Icon for DeepSeek

DeepSeek

Open Source Free Trial

Cost-effective inference API with OpenAI-compatible endpoints and open-weight models

DeepSeek offers an inference API for its DeepSeek-V3 and reasoning models with OpenAI-compatible endpoints. Known for strong performance at significantly lower cost than competitors. Models support 128K context windows with both standard chat and chain-of-thought reasoning modes. The underlying models are open-weight, available on Hugging Face.

Pricing: Per token usage

Hosting Cloud
Pricing Usage Based, $0.028/1M tokens (cache hit)
HQ 🇨🇳 China
Founded 2023
License MIT
GitHub 102,046 stars
Screenshot of DeepSeek webpage

DeepSeek prices by model

Per 1M tokens, read off DeepSeek's own pricing page on the date shown.

Model Input / 1M Cached / 1M Output / 1M Checked Notes
DeepSeek V4 Pro (off peak) $0.66 $0.022 $1.98 25 Sep 2026 Off-peak hours (most of the week)
DeepSeek V4 Pro $1.32 $0.044 $3.96 25 Sep 2026 Peak rate; off-peak hours are half price
DeepSeek V4.1 Flash (off peak) $0.15 $0.003 $0.60 25 Sep 2026 Off-peak hours (most of the week)
DeepSeek V4.1 Flash $0.30 $0.006 $1.20 25 Sep 2026 Peak rate; off-peak hours are half price

Work on DeepSeek? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →