LLM Reference

GPT-4

gpt-4

DeprecatedResearched 16d ago

Last refreshed 2026-05-11. Next refresh: weekly.

ProprietaryMultimodalCodingAgentsVisionJSON / Tool use

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

Decision context: Coding task fit, 4 tracked provider routes, and research from 2026-05-10.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 8K context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • New production launches

Cheapest output

$60.00

OpenAI API per 1M tokens

Provider routes

4

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-05-10

Researched 16d ago

fresh

This API model is marked deprecated. Use GPT-4.1 as the replacement candidate before sending new production traffic.

Top use-case fit

Coding

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 4
ProviderInput / 1MOutput / 1MBatch in / outRoute
OpenAI API$30.00$60.00$15.00 / $30.00
Serverless
OpenRouter$30.00$60.00-
Serverless
Salesforce Einstein Generative AI---
ServerlessPartial

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

About

OpenAI's original GPT-4 model with strong reasoning and general knowledge. Foundation model for many applications.

GPT-4 has a 8K-token context window.

GPT-4 input tokens at $30/1M, output at $60/1M.

Capabilities

VisionMultimodalFunction CallingStructured OutputsCode Execution

Benchmark Scores(1)

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
GAOKAO72.2zero-shot, objective-accuracyhttps://github.com/OpenLMLab/GAOKAO-Bench

API Versions

gpt-4-0314gpt-4-0613gpt-4

Rankings

Show all 41 popular comparisonssorted by 7-day search impressions

Specifications

FamilyGPT-4
Released2023-03-14
Parameters1.76T (8x222B MoE)*
Context8K
ArchitectureMixture of Experts
Knowledge cutoff2021-09
Specializationgeneral
LicenseProprietary
Trainingfinetuned

Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website