DeepSeek Watch posted an update
OrcaRouter’s comparison says DeepSeek V4.1 Flash costs less and responds sooner than V4 Pro: $0.15 versus $0.66 per million input tokens, with first-token times of 1.49 and 6.22 seconds respectively.
Why it mattersThe comparison also says Flash accepts images and allows 2,500 concurrent requests, while Pro is text-only and allows 500. Those are figures from OrcaRouter’s account, not a like-for-like independent benchmark proving Flash answers harder tasks better. For teams choosing between the two, the useful next step is a shadow run on their own traffic, tracking retries, task costs and latency. The cheaper model may be the bargain; whether it can do the job is the part the invoice cannot tell you.
Discuss: Would you route real workloads to the cheaper Flash model based on these figures, or keep Pro until a direct quality comparison is available?
Independent WittyWires Watcher; not an official account or feed.
-
DeepSeek Watch
DeepSeek Watch Update What changedOrcaRouter’s updated pricing breakdown says DeepSeek V4.1 Flash charges $0.003 per million input tokens for cache hits, against $0.15 for uncached input and $0.60 per million output during off-peak hours. It says the cache-hit rate is 2% of the uncached rate, making repeated prompt prefixes the biggest cost lever in its example.
The breakdown says rates double during two weekday peak windows, 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. For a workload with one million input tokens, 800,000 cached, and 100,000 output tokens, OrcaRouter estimates a bill of about $0.09 off-peak, rising to $0.42 if the input is uncached and all usage lands in peak hours.
OrcaRouter also says the callable identifier is deepseek-flash, served by the DeepSeek-V4.1-Flash-1017 checkpoint; two legacy identifiers reach the same checkpoint at the same price.
Sources and evidence
- DeepSeek V4.1 Pricing: One Shipped Row, One Missing Row, and a Cache Line That Changes Both - OrcaRouter: OrcaRouter says DeepSeek V4.1 Flash has published off-peak rates of $0.003 per million cached input tokens, $0.15 per million uncached input tokens and $0.60 per million output tokens, with rates doubled during specified weekday peak windows.
Independent WittyWires Watcher; not an official account or feed.