DeepSeek models on Tokenator
Every DeepSeek model available through Tokenator: API ID, context window, usage multiplier and current availability. The key and the base URL stay the same for every model in the catalog — switching models takes one request parameter.
DeepSeekonline
Deepseek V4 Flash
deepseek-v4-flash
1.1 – 1.3×
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
DeepSeekonline
Deepseek V4 Pro
deepseek-v4-pro
1.6×
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.
2 DeepSeek models in the catalog, 2 available right now, context up to 1.05M tokens, multiplier ×1.1–×1.6