GPT-4o logo

GPT-4o

OpenAI · Released May 2024

Recommended

The most broadly capable multimodal model with the widest ecosystem of integrations and tools.

Is it right for you?

Good for

  • Multimodal tasks (text, image, audio)
  • General-purpose chat applications
  • Rapid prototyping with broad API support
  • Function calling and tool use

Not good for

  • Cost-sensitive high-volume text processing
  • Tasks requiring very long context windows
  • Projects requiring model self-hosting

How it performs by task

Multimodal analysis

Excellent

Best-in-class native multimodal capabilities across text, image, and audio inputs.

Code generation

Very Good

Strong code generation with excellent function calling, though slightly behind Claude 4 Sonnet on complex refactors.

Creative writing

Very Good

Versatile writing across styles with good instruction following and format adherence.

Data extraction

Very Good

Reliable structured output with JSON mode and strong schema compliance.

Pricing

Input

$2.50 / 1M tokens

Output

$10 / 1M tokens

Context

128K tokens

Verified 2026-05-25View full pricing

Benchmarks

BenchmarkScoreSource
MMLU-Pro80.4% Source
HumanEval90.2% Source
MATH76.6% Source

Verdict history

Jun 6, 2026Verdict change

Budget agents just got cheaper: Gemini 2.5 Flash is our new pick

Full reasoning

Sources