Yandex Foundation Models pricing policy

To calculate the cost of using the service, see the prices in this section.

In the management console, new users without a billing account have access to models for testing:

• YandexGPT API: 10 free requests per hour.
• YandexART: 10 free requests per day.

What goes into the cost of using Yandex Foundation ModelsWhat goes into the cost of using Yandex Foundation Models

Billing unitBilling unit

Foundation Models usage is detailed out in billing units. The cost of a billing unit is different for text generation and vectorization.

Text generationText 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 the following:

• 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.

TokenizationTokenization

The use of tokenizer (TokenizerService calls and Tokenizer methods) is not charged.

Fine-tuned modelsFine-tuned models

The use of models fine-tuned in Yandex DataSphere is charged according to the YandexGPT Pro policy.

Text classificationText classification

At the Preview stage, the use of classifiers based on YandexGPT is free of charge.

The cost of text classification depends on the classification model you use and the number of tokens you provide.

• When classifying with YandexGPT Lite, a billing unit is a request of up to 1,000 tokens.
• When classifying with YandexGPT Pro and fine-tuned classifiers, a billing unit is a request of up to 250 tokens.

Requests with less than one billing unit are rounded up to the next integer. Large texts are billed as multiple requests with rounding up.

For example, classifying a text of 770 tokens with YandexGPT Lite will be billed as a single request, i.e., as one billing unit.
The same 770-token text classified with YandexGPT Pro or a fine-tuned classifier will be billed as four requests.

Text vectorizationText vectorization

The cost of text vectorization (getting text embeddings) depends on the size of the text submitted for vectorization.

Work of assistantsWork of assistants

At the Preview stage, you can use AI Assistant API and store files free of charge; however, you will be charged for models according to the text generation rules.

Image generationImage generation

You are charged for each generation request in YandexART. The requests are not idempotent; therefore, two requests with the same settings and generation prompt are two separate requests.

Internal server errorsInternal server errors

You are not charged for a request that fails due to an internal server error.

Prices for the Russia regionPrices for the Russia region

Text generationText generation

Number	Cost, without VAT
1,000 units	$0.0016

Model parameters	Number of units per token	Cost per 1,000 tokens, without VAT
YandexGPT Lite, synchronous mode	1	$0.0016
YandexGPT Lite, asynchronous mode	0.5	$0.0008
YandexGPT Pro, synchronous mode	6	$0.0096
YandexGPT Pro, asynchronous mode	3	$0.0048
Models fine-tuned in DataSphere, synchronous mode	6	$0.0096
Models fine-tuned in DataSphere, asynchronous mode	3	$0.0048
Llama 8b1, synchronous mode	1	$0.0016
Llama 8b, asynchronous mode	0.5	$0.0008
Llama 70b1, synchronous mode	6	$0.0096
Llama 70b, asynchronous mode	3	$0.0048

Text classificationText classification

Service	Cost, without VAT
1 request (1,000 tokens) to classifier based on YandexGPT Lite	$0.0012
1 request (250 tokens) to classifier based on YandexGPT Pro	$0.0012
1 request (250 tokens) to tuned classifier	$0.0012

Text vectorizationText vectorization

Number	Cost, without VAT
1,000 units	$0.00008

Model parameters	Number of units per token	Cost per 1,000 tokens, without VAT
Embeddings	1	$0.00008

Image generationImage generation

Service	Cost, without VAT
1 request for YandexART image generation	$0.0176

Examples of YandexGPT API usage cost calculationExamples of YandexGPT API usage cost calculation

Calculating text generation costCalculating text generation cost

Example 1Example 1

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

Total: ($0.0016 / 1,000 units) × 750 units = $0.0015

Example 2Example 2

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

The cost is calculated as follows:

• Number of prompt and response tokens: 115 + 1,500 = 1,615
• Price per 1,000 tokens for the YandexGPT Pro model, asynchronous mode: $0.0048
• Number of units per token for the YandexGPT Pro model, asynchronous mode: 3
• Total number of units in usage details: 1,615 × 3 = 4,845

Total: ($0.0048 / 1,000 tokens) × 1,615 tokens = $0.007752

Example 3Example 3

Cost of using YandexGPT API for text generation with the following parameters:

• Number of prompt tokens: 1,020
• Number of response tokens: 30
• Model: YandexGPT Pro fine-tuned in DataSphere
• Model working mode: Synchronous

The cost is calculated as follows:

• Number of prompt and response tokens: 1,020 + 30 = 1,050
• Price per 1,000 tokens for the model fine-tuned in DataSphere, synchronous mode: $0.0096
• Number of units per token for the model fine-tuned in DataSphere, synchronous mode: 6
• Total number of units in usage details: 1,050 × 6 = 6,300

Total: ($0.0016 / 1,000 units) × 6,300 units = $0.01008 or ($0.0096 / 1,000 tokens) × 1,050 tokens = $0.01008

Calculating text vectorization costCalculating text vectorization cost

Cost of using YandexGPT API for text vectorization with the following parameter:

• Number of tokens in the request: 2,000

¹ Llama was created by Meta. Meta is designated as an extremist organization and its activities are prohibited in Russia.