OpenAI: GPT-4 Turbo (older v1106)

Public pricingIntelligence 70/100Medium memory工具调用

OpenAI: GPT-4 Turbo (older v1106) 是一款文本模型，适合视觉语言理解。它结合了图像理解、128K tokens上下文和高端定价定位，可在vision-language understanding and content analysis中提供可靠表现。它适合重视质量、速度与成本的团队，能带来稳定输出、灵活部署与扩展空间。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。

Input

$10.00/1M

Output

$30.00/1M

Cached

$1.00/1M

Batch

$5.00/1M

Calculate your GPT-4 Turbo (older v1106) bill.

Set your workload — see cost at your exact volume.

What would GPT-4 Turbo (older v1106) cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

GPT-4 Turbo (older v1106) at a glance.

Memory

128,000

tokens

Max reply

4,096

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

tiktoken-o200k

Released

Nov 2023

Training cutoff

Apr 2023

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • gpqa_diamond

    35.73

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick GPT-4 Turbo (older v1106)

  • Agentic workflows that call tools or APIs.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

GPT-4 Turbo (older v1106) — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, GPT-4 Turbo (older v1106) costs roughly $1,950 per month. Input is $10.00 /1M tokens and output is $30.00 /1M tokens.
GPT-4 Turbo (older v1106) has a 128,000-token context window (medium memory — a long report or a codebase file). That means you can fit about 24,000 words of input and history in a single call.
Beyond text generation, GPT-4 Turbo (older v1106) supports calling functions / tools, strict JSON output. It streams replies by default.
GPT-4 Turbo (older v1106) was released in November 2023, with training data cut off around April 2023.
Models in a similar class include GPT-4 Turbo, GPT-4 Turbo Preview, GPT-5 Image. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare GPT-4 Turbo (older v1106) against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard