GPT-3 Instruct Models by OpenAI
OpenAIProprietary
This model family is considered obsolete. Consider newer alternatives in Related Model Families below.
4 models2020–2022Up to 4k ctx
Details
ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use: conditional
Models4
Released2020–2022
Max context4k
Links
WebsiteAbout
GPT-3.5 Turbo Instruct has similar capabilities to text-davinci-003 using the Completions API instead of the Chat Completions API. It is recommended to use GPT-3.5 Turbo and GPT-3.5 Turbo Instruct over legacy GPT-3.5 and GPT-3 models.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
4 in view
text-davinciCurrent
Use when the workload needs 4k context and 175B parameters.
2022-014k context175B parameters
text-curieCurrent
Use when the workload needs 2k context and 6.7B parameters.
2020-062k context6.7B parameters
text-babbageCurrent
Use when the workload needs 2k context and 1.3B parameters.
2020-062k context1.3B parameters
text-adaCurrent
Use when the workload needs 2k context and 350M parameters.
2020-062k context350M parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| text-davinci | Use when the workload needs 4k context and 175B parameters. | 2022-01 | 4k context175B parameters | Current |
| text-curie | Use when the workload needs 2k context and 6.7B parameters. | 2020-06 | 2k context6.7B parameters | Current |
| text-babbage | Use when the workload needs 2k context and 1.3B parameters. | 2020-06 | 2k context1.3B parameters | Current |
| text-ada | Use when the workload needs 2k context and 350M parameters. | 2020-06 | 2k context350M parameters | Current |
Release Timeline
2 release groups2022-01
1 current
text-davinci
Current4k context175B parameters
2020-06
3 current
text-ada
Current2k context350M parameters
text-babbage
Current2k context1.3B parameters
text-curie
Current2k context6.7B parameters
Specifications(4 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| text-davinci | 2022-01 | 4k | 175B |
| text-curie | 2020-06 | 2k | 6.7B |
| text-babbage | 2020-06 | 2k | 1.3B |
| text-ada | 2020-06 | 2k | 350M |
Popular comparisons in this family
- Llama 3.1 NemoGuard 8B Content Safety vs text-curie68
- Llama 2 7B vs text-davinci49
- GPT-1 vs text-davinci45
- Llama 2 70B Chat vs text-davinci28
- Llama 3.2 NV RerankQA 1B v2 vs text-davinci15
- Codex 1 vs text-davinci12
- GPT-2 vs text-davinci11
- Hunyuan Hy3 Preview vs text-davinci9
- GPT-4 vs text-davinci7
- Claude Instant vs text-davinci6
Frequently Asked Questions
- What is GPT-3 Instruct used for?
- GPT-3 Instruct is used for chatbot and role-playing use cases. The family description and listed model capabilities point to those workloads as the best fit.
- How does GPT-3 Instruct compare to GPT Realtime 2?
- GPT-3 Instruct by OpenAI is strongest where you need chatbot and role-playing use cases, while GPT Realtime 2 by OpenAI is the closest related family to check for realtime voice. GPT-3 Instruct has 4 listed variants and reaches up to 4k context, while GPT Realtime 2 reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which GPT-3 Instruct model should I use?
- If price is the main constraint, use the pricing table first because GPT-3 Instruct does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate text-davinci with 4k context.
