Skip to content

Commit 59fa81e

Browse files
Keiji KanazawaKeiji Kanazawa
authored andcommitted
Add Turbo Instruct
1 parent 20acdce commit 59fa81e

File tree

1 file changed

+5
-3
lines changed
  • articles/ai-services/openai/concepts

1 file changed

+5
-3
lines changed

articles/ai-services/openai/concepts/models.md

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -38,14 +38,15 @@ The `gpt-4` model supports 8192 max input tokens and the `gpt-4-32k` model suppo
3838

3939
## GPT-3.5
4040

41-
GPT-3.5 models can understand and generate natural language or code. The most capable and cost effective model in the GPT-3.5 family is GPT-3.5 Turbo, which has been optimized for chat and works well for traditional completions tasks as well. We recommend using GPT-3.5 Turbo over [legacy GPT-3.5 and GPT-3 models](./legacy-models.md).
41+
GPT-3.5 models can understand and generate natural language or code. The most capable and cost effective model in the GPT-3.5 family is GPT-3.5 Turbo, which has been optimized for chat and works well for traditional completions tasks as well. GPT-3.5 Turbo Instruct has similar capabilities to `text-davinci-003` using the Completions API instead of Chat Completions. We recommend using GPT-3.5 Turbo and Turbo Instruct over [legacy GPT-3.5 and GPT-3 models](./legacy-models.md).
4242

4343
- `gpt-35-turbo`
4444
- `gpt-35-turbo-16k`
45+
- `gpt-35-turboinstruct`
4546

46-
The `gpt-35-turbo` model supports 4096 max input tokens and the `gpt-35-turbo-16k` model supports up to 16,384 tokens.
47+
The `gpt-35-turbo` model supports 4096 max input tokens and the `gpt-35-turbo-16k` model supports up to 16,384 tokens. `gpt-35-turbo-instruct` supports 4097 max input tokens.
4748

48-
Like GPT-4, use the Chat Completions API to use GPT-3.5 Turbo. To learn more about how to interact with GPT-3.5 Turbo and the Chat Completions API check out our [in-depth how-to](../how-to/chatgpt.md).
49+
To learn more about how to interact with GPT-3.5 Turbo and the Chat Completions API check out our [in-depth how-to](../how-to/chatgpt.md).
4950

5051
## Embeddings models
5152

@@ -97,6 +98,7 @@ GPT-3.5 Turbo is used with the Chat Completion API. GPT-3.5 Turbo (0301) can als
9798
| `gpt-35-turbo`<sup>1</sup> (0301) | East US, France Central, South Central US, UK South, West Europe | N/A | 4,096 | Sep 2021 |
9899
| `gpt-35-turbo` (0613) | Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South | N/A | 4,096 | Sep 2021 |
99100
| `gpt-35-turbo-16k` (0613) | Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South | N/A | 16,384 | Sep 2021 |
101+
| `gpt-35-turbo-instruct` (0914) | East US, Sweden Central | N/A | 4,097 | Sep 2021 |
100102

101103
<sup>1</sup> Version `0301` of gpt-35-turbo will be retired no earlier than July 5, 2024. See [model updates](#model-updates) for model upgrade behavior.
102104

0 commit comments

Comments
 (0)