Yandex Foundation Models pricing
Yandex Foundation Models is at the Preview stage. The service is at the Preview stage and is billed according to the Special Terms of Use
In the management console
- YandexGPT API: 10 free requests per hour.
- YandexART: 10 free requests per day.
What goes into the cost of using Yandex Foundation Models
Pricing unit
A pricing unit means a single billing unit. The cost of a billing unit is different for text generation and vectorization.
Text generation
Text generation cost is based on the overall number of prompt and response tokens and depends on the YandexGPT API request parameters. Namely, the cost depends on these parameters:
- Model that gets a request.
- Model working mode.
The number of prompt and response tokens for the same text may vary depending on model.
The number of billing units is based on the overall number of prompt and response tokens and is rounded up to a whole number after applying the multiplier.
Fine-tuned models
The use of summary models is charged according to the YandexGPT Lite rules. The use of models fine-tuned in Yandex DataSphere is charged according to the YandexGPT Pro rules.
Text vectorization
The cost of text vectorization (getting text embeddings) depends on the size of the text submitted for vectorization.
Image generation
At the Preview stage, YandexART is free of charge.
Image generation
At the Preview stage, YandexART is free of charge.
Internal server errors
You are not charged for a request that fails due to an internal server error.
Examples of YandexGPT API usage cost calculation
Calculating text vectorization cost
In this example, we will calculate the cost of using YandexGPT for text vectorization with the following parameters:
- Number of tokens in the request: 2,000.
The cost is calculated as follows:
2,000 × 1.0 × ($0.00008/1,000) = $0.00016
Total: $0.00016.
Where:
- 2,000: Number of tokens in the request.
- 1.0: Multiplier for using text vectorization.
- $0.00008: Cost per 1,000 tokens.
- $0.00008 / 1,000: Cost per token.
Pricing
Text generation in YandexGPT API
Warning
In Kazakhstan, Yandex Cloud can be used free of charge at the Technical Preview stage.
The pricing below applies to Russia.
The prices below are effective as of March 25, 2024.
Text generation in YandexGPT API
Number | Cost, without VAT |
---|---|
1,000 units | $0.0016 |
Model parameters | Multiplier | Cost per 1,000 tokens, without VAT |
---|---|---|
YandexGPT Lite, synchronous mode | 1.00 | $0.0016 |
YandexGPT Lite, asynchronous mode | 0.50 | $0.0008 |
YandexGPT Pro, synchronous mode | 6.00 | $0.0096 |
YandexGPT Pro, asynchronous mode | 3.00 | $0.0048 |
Summary model, synchronous mode | 1.00 | $0.0016 |
Summary model, asynchronous mode | 0.50 | $0.0008 |
Models tuned in DataSphere, synchronous mode | 6.00 | $0.0096 |
Models tuned in DataSphere, asynchronous mode | 3.00 | $0.0048 |
Text vectorization in YandexGPT API
Number | Cost, without VAT |
---|---|
1,000 units | $0.00008 |
Model parameters | Multiplier | Cost per 1,000 tokens, without VAT |
---|---|---|
Embeddings | 1.0 | $0.00008 |