OpenAI: GPT-4 Turbo (older v1106)

Text input Text output
Author's Description

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to April 2023.

Key Specifications
Cost
+$$$$$
Context
128K
Released
Nov 05, 2023
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Response Format Tools Structured Outputs
Performance Summary

OpenAI's GPT-4 Turbo (v1106), released on November 5, 2023, with training data up to April 2023, demonstrates a strong performance profile. It exhibits competitive response times, performing among the faster models with a 49th percentile speed ranking across two benchmarks. However, its pricing tends to be at a premium level, ranking in the 8th percentile for cost. A standout feature is its exceptional reliability, achieving a perfect 100% success rate across all benchmarks, indicating consistent and usable responses. In specific benchmark evaluations, GPT-4 Turbo excels in acknowledging uncertainty, achieving 100.0% accuracy in the Hallucinations (Baseline) test. This makes it the most accurate model at its price point and among models of comparable speed for this task. For Instruction Following (Baseline), it achieved 70.0% accuracy, placing it in the 80th percentile, indicating strong capability in handling complex directives. While its hallucination test cost was low ($0.1917), the instruction following test was higher ($0.2917). Overall, its key strengths lie in its high reliability and precision in identifying fictional concepts, alongside robust instruction following. Its primary weakness is its premium pricing.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $10
Completion $30

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-4-1106-preview 128K $10 / 1M tokens $30 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai