DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is the latest MIT-licensed release from DeepSeek, a natively multimodal mixture-of-experts model that accepts text and image input and returns text. Its causal encoder-decoder design pairs a 20-layer encoder with a 20-layer decoder, routing 6 of 384 experts per token for roughly 8 billion active parameters during prefill and 16 billion during decode, with a 196B-parameter Engram conditional memory accessed sparsely alongside the 552B backbone. Compressed Sparse Attention 2 and an FP4 KV cache of under 1KB per token make a full 1 million token context practical, while continuously controllable reasoning effort lets you trade depth for latency per request. Strong across coding, math, and agentic benchmarks, it is well-suited to long-horizon agent runs, repository-scale engineering, and document-heavy multimodal workloads.

Features

On-demand Deployments

On-demand deployments let you run DeepSeek V4.1 Flash on dedicated GPUs with Sciforium's high-performance serving stack, with high reliability and no rate limits.

Docs

FP4 KV Cache at 1M Context

Compressed Sparse Attention 2 and an FP4 KV cache under 1KB per token keep a full 1M-token multimodal context fast and affordable.

Docs
DeepSeek V4 Flash
DeepSeek V4 Pro
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash 1017
Gemma 4 31B
GLM 5.2
GLM 5.3
GLM 5.3 Flash
Kimi K2.6
Kimi K2.7 Code
Kimi K3
MiniMax H3
MiniMax M3
MiniMax M3.1 Flash
Muse Spark Open
Nemotron 3.5 Super VL
Qwen3.5
Qwen3.8
DeepSeek V4 Flash
DeepSeek V4 Pro
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash 1017
Gemma 4 31B
GLM 5.2
GLM 5.3
GLM 5.3 Flash
Kimi K2.6
Kimi K2.7 Code
Kimi K3
MiniMax H3
MiniMax M3
MiniMax M3.1 Flash
Muse Spark Open
Nemotron 3.5 Super VL
Qwen3.5
Qwen3.8