Model Overview
GPT-4 Turbo is the next generation of GPT-4, an older high-intelligence GPT model. It was designed to be a cheaper, better version of GPT-4. Today, we recommend using a newer model like GPT-4o.
Key Features
- Average intelligence (2/4 dots rating)
- Medium speed (3/5 lightning bolts rating)
- 128,000 context window
- 4,096 max output tokens
- Dec 01, 2023 knowledge cutoff
- Text and image input support
- Text output support
Technical Specifications
- Pricing: $10.00 per 1M tokens (input), $30.00 per 1M tokens (output)
- Supports: Input: text, image; Output: text only
- Features: Streaming, Function calling
Snapshots
- gpt-4-turbo (alias for gpt-4-turbo-2024-04-09)
- gpt-4-turbo-2024-04-09
- gpt-4-turbo-preview (alias for gpt-4-0125-preview)
- gpt-4-0125-preview
- gpt-4-1106-vision-preview
Positioning and Use Cases
GPT-4 Turbo is the next generation of GPT-4, an older high-intelligence GPT model. It was designed to be a cheaper, better version of GPT-4. Today, we recommend using a newer model like GPT-4o.
Rate Limits
- Free tier: Not supported
- Tier 1: 500 RPM, 30,000 TPM, 90,000 batch queue limit
- Tier 2: 5,000 RPM, 450,000 TPM, 1,350,000 batch queue limit
- Tier 3: 5,000 RPM, 600,000 TPM, 40,000,000 batch queue limit
- Tier 4: 10,000 RPM, 800,000 TPM, 80,000,000 batch queue limit
- Tier 5: 10,000 RPM, 2,000,000 TPM, 300,000,000 batch queue limit
Documentation
Official Documentation
