DeepSeek is an API provider that hosts large language models. Active models: 4; From (input): $0.14 / 1M tok; Avg throughput: 55 tok/s; Avg latency: 0.30 s; Max context: 1.0M.

DeepSeek currently serves 4 active models out of 9 historical offerings on LLM Stats.

DeepSeek input pricing starts from $0.14 per 1M tokens, with the most expensive offering at $1.74 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

DeepSeek averages 55 output tokens per second across its catalog, with average latency of 0.30s. Per-model performance is shown in the Performance tab.

Most providers expose an OpenAI-compatible /v1/chat/completions endpoint so you can switch from OpenAI to DeepSeek by changing only the base URL and API key. Check https://deepseek.com/ for the exact endpoint format and any provider-specific parameters.

DeepSeek hosts models from DeepSeek. See the Models tab for the full catalog grouped by creator.

Sign up at https://deepseek.com/ to get an API key, then call DeepSeek's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at DeepSeek's base URL with your key. Use the Pricing and Performance tabs above to pick the right model for your latency, cost, and context-window requirements.