GPT-4oon Krater.ai

OpenAI's flagship multimodal model combining text, vision, and audio understanding. GPT-4o ("o" for "omni") delivers GPT-4 Turbo-level intelligence with faster responses and native multimodal capabilities.

Released May 13, 2024

Specifications

GPT-4o at a glance

Context

128K tokens

Max output

16.4K tokens

Input

Text, Image, File

Output

Text

Input price

$2.50 / 1M

Output price

$10.00 / 1M

Knowledge cutoff

2023-10-31

Krater rank

#16

Image inputTool callingStructured outputsProvider moderated

Capabilities

What it is good at

Catalog capabilities

  • Accepts image input
  • Generates text responses
  • Supports tool calling
  • Supports structured outputs
  • Native multimodal understanding (text, images, audio)
  • Faster response times than GPT-4 Turbo

Good for

Complex conversations requiring nuanced understandingAnalyzing images and documentsCreative writing and content generationCode generation and debugging

Benchmarks

Catalog data, not Krater benchmarks.

Design Arena 3d rank

#103

Design Arena uicomponent rank

#107

FAQ

Questions about GPT-4o

Clear answers based on the model catalog and Krater access.

GPT-4o supports a context window of 128,000 tokens.

Use GPT-4o in your API

Connect with Krater's unified API.

API access

Ready to use GPT-4o?

Access leading models in one focused workspace.