Expired50% confidenceEventExact time
The Ollama platform acknowledged that its hosted deepseek-v4.1-flash model experienced billing anomalies over the past several hours.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/29/2026
First Seen
Valid until: 10/13/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe officially advertised 1 million token context of DeepSeek V4 Flash cannot truly be output on this machine, as the system will crash.67% similarUnverifieddeepseek-v4.1-flash belongs to the lightweight, high-throughput flash-class models, which are typically lower in price and called frequently.64% similarUnverifiedThis practical test deployed DeepSeek-V4-Flash (DSpark version) via GPUStack in an 8-GPU H20-141G environment.64% similarVerifiedV4.1 Flash surpassed Opus 5 on the DeepSWE benchmark by a narrow margin of 0.2 points.64% similarUnverifiedThis update adds support for the official model ID deepseek-flash; new sessions default to V4.1 Flash, but explicitly configured models take higher priority.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/959501API
curl https://kongchang.com/api/v1/knowledge/claims/959501MCP
get_claim(id=959501)