Loading page
FlagshipOpenAI
GPT-4o
GPT-4o is OpenAI's flagship multimodal model with text and image capabilities, featuring a 128K token context window and tool calling support.
Context 128K
Tier Flagship
Knowledge Oct 2023
Tools Supported
Modalities text, image
Input from
$1.25 / 1M tokens
across 4 providers
API Pricing
Cheapest on OpenAI — 40% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $1.25 | $5.00 | - | |
| $1.25 | $5.00 | $0.625 | |
| $2.50 | $10.00 | $1.25 | |
| $2.50 | $10.00 | $1.25 | |
| $2.50 | $10.00 | $1.25 | |
| $2.50 | $10.00 | $1.25 |
Prices updated daily. Last check: Sep 6, 2026
GPT-4o pricing by provider
Input, output, and batch rates, plus alternatives, for one provider at a time.
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
6.5 / 100
Math
25.7 / 100
Reasoning & Knowledge
- MMLU-Pro80.3%
- GPQA Diamond65.5%
- Humanity's Last Exam4.0%
Coding
- LiveCodeBench42.5%
Math
- AIME 202525.7%
- AIME32.7%
- MATH-50089.3%
Benchmarks measured Sep 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- OpenAI
- Family
- GPT
- Tier
- Flagship
- Context Window
- 128K
- Knowledge Cutoff
- Oct 2023
- Modalities
- Text, Image
Capabilities
- Tool Calling
- Yes
- Open Source
- No
- Subtypes
- Chat Completion, Code Generation
Strengths & Limitations
Strengths
- Multimodal support for both text and image inputs
- 128,000 token context window for handling long documents
- Tool calling capability for API integrations and function execution
- Chat completion and code generation support
- Established model with widespread API provider support
- Part of OpenAI's well-documented platform ecosystem
Limitations
- Knowledge cutoff limited to October 2023
- Proprietary model with no open-source weights available
- No audio or video processing capabilities
- Smaller context window compared to some competing models
- Older generation within the GPT family lineup
Key Features
•128K token context window
•Text and image input processing
•Tool calling with function execution
•Chat completion API
•Code generation capabilities
•Structured output formatting
•Streaming response support
•System message customization
About GPT-4o
GPT-4o is OpenAI's flagship model in the GPT family, designed as a multimodal system that processes both text and images. As OpenAI's primary offering, it represents the company's current generation of large language models, though newer iterations like GPT-5.4 have since been released in the family lineup.
The model features a 128,000 token context window and supports both text generation and image analysis capabilities. GPT-4o includes tool calling functionality, enabling it to interact with external APIs and execute functions as part of its responses. It handles chat completion and code generation tasks, with a knowledge cutoff of October 2023.
GPT-4o serves organizations requiring multimodal AI capabilities for applications spanning customer service, content creation, and technical documentation. While it remains a capable model within the GPT family, users evaluating OpenAI's offerings should consider how it positions against newer family members for their specific requirements.
Common Use Cases
GPT-4o suits applications requiring multimodal processing, such as document analysis with visual components, customer support systems that handle both text queries and image uploads, and content creation workflows involving text and image coordination. Its tool calling capabilities make it appropriate for building AI agents that interact with external systems, while the 128K context window supports applications processing lengthy documents or maintaining extended conversation history. The model works well for code generation tasks, technical documentation creation, and scenarios where reliable text and image understanding within a single API call is required.
Frequently Asked Questions
How much does GPT-4o cost per million tokens?
GPT-4o pricing varies by provider and may include different rates for input and output tokens. Check the pricing table above for current rates across all providers offering GPT-4o access.
What is GPT-4o best used for?
GPT-4o excels at multimodal tasks requiring both text and image processing, such as document analysis, content creation with visual elements, and building AI agents with tool calling capabilities. Its 128K context window makes it suitable for applications involving long documents or extended conversations.
How does GPT-4o compare to newer GPT models?
GPT-4o is an earlier generation model in OpenAI's GPT family. While it provides solid multimodal capabilities and tool calling support, newer models in the family may offer improved performance, updated knowledge, or additional features. Consider your specific requirements for context length, modality support, and recency when choosing between GPT family models.