DeepSeek V4 Flash
⚠️ DeprecatedLower-latency DeepSeek V4 model for high-throughput chat, coding, and agent workloads; retired in favor of V4.1 Flash
Provider list prices
Capabilities
⚠️ This model was deprecated on Sep 10, 2026
Consider migrating to a newer model from DeepSeek.
Crazyrouter API catalogue
Not confirmed in the current default-group API catalogue.
Catalogue checked: 2026-10-10T14:22:39+00:00. USD per 1M tokens, default group. The first context tier is shown; long contexts may cost more. This is a gateway catalogue snapshot, not a provider release announcement.
Get API Access →Current API modelsVersion History
V4 Flash and V4 Flash Vision Exp retired on September 10, 2026; the deepseek-v4-flash and deepseek-v4-flash-vision-exp names are temporarily routed to V4.1 Flash
Experimental multimodal variant DeepSeek-V4-Flash-Vision-Exp released on the API
DeepSeek V4 Flash official release (build 0731) entered public beta with open weights under the MIT license, re-post-trained on the same architecture with much stronger agent benchmarks
Legacy deepseek-chat and deepseek-reasoner API names, which had pointed to V4 Flash, were discontinued on July 24, 2026
DeepSeek scheduled deepseek-chat and deepseek-reasoner compatibility aliases for retirement on June 15, 2026
DeepSeek V4 Flash released alongside V4 Pro for faster and lower-cost API workloads
Pricing set at $0.14 per 1M input tokens and $0.28 per 1M output tokens