GPT-4 Turbo

Name: GPT-4 Turbo
Author: OpenAI

Compact GPT model for low-latency assistance and high-volume workloads

Live

Open / InstallLast updated August 5, 2026

Description

Compact GPT model for low-latency assistance and high-volume workloads. Supports a context window of 128,000 tokens. Supports tool calling. Input priced at $10 per million tokens. Weights are not publicly released; access is via the provider API.

Author

OpenAI

Platform

api

Pricing model

paid

Capabilities

Text generation
128,000 token context
Tool calling
File attachments
Image input

Benchmarks

No benchmark results have been added yet.