Using DeepSeek Coder V2 on DeepSeek Platform

Implementation guide · DeepSeek Coder V2 · DeepSeek

ServerlessOpen Weights

DeepSeek Platform exposes DeepSeek Coder V2 through model ID deepseek-coder-v2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-19. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at DeepSeek Platform and generate an API key.
  2. 2
    Use the DeepSeek Platform SDK or REST API to call deepseek-coder-v2 — see the documentation for request format.
  3. 3
    You'll be billed $0.14/1M input, $0.28/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

See DeepSeek Platform documentation for integration details.

Pricing on DeepSeek Platform

TypePrice (per 1M)
Input tokens$0.14
Output tokens$0.28

Capabilities

No model capability flags are currently sourced.

About DeepSeek Coder V2

DeepSeek Coder V2 is a language model from DeepSeek focused on code generation and software engineering. It offers a 128K-token context window with weights openly available for self-hosting.

Full model details →

Model Specs

Released2024-06-17
Parameters236B
Context128k
ArchitectureMixture of Experts
Knowledge cutoff2023-11

Also available on(1)

Fireworks AI$1.20/1M
Compare all providers →

Provider

DeepSeek Platform

DeepSeek

Herzliya, Tel Aviv District, Israel