This is a list of the OpenAI models provided by OpenAI API, along with their descriptions and OpenAI_MaxTokens, which can be set as the value of the OpenAI_Model text variable in this Plugin for VoiceAttack. If a model is set to this text variable which is inapplicable to the context of the current plugin call, the default model for that function will be used instead.

These values are hard set into the codebase of the plugin, and so reflect values only as they apply to this compilation, until changed, even if these values change on the OpenAI API Reference. I will of course maintain this plugin, and keep these values in sync with published values as best as able through regular updates as needed. Descriptions below are literally those in the OpenAI Documentation.

NOTE: It is not possible to change the Whisper, Dall-E, Moderation, Files, or Embedding models.

---

text-ada-001

Capable of very simple tasks, usually the fastest model in the GPT-3 series, and lowest cost.

---

text-babbage-001

Capable of straightforward tasks, very fast, and lower cost.

---

text-curie-001

Very capable, but faster and lower cost than Davinci.

---

text-davinci-003

Most capable GPT-3 model. Can do any task the other models can do, often with higher quality, longer output and better instruction-following. Also supports inserting completions within text.

---

code-cushman-001

Almost as capable as Davinci Codex, but slightly faster. This speed advantage may make it preferable for real-time applications.

---

code-davinci-002

Most capable Codex model. Particularly good at translating natural language to code. In addition to completing code, also supports inserting completions within code.

      |   (table of contents)   |   (back to top)   |

---

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 the latest model iteration.

---

gpt-3.5-turbo-0301

Snapshot of gpt-3.5-turbo from March 1st 2023. Unlike gpt-3.5-turbo, this model will not receive updates, and will only be supported for a three month period ending on June 1st 2023.

---

gpt-4

More capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat. Will be updated with the latest model iteration. Currently in limited beta so your OpenAI account needs to be whitelisted to use this.

---

gpt-4-32k

Same capabilities as the base gpt-4 mode but with 4x the context length. Will be updated with the latest model iteration. Currently in limited beta so your OpenAI account needs to be whitelisted to use this.

      |   (table of contents)   |   (back to top)   |