Vendor API
DeepSeek
DeepSeek through your own DeepSeek API key and its REST API, for text and tool-calling chat with thinking on demand, across the current V4 tiers. Requests go straight from your machine to DeepSeek and you pay DeepSeek's own per-token rates.
Text(2 models)
V4.1 Flash
DeepSeek's fast mixture-of-experts model and the first on its Causal Encoder-Decoder architecture, with image input, a 1M-token context and native tool calling.
Oct 2026
V4 Pro
DeepSeek's high-capability V4 model (MIT) with a 1M-token context, dual thinking modes, and stronger agentic performance than V4 Flash.
Aug 2026