| Overview |  GPT-4 Turbo | GPT-4 | Select LLM Model |
|---|---|---|---|
Max Tokens | 4096 | 4096 | |
Max Input Tokens | 128000 | 8192 | |
Max Output Tokens | 4096 | 4096 | |
Input Cost per Token | 0.00001 | 0.00003 | |
Output Cost per Token | 0.00003 | 0.00006 | |
Provider | OpenAI | OpenAI | |
Mode | Chat | Chat | |
Supports Function Calling | Yes | Yes | |
Supports Parallel Function Calling | Yes | Yes | |
Supports Vision | Yes | Yes |