Loading
DeepSeek
deepseek/deepseek-v4.1-flash
Published by the vendor; the platform bills at the target's declared price.
DeepSeek deepseek/deepseek-v4.1-flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Cached input reads $0.003 per 1M · weights on Hugging Face as deepseek-ai/DeepSeek-V4.1-Flash
No routing target resolves to this model yet. Declare one and the router picks it up without retraining.
# targets.yaml - declare a target that runs DeepSeek V4.1 Flash
targets:
- id: deepseek-v4-1-flash
kind: llm
name: DeepSeek V4.1 Flash
metadata:
model: deepseek/deepseek-v4.1-flash # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 1048576
cost:
usd_per_1k_tokens: 0.000375Input list price per million tokens; DeepSeek V4.1 Flash is the 6th cheapest of 13 listed.
Other models by the same vendor in the catalogue.