Ordinal
Which model is worth using
1 Oct 2026
DeepSeek
DeepSeek ships open weights and a very cheap cache. V4.1 Flash is the current fast model. The official price doubles during peak hours.
DeepSeek V4.1 Flash
10 Sep 2026 · Open weights · The current fast DeepSeek. Index 39 at max, about 209 tokens per second, and one of the cheapest measured tasks among models that are actually capable.
DeepSeek V4 Pro
13 Aug 2026 · Open weights · The larger DeepSeek still on the official API. Index 36 at max, behind its own flash model.