Skip to main content
Use deepseek-flash for the current Flash model, or deepseek-v4-pro for Pro. These model IDs were checked against the provider catalog on October 24, 2026. DeepSeek exposes an OpenAI-compatible API, so Agentium connects using the standard openai SDK pointed at https://api.deepseek.com.
DeepSeek enforces account-level concurrency limits and returns HTTP 429 when they are exceeded. See Rate limit and isolation.

Setup


Factory

string
required
Model ID (e.g., "deepseek-flash", "deepseek-v4-pro").
DeepSeekConfig
Optional { apiKey?, baseURL? }.

Supported models


The old deepseek-chat and deepseek-reasoner names were retired. The deepseek-v4-flash and deepseek-v4-flash-vision-exp aliases are still accepted by DeepSeek but now resolve to the current Flash model. Agentium forwards your chosen ID unchanged and records the returned model identity separately; it does not guess a replacement or a tariff. See the current catalog and retirement notice.

Basic example


Reasoning

Set reasoning.enabled to send thinking: { type: "enabled" } and reasoning_effort. DeepSeek only accepts low, high, and max, so medium is sent as high. effort: "none" sends thinking: { type: "disabled" }. Tool turns replay reasoning_content. The provider returns supported reasoning content in reasoning_content:

Tool calling


Full example

The tracker preserves reported usage. A missing tariff or billing field makes total null. Supply a catalog that matches your billing provider, API, model or deployment, tier, and region; see cost accounting.

Environment variables