DeepSeek: DeepSeek V4.1 Flash (batch)
deepseek/deepseek-v4.1-flash:batch
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Modalities
In / Out Price
$0.112 / $0.336 per 1M
Context
1M
Released
Sep 10, 2026
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 DeepInfrafp8 | 1M | $0.112 | $0.336 | $0.00336 | — | — | — |