Using DeepSeek V4 Flash on Yandex AI Studio

Implementation guide · DeepSeek V4 · DeepSeek

ServerlessOpen Source

Yandex AI Studio exposes DeepSeek V4 Flash through model ID deepseek-v4-flash. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-13. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Yandex AI Studio and generate an API key.
  2. 2
    Use the Yandex AI Studio SDK or REST API to call deepseek-v4-flash — see the documentation for request format.
API PortalDocumentationPricing

Code Examples

See Yandex AI Studio documentation for integration details.

Pricing on Yandex AI Studio

Capabilities

ReasoningJSON / Tool useStructured OutputsPrompt Caching

About DeepSeek V4 Flash

DeepSeek V4 Flash is a 284B parameter (13B activated) Mixture-of-Experts language model with 1M-token context. Features a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) for efficient long-context inference. Supports thinking and non-thinking modes. Legacy API aliases deepseek-chat and deepseek-reasoner map to this model's non-thinking and thinking modes respectively. Pricing: $0.14/1M input, $0.28/1M output (cache hit: $0.0028/1M input). MIT licensed.

Full model details →

Model Specs

Released2026-04-24
Parameters284B
Context1M
ArchitectureMixture of Experts

Also available on(5)

OpenRouter$0.06/1MVercel AI Gateway$0.13/1MNovita AI$0.14/1M
Compare all providers →

Provider

Yandex AI Studio

Yandex Cloud

Moscow, Russia