DeepSeek’s 2024 workhorse—fast, fluent, and fully open-weights.
Price per 1 million tokens
per 1M tokens you send
per 1M tokens you receive
Input tokens are what you send to the AI, output tokens are what the AI sends back. These rates are set by the provider and reflect the current DeepSeek DeepSeek v3 (old) API pricing. Price accurate as of June 2025.
per month
per month
per month
First-generation 671-B MoE DeepSeek model (chat endpoint); now kept for backward compatibility.
The context window is the maximum amount of text the model can "see" at once. Larger windows allow for longer conversations or documents.
Join thousands of users who have switched to API.chat and are saving on their AI expenses while enjoying a better experience.