DeepSeek V4.1 Flash
✅ ActiveSmallest model of DeepSeek's new architecture family with native multimodal visual understanding, served under the deepseek-flash API name
Provider list prices
Context Window
1M
Input Price
$0.30/1M
Peak-hour rate; off-peak (weekends and outside 01:00-04:00 and 06:00-10:00 UTC weekdays) is 50% lower
Output Price
$1.20/1M
Released
Sep 10, 2026
Capabilities
textvisioncodereasoningfunction-calling
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
Sep 10, 2026New Release
DeepSeek V4.1 Flash released with a 1M context window, up to 384K output, native vision, and support for both thinking and non-thinking modes; call it via the deepseek-flash model name
Sep 10, 2026Pricing Change
API pricing reduced to $0.30 per 1M input tokens and $1.20 per 1M output tokens at peak hours ($0.15 and $0.60 off-peak); cache hits $0.006 per 1M tokens