The OpenAI API is powered by a diverse set of models with different capabilities and price points. You can also make limited customizations to our original base models for your specific use case with fine-tuning.
| Models | Description |
| GPT-4 | A set of models that improve on GPT-3.5 and can understand as well as generate natural language or code |
| GPT-3.5 | A set of models that improve on GPT-3 and can understand as well as generate natural language or code |
| GPT-3 | A set of models that can understand and generate natural language |
Model endpoint compatibility
Model endpoint compatibility different for Chat and Text completion, you can see the list available below:
Chat
by default the model is gpt-3.5-turbo, you can change it if you subscribe for more optimal results.
| Models | Description | Max Tokens |
| gpt-4 | More capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat. Will be updated with our latest model iteration. | 8,192 |
| gpt-4-0314 | Snapshot of gpt-4 from March 14th 2023. Unlike gpt-4, this model will not receive updates, and will be deprecated 3 months after a new version is released. | 8,192 |
| gpt-4-32k | Same capabilities as the base gpt-4 mode but with 4x the context length. Will be updated with our latest model iteration. | 32,768 |
| gpt-4-32k-0314 | Snapshot of gpt-4-32 from March 14th 2023. Unlike gpt-4-32k, this model will not receive updates, and will be deprecated 3 months after a new version is released. | 32,768 |
| gpt-3.5-turbo | Most capable GPT-3.5 model and optimized for chat at 1/10th the cost of text-davinci-003. Will be updated with our latest model iteration. | 4,096 |
Text Completion
by default the model is text-davinci-003
| Model | Description | Max Tokens |
| text-davinci-003 | Can do any language task with better quality, longer output, and consistent instruction-following than the curie, babbage, or ada models. Also supports inserting completions within text. | 4097 |
| text-davinci-002 | Similar capabilities to text-davinci-003 but trained with supervised fine-tuning instead of reinforcement learning | 4,097 |
| text-curie-001 | Very capable, faster and lower cost than Davinci. | 2,049 |
| text-babbage-001 | Capable of straightforward tasks, very fast, and lower cost. | 2,049 |
| text-ada-001 | Capable of very simple tasks, usually the fastest model in the GPT-3 series, and lowest cost. | 2,049 |