A workload of 20M input and 5M output tokens a month is about $350.

What is the context length of GPT-4 Turbo?

GPT-4 Turbo accepts up to 128,000 tokens (128K) of input and can return up to 4,096 tokens in one response.

Does GPT-4 Turbo support tool calling and structured outputs?

Yes, GPT-4 Turbo supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Log probabilities, Deterministic seed.

What inputs and outputs does GPT-4 Turbo support?

GPT-4 Turbo accepts Text, Image as input and produces Text as output.

When was GPT-4 Turbo released?

GPT-4 Turbo was released by OpenAI in 2024-04-09.

GPT-4 Turbo

gpt-4-turbo

API Provider site

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023. Built by OpenAI.

Prices updated recently

Input price

$10

per 1M tokens · Standard

Output price

$30

per 1M tokens · Standard

Input limit

128K

tokens

Output limit

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF

Compare

GPT-4 Turbo price history

2 price records since 9/25/2026

GPT-4 Turbo cost calculator

Input20M tokens

Output5M tokens

$350/month

Standard pricing

Overview

What is GPT-4 Turbo?

GPT-4 Turbo is a text & reasoning and vision model from OpenAI. The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023. Its 128K context window and $10 input price make it a candidate for quality-focused production applications.

Image understandingDocument analysisContent workflowsClassification

Benchmarks

GPT-4 Turbo benchmarks & speed

How GPT-4 Turbo scores on standardized evaluations, and where it lands among every model we track.

7.0

Intelligence Index

Better than 11% of 153 models

33tok/s

Output speed

Better than 0% of 119 models

Reasoning

HLE

3.1%

Humanity's Last Exam · top 96%

Latency & design

Time to first token: 3.33s

Independent scores from Artificial Analysis and DesignArena · updated 10/5/2026. Higher is better; ranks compare against every model we track with that score.

Rates

GPT-4 Turbo pricing

Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

Input · Standard

$10

Per 1M tokens

Cached input · Standard

Not available

No listed cached-input rate

Capabilities

GPT-4 Turbo Tools

Tools available when using GPT-4 Turbo through supported provider APIs.

Function calling

Supported

Structured outputs

Supported

JSON mode

Supported

Reasoning

Not supported

Built-in web search

Not supported

Log probabilities

Supported

Deterministic seed

Supported

Parallel tool calls

Not supported

Prompt caching

Not supported

Strengths and limitations

Strengths

Measured results (AA Intelligence 7) position it for demanding production work.
A 128K context window covers most focused application workflows.
Supports text & reasoning and vision workloads in one model.

Limitations

Real-world cost still depends on prompt length, response length and provider-specific billing rules.
The 128K context window is smaller than several long-context alternatives.
Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

Same provider