API platform ↗
DeepSeek model APIs for reasoning, code, structured output and tool calls.
TOOLORA / Local reading edition
DeepSeek
A language-model service available through chat and compatible APIs for apps and agents.
Overview
DeepSeek provides a chat interface and developer APIs for language-model questions, generation and reasoning-based applications. Developers send messages and instructions through OpenAI- or Anthropic-compatible formats, or configure it as the backend of coding assistants and agents. Its SDK examples and agent-integration guides suit teams adding model capabilities to existing software.
- Company country / region
- China · Company registration
Access options
Web chat ↗
Chat directly in DeepSeek’s web app, using thinking for text and coding tasks.
Usage guide & costs
- Useful for
Use it as the model backend for apps, coding assistants or agents, with configurable thinking and tool calls. The foundation-model entry is for developers; the profile also links to chat.
Official details ↗ · Official details ↗- Access & setup
Obtain an API key, then configure the endpoint, model and messages. Current documented IDs are deepseek-flash and deepseek-v4-pro. Chat sign-in does not configure an API client.
Official details ↗- Suggested workflow
Start with a small set of real tasks to compare thinking settings, latency and token use. Flash and Pro differ in vision support; check the model table before sending images.
Official details ↗ · Official details ↗ · Official details ↗- Billing model
API billing is based on input and output tokens; rates depend on the model and cache hits.
Official details ↗- Before you start
Search / Fetch has separate billing rules. The official page schedules per-request charges from November 1, 2026; it is currently free.
Official details ↗
Capabilities
Compatible API calls
Call models with messages and task instructions using documented OpenAI and Anthropic API formats and SDK configurations.
Agent and coding integrations
Configure DeepSeek in compatible coding assistants or agent tools without building a separate chat interface.
Related product news
News summaries are prepared by this site; open the title to read the original.
DeepSeek updates V4.1-Flash-1017
DeepSeek upgrades its web, app and API to V4.1-Flash-1017, retaining the deepseek-flash model ID and pricing. The update targets reasoning and agent tasks, with optimizations for DeepSeek Harness, Tencent CodeBuddy and WorkBuddy.
DeepSeek ↗Product profile →DeepSeek opens its in-house search API
DeepSeek opens Search / Fetch APIs for its own search engine, providing multilingual web search and page retrieval for models and agents.
DeepSeek ↗Product profile →DeepSeek releases V4.1-Flash
DeepSeek releases V4.1-Flash with native visual understanding and an asymmetric MoE architecture aimed at reducing inference and cache costs. The multimodal API uses deepseek-flash; older Flash model IDs temporarily route to the new model.
DeepSeek ↗Product profile →Official sources and references
- Official websitehttps://platform.deepseek.com/
- Official websitehttps://chat.deepseek.com/
- Documentationhttps://api-docs.deepseek.com/guides/thinking_mode/
Descriptions summarize public information; consult official websites for features, pricing and regional availability.