Unverified50% confidenceBenchmarkExact time
In a 3D city generator test, V4.1 Flash achieved an output speed of 287 tokens per second, with a total completion time of 83 minutes.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedThe community measured V4.1 Flash reaching a peak speed of 400 tokens/second, with little change in speed even when the context is extended to 1 million tokens.80% similarUnverifiedIn an image-to-website replication test, V4 Flash v-simple took 2 minutes and 54 seconds and cost 0.1 yuan but had significant recognition errors, while V4.1 Flash took 8 minutes and 26 seconds and cost 1.4 yuan with more complete recognition.80% similarVerifiedDeepSeek V4 Flash has a rate limit of 10 requests per minute (10 RPM) and 100K tokens per minute (100K TPM) on the OpenModel platform.74% similarUnverifiedOn a dual-Spark system, DeepSeek V4 Flash (FP8 quantization) peaks at approximately 53 tokens per second.74% similarUnverifiedDeepSeek V4 Flash is a cloud-based model focused on high throughput, with an inference speed of approximately 140 tokens per second.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/908599API
curl https://kongchang.com/api/v1/knowledge/claims/908599MCP
get_claim(id=908599)