gpt-4o-2024-11-20

2024-11-20
Chat, Vision
By OpenAI

Input: ￥20.00 / M tokens Output: ￥80.00 / M tokens
Features: Function Calling, Image Input, Streaming, Structured Outputs, Text Input, Text Output
Context Window: 128K
Maximum Output: 16K

Input: ￥20.00 / M tokens Output: ￥80.00 / M tokens
Features: Function Calling, Image Input, Streaming, Structured Outputs, Text Input, Text Output
Context Window: 128K
Maximum Output: 16K

Model Description

GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is the best model for most tasks, and is our most capable model outside of our o-series models.

Recommend Models

DeepSeek-V3-0324

Chat
DeepSeek

DeepSeek-V3-0324 is an upgraded AI model with enhanced reasoning, coding, Chinese writing, and web search capabilities, outperforming GPT-4.5 in certain tasks while maintaining 128K context support and open-source MIT licensing.

2025-03-24

o4-mini-2025-04-16

Chat, Reasoning, Vision
OpenAI

Our faster, cost-efficient reasoning model delivering strong performance on math, coding and vision

2025-04-16

claude-3-5-sonnet-20241022-rev

Chat, Vision
Reverse Source

Using reverse engineering to call the model within the official application and convert it into an API.

2024-12-01