DeepSeek
Strong coding and reasoning, cost-effective, good Chinese support.
getModelKey links official API key pages only. We do not sell, generate, or broker API keys.
Overview
DeepSeek provides coding- and reasoning-strong models through its platform API. The current model is DeepSeek V4.1 Flash, available through the canonical deepseek-flash ID with native text and image input, a 1M-token context window, and thinking controls.
The retired deepseek-v4-flash and deepseek-v4-flash-vision-exp IDs temporarily route to V4.1 Flash. From September 14, 2026 at 04:00 UTC, deepseek-v4-pro will also route to V4.1 Flash and use Flash pricing until V4.1 Pro launches.
How to Get an API Key
- Register or sign in at platform.deepseek.com.
- Open API Keys at https://platform.deepseek.com/api_keys and create a new key.
- Copy the key when it is displayed and keep it out of public repos.
- Call DeepSeek’s OpenAI-compatible chat APIs with that key using platform.deepseek.com API docs.
Common Models
FAQ
Are DeepSeek APIs OpenAI-compatible?
Yes. The platform documents OpenAI-compatible endpoints; use your DeepSeek key and the official base URL.
Which DeepSeek models need a platform key?
Use deepseek-flash for new V4.1 Flash integrations. The old Flash IDs temporarily route to the same model, while deepseek-v4-pro is scheduled to route to V4.1 Flash from September 14, 2026 at 04:00 UTC.
What are the current DeepSeek V4.1 Flash prices?
As of September 13, 2026, off-peak direct API rates per 1M tokens are ¥0.02 cached input, ¥1 uncached input, and ¥4 output. Weekday peak rates are twice those amounts during Beijing time 09:00–12:00 and 14:00–18:00. Verify live prices before recharging.