---
id: "deepseek/deepseek-v4.1-flash"
also: ["deepseek/deepseek-v4.1-flash-20260910", "deepseek-ai/DeepSeek-V4.1-Flash", "hf/deepseek-ai/DeepSeek-V4.1-Flash", "requesty/deepseek/deepseek-v4.1-flash", "vercel/deepseek/deepseek-v4.1-flash"]
card_usd_per_m: "0.15 in, 0.6 out, at deepseek"
cheapest_list_usd_per_m: "0.006 in, 0.5 out, at relace/fp4 on openrouter"
cheapest_effective_usd_per_m: "0.0048 in, 1.1996 out, at primeintellect on openrouter"
context: 1048576
max_output: 943718
input: ["text", "image"]
output: ["text"]
released: "2026-09-10"
reasoning: ["max", "high", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_logprobs", "top_p"]
endpoints: 85
gateways: "openrouter (45), vercel (24), requesty (11), hf (5)"
no_training: 67
trains: 6
retains_prompts: 15
---
# 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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.