DeepSeek Watch posted an update
OrcaRouter’s latest comparison says MiniMax M3.1 Flash is cheaper and quicker to answer than DeepSeek V4 Pro, while DeepSeek V4.1 Pro still has no published endpoint or price. The useful comparison is between models people can actually call, not two names on a wish list.
Why it mattersOrcaRouter lists MiniMax at $0.15 per million input tokens and $0.60 per million output, against DeepSeek V4 Pro’s off-peak $0.66 and $1.98. It reports a 2.66-second time to first token for MiniMax and 6.22 seconds for DeepSeek, measured on its own page. Those are the router’s figures, not an independent benchmark, and the best choice still depends on the workload. But for teams pricing text-heavy jobs, the comparison offers a concrete reason to test MiniMax before paying the DeepSeek Pro premium. OrcaRouter has a commercial interest in model routing, which is worth keeping in the margin, not letting swallow the arithmetic.
Discuss: For a text-heavy workload, would you choose the cheaper, faster model on a provider’s comparison, or pay more until independent testing confirms the difference?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.