YandexGPT API models
YandexGPT API provides access to large generative models:
- Standard YandexGPT Lite suitable for solving tasks in real time.
- Large YandexGPT Pro that provides more accurate responses to complex prompts.
If out-of-the-box models are not enough, you can fine-tune YandexGPT Pro in Yandex DataSphere
To access your model via the API, under modelUri
, specify its URI/latest
, /rc
, and /deprecated
segments indicate the model version. /latest
is used by default.
YandexGPT API generative models
When updating models, YandexGPT generations available in different branches (/latest
, /rc
, and /deprecated
segments) may change.
Warning
The next update of the model in the Latest
branch is scheduled for December 1, 2024.
Model |
URI |
YandexGPT generation |
|
YandexGPT Lite |
|
334 |
Asynchronous, synchronous |
YandexGPT Pro |
|
334 |
Asynchronous, synchronous |
YandexGPT Pro 32k |
|
4 |
Synchronous1 |
Model fine-tuned in Yandex DataSphere |
|
3 |
Asynchronous, synchronous |
Modified models share usage quotas with their basic models.
1 YandexGPT Pro 32k features an expanded context and is designed specifically to handle large texts in synchronous mode. In asynchronous mode, the YandexGPT Pro model supports the same amount of context.
Model lifecycle
Each model has certain lifecycle characteristics, such as the model name, branch, and release date. These characteristics allow you to precisely identify the model version. Below, you can see our rules for updating models. Refer to these rules to adjust your solutions to a new version as apporpriate.
For each model, there are three branches (in the order from the oldest to the newest one): Deprecated
, Latest
, and Release Candidate
(RC
). Each of the branches is subject to the SLA.
The RC
branch is updated as the new model is ready and may change at any time. When a model in the RC
branch is ready for general use, we announce the upcoming release both in the release notes and our Telegram community
One month after the announcement, the RC
version becomes the Latest
one, and the Latest
version is moved to the Deprecated
branch. We continue the support of the Deprecated
version for one more month, after which models in the Deprecated
and Latest
branches become identical.
Tuning capabilities
You cannot tune the YandexGPT Pro model on new information, e.g., a support service knowledge base. However, you can train the model to generate responses in a specific format or analyze texts. You can train the model to:
- Summarize and rewrite texts.
- Generate questions and answers from text input.
- Provide responses in a particular format or style.
- Classify texts, forms of address, and dialogs.
- Extract data from texts.
If you want to fine-tune the model for other capabilities, contact our support team
Note
To make sure your fine-tuned model works properly, specify the prompt used for training in your message with the system
sender role.