LLM Reference

GPT-4 Turbo

Released
2024-04-09
Last refreshed
2026-06-29
Status
Researched 61d ago
DeprecatedProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool usehighlight

GPT-4 Turbo is a legacy integration reference; evaluate GPT-4.1 before starting new work.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 128k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • New production launches
Specifications
Family
GPT-4
Released
2024-04-09
Context
128k
Parameters
1.76T (8x222B MoE)*
Architecture
Mixture of Experts
Knowledge cutoff
2023-12
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing
Output / 1M
$15.00
Input / 1M
$5.00

Cheapest of 6 routes · Replicate API

This model is deprecated. OpenAI recommends switching to GPT-4.1.

About

OpenAI's high-performance variant of GPT-4 with 128K context window and improved reasoning. Widely used for production applications.

GPT-4 Turbo is a proprietary model in the GPT-4 family. The structured metadata tracks a 128k-token context window, multimodal input, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenAI API, Azure OpenAI, Salesforce Einstein Generative AI, and 3 more, with the cheapest tracked route listed at $5 input and $15 output per 1M tokens. Headline tracked benchmarks include Massive Multitask Language Understanding 86.5, Chatbot Arena 1242.0, and MMLU PRO 69.4.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 6

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MBatch in / outRoute
Replicate API$5.00$15.00-
Serverless
OpenAI API$10.00$30.00$5.00 / $15.00
Serverless
OpenRouter$10.00$30.00-
Serverless
Vercel AI Gateway$10.00$30.00-
Serverless

Available via routers & gateways(16)

Capabilities

VisionMultimodalFunction CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Classification

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Massive Multitask Language Understanding86.55-shothttps://openai.com/index/gpt-4-research/
Chatbot Arena1242.0https://lmarena.ai
MMLU PRO69.4https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro

Migration checks

No linked migration route is available for this model yet.

API versions

gpt-4-turbo-2024-04-09gpt-4-turbo

Compare GPT-4 Turbo with other models

Show all 2 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of GPT-4 Turbo?

GPT-4 Turbo has a context window of 128k tokens.

How much does GPT-4 Turbo cost?

GPT-4 Turbo pricing ranges from $5/1M to $10/1M input tokens depending on the provider.

When was GPT-4 Turbo released?

GPT-4 Turbo was released on 2024-04-09.

Which providers offer GPT-4 Turbo?

GPT-4 Turbo is available from 6 providers: OpenAI API, Azure OpenAI, Salesforce Einstein Generative AI, OpenRouter, Replicate API, Vercel AI Gateway.

What benchmarks has GPT-4 Turbo been tested on?

GPT-4 Turbo has been evaluated on 3 benchmarks, including Massive Multitask Language Understanding, Chatbot Arena, MMLU PRO.