OpenAI: GPT-4 (older v0314)

Text input Text output
Author's Description

GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.

Key Specifications
Cost
+$$$$$
Context
8K
Released
May 27, 2023
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Top Logprobs Seed Max Tokens Structured Outputs Frequency Penalty Logprobs Stop Tools Temperature Presence Penalty Response Format Logit Bias Top P
Features

This model supports the following features:

Structured Outputs Response Format Tools
Performance Summary

OpenAI's GPT-4 (v0314), released on May 27, 2023, and supported until June 14, demonstrates exceptional performance in several key areas. The model consistently ranks among the fastest, achieving an Infinityth percentile in speed across three benchmarks. However, this premium speed is reflected in its pricing, which tends to be at the higher end, ranking in the 5th percentile across two benchmarks. A significant strength is its outstanding reliability, boasting a 100% success rate across all three benchmarks, indicating minimal technical failures. In terms of benchmark results, GPT-4 (v0314) achieved perfect accuracy in the "Hallucinations (Baseline)" test, effectively identifying fictional concepts and correctly responding "I don't know." This makes it the most accurate model at its price point and among models of comparable speed for this task. Its instruction-following capabilities are also strong, with 68.0% accuracy, placing it in the 71st percentile. A notable weakness, however, is its performance in the "General Knowledge (Baseline)" test, where it scored 0.0% accuracy, suggesting a limitation in recalling or applying broad factual information within this specific evaluation.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $30
Completion $60

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-4-0314 8K $30 / 1M tokens $60 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai