bytedance:deepseek/deepseek-v4-1-flash-260910
Common Name: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash with native multimodal understanding and efficient reasoning for agentic workloads.
Specifications
Context
1000K
Maximum Output
384K
Inputtext, image
Outputtext
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Availability Trend (24h)
Pricing
Peak window (local): 01:00–04:00, 06:00–10:00
Off-peak
Input¥0.50/MTokens
Cached Input¥0.02/MTokens
Output¥2.00/MTokens
Peak
Input¥1.00/MTokens
Cached Input¥0.04/MTokens
Output¥4.00/MTokens
Performance Metrics (24h)
Similar Models
¥0.80/¥8.00/M
ctx128Kmax—avail—tps—
InOutCap
A vision-focused Doubao Seed 1.6 model for text, image, and video understanding.
¥0.80/¥2.00/M
ctx256Kmax16Kavail—tps—
InOutCap
ByteDance's general-purpose multimodal model with a 256K context window for text, image, and video understanding.
¥0.60/¥3.60/M
ctx256Kmax32Kavail—tps—
InOutCap
A lower-cost Doubao Seed 2.0 model for everyday multimodal workloads.
¥0.60/¥3.60/M
ctx256Kmax32Kavail—tps—
InOutCap
A lower-cost Doubao Seed 2.0 model for everyday multimodal workloads.