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
Foundation Models usage is detailed out in billing units. 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 total number of billing units is based on the overall number of prompt and response tokens and is rounded up to a whole number.
Tokenization
The use of tokenizer (TokenizerService calls and Tokenizer methods) is not charged.
Fine-tuned models
The use of summary models is charged according to the YandexGPT Lite policy. The use of models fine-tuned in Yandex DataSphere is charged according to the YandexGPT Pro policy.
Text classification
At the Preview stage, the use of classifiers based on YandexGPT is free of charge.
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.
Internal server errors
You are not charged for a request that fails due to an internal server error.
Prices for Russia
Warning
Prices for Yandex Cloud resources vary from region to region. For more information about the available regions, see Regions.
The currency that can be used to pay for resources depends on which legal entity the user has entered into agreement with. For more information about account registration, see Registering an account in Yandex Cloud.
Text generation in YandexGPT API
Amount | Price, including VAT |
---|---|
1,000 units | ₽0.20 |
Amount | Price, including VAT |
---|---|
1,000 units | ₸1.00 |
Model parameters | Number of unitsper token | Cost per 1,000 tokens, including VAT |
---|---|---|
YandexGPT Lite, synchronous mode | 1 | ₽0.20 |
YandexGPT Lite, asynchronous mode | 0.5 | ₽0.10 |
YandexGPT Pro, synchronous mode | 6 | ₽1.20 |
YandexGPT Pro, asynchronous mode | 3 | ₽0.60 |
Summary, synchronous mode | 1 | ₽0.20 |
Summary, asynchronous mode | 0.5 | ₽0.10 |
Model fine-tuned in DataSphere, synchronous mode | 6 | ₽1.20 |
Model fine-tuned in DataSphere, asynchronous mode | 3 | ₽0.60 |
Model parameters | Number of unitsper token | Cost per 1,000 tokens, including VAT |
---|---|---|
YandexGPT Lite, synchronous mode | 1 | ₸1.00 |
YandexGPT Lite, asynchronous mode | 0.5 | ₸0.50 |
YandexGPT Pro, synchronous mode | 6 | ₸6.00 |
YandexGPT Pro, asynchronous mode | 3 | ₸3.00 |
Summary, synchronous mode | 1 | ₸1.00 |
Summary, asynchronous mode | 0.5 | ₸0.50 |
Model fine-tuned in DataSphere, synchronous mode | 6 | ₸6.00 |
Model fine-tuned in DataSphere, asynchronous mode | 3 | ₸3.00 |
Text vectorization in YandexGPT API
Amount | Cost, including VAT |
---|---|
1,000 units | ₽0.01 |
Amount | Price, including VAT |
---|---|
1,000 units | ₸0.05 |
Model parameters | Number of unitsper token | Total cost of processing 1,000 tokens, including VAT |
---|---|---|
Getting text embeddings | 1 | ₽0.01 |
Model parameters | Number of unitsper token | Cost of processing 1,000 tokens, including VAT |
---|---|---|
Getting text embeddings | 1 | ₸0.05 |
Examples of YandexGPT API usage cost calculation
Calculating text generation cost
Cost of using YandexGPT API for text generation with the following parameters:
- Number of prompt tokens: 225
- Number of response tokens: 525
- Model: YandexGPT Lite
- Model working mode: Synchronous
The cost is calculated as follows:
Number of prompt and response tokens: 225 + 525 = 750
Number of units per token for the YandexGPT Lite model in synchronous mode: 1
Total number of units in the usage breakdown: 750
Total: (₽0.20 / 1,000 units) × 750 units = ₽0.15.
Total: (₸1 / 1,000 units) × 750 units = ₸0.75.
Cost of using YandexGPT API for text generation with the following parameters:
- Number of prompt tokens: 115
- Number of response tokens: 1,500
- Model: YandexGPT Pro
- Model working mode: Asynchronous
Number of prompt and response tokens: 115 + 1,500 = 1,615
Cost of 1,000 tokens for the YandexGPT Pro model in asynchronous mode: ₽0.60
Number of units per token for the YandexGPT Pro model in asynchronous mode: 3
Total number of units in the usage breakdown: 1,615 × 3 = 4,845
Total: (₽0.60 / 1,000 tokens) × 1,615 tokens = ₽0.969 rounded to ₽0.97.
Number of prompt and response tokens: 115 + 1,500 = 1,615
Cost of 1,000 tokens for the YandexGPT Pro model in asynchronous mode: ₸3.00
Number of units per token for the YandexGPT Pro model in asynchronous mode: 3
Total number of units in the usage breakdown: 1,615 × 3 = 4,845
Total: (₸3.00 / 1,000 tokens) × 1,615 tokens = ₸4.845 rounded to ₸4.85.
Cost of using YandexGPT API for text generation with the following parameters:
- Number of prompt tokens: 1,020
- Number of response tokens: 30
- YandexGPT Pro model fine-tuned in DataSphere
- Model working mode: Synchronous
Number of prompt and response tokens: 1,020 + 30 = 1,050
Cost of 1,000 tokens for the model fine-tuned in DataSphere, synchronous mode: ₽1.20
Number of units per token for the model fine-tuned in DataSphere, synchronous mode: 6
Total number of units in the usage breakdown: 1,050 × 6 = 6,300
Total: (₽0.20 / 1,000 units) × 6,300 units = ₽1.26 or (₽1.20 / 1,000 tokens) × 1,050 tokens = ₽1.26.
Number of prompt and response tokens: 1,020 + 30 = 1,050
Cost of 1,000 tokens for the model fine-tuned in DataSphere, synchronous mode: ₸6.00
Number of units per token for the model fine-tuned in DataSphere, synchronous mode: 6
Total number of units in the usage breakdown: 1,050 × 6 = 6,300
Total: (₸1.00 / 1,000 units) × 6,300 units = ₸6.30 or (₸6.00 / 1,000 tokens) × 1,050 tokens = ₸6.30.
Calculating text vectorization cost
Cost of using YandexGPT for text vectorization with the following parameters:
- Number of tokens in the request: 2,000
- Multiplier for using text vectorization: 1.0
2,000 × 1.0 × (₽0.01 / 1,000) = ₽0.02
Total: ₽0.02.
Where:
- ₽0.01: Cost per 1,000 tokens.
- ₽0.01 / 1,000: Cost per token.
2,000 × 1.0 × (₸0.05 / 1,000) = ₸0.10
Total: ₸0.10.
Where:
- ₸0.05: Cost per 1,000 tokens.
- ₸0.05 / 1,000: Cost per token.