No longer supported

This model is retired (released March 2023) and is no longer actively maintained or recommended by OpenAI. Consider using their current flagship model instead.

retiredfrontierllm Proprietary

GPT-4-0314

by OpenAI· Released March 2023· Cutoff September 2021

GPT-4-0314 is an early snapshot of OpenAI's GPT-4 model, released in March 2023. It is a large multimodal model capable of processing text and image inputs (though image input was not available via API at launch). This version was deprecated and replaced by newer snapshots like gpt-4-0613.

Official Site API Docs 📄 Research Paper

Input cost

$30.00 per 1M tokens

Output cost

$60.00 per 1M tokens

Context window

8192 tokens

Max output

4096 tokens

Modalities

text

License

proprietary

Capabilities

Text GenerationCode GenerationReasoningInstruction FollowingSteerabilityMultilingual

Best For

General-purpose text generation and reasoning tasks requiring high accuracy and nuance.

Strengths

Superior reasoning and problem-solving compared to GPT-3.5
Strong performance on complex tasks like legal analysis and coding
Steerable and controllable via system messages

Limitations

No vision support in API (despite being multimodal)
Higher cost than later snapshots
Deprecated and no longer recommended for new projects

Use Cases

Content creation and editing

Code generation and debugging

Data analysis and interpretation

Customer support chatbots

Educational tutoring

Document summarization

Creative writing assistance

Improvements Over Previous Model

First model in GPT-4 family; no predecessor to compare within same family.

Back to all models