Asymmetric design
Input and output use different activation levels (8B / 16B), delivering higher capability at a far lower cost than other models of a similar size.
DeepSeek V4.1 Flash is a 552B MoE model with an asymmetric
Causal-Encoder-Decoder architecture: only 8B parameters are active on the input side
and 16B on the output side. A 1M-token context, native image understanding, and compatibility with the OpenAI and
Anthropic APIs — you only need to rename the model to
deepseek-flash.
deepseek-flash
curl https://api.deepseek.com/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPSEEK_API_KEY" \
-d '{
"model": "deepseek-flash",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": false
}'
Overview
V4.1 Flash is the smallest model in DeepSeek’s brand-new architecture line. The design philosophy is clear: raise the capability ceiling, speed up reasoning, increase throughput, and open a path to scale up to larger parameter models. As a result, a low-cost model beats the previous generation of flagship models on many agentic tests.
Input and output use different activation levels (8B / 16B), delivering higher capability at a far lower cost than other models of a similar size.
The KV cache is compressed aggressively: HBM demand drops to 1/4 and SSD to 1/8 versus the previous generation. For agent workloads — where cache hits make up a large share of the bill — this is the decisive factor.
Image understanding is built into the model (native vision) from the very first Flash release — something
deepseek-v4-pro does not have.
Architecture
Instead of a single computation path for both reading and writing, CED splits the work into two phases with different costs: the read phase (prefill) activates only 8B parameters, while the generation phase (decode) activates 16B. Combined with new pre-training and large-scale RL post-training, the model reaches reasoning levels that surpass its own house’s flagships.
Full technical details are in the DeepSeek V4.1 technical report .
Features
Model capabilities come with a full API surface: tool calling, structured output, reasoning modes, vision, and the two most widely used interface standards today.
Supports both thinking and non-thinking. Thinking is on by default; turn it off for fast, cheap responses on simple tasks.
Call tools and constrain the output to JSON — a good fit for pipelines that need structured data rather than free-form text.
Read images directly in the same API call. No OCR pipeline or separate vision model required.
Fit an entire codebase or long document into a single call, and get answers at the scale of hundreds of thousands of tokens.
Two separate base URLs, so you can reuse existing SDKs, agent frameworks, and tooling. Moving to Flash means changing one line: the model name.
A native Responses API for modern agents, plus FIM completion and chat prefix completion (beta, only in non-thinking mode).
Performance
According to DeepSeek’s announcement, V4.1 Flash has surpassed several flagship models — including DeepSeek V4 Pro — on agentic benchmarks, while also doing better on cost, speed, and total processing time. That is why DeepSeek is retiring V4 Pro from the API and steering users toward Flash.
A note on the numbers: detailed benchmark figures are in DeepSeek’s technical report and official comparison tables. This page does not invent scores — compare directly with the original sources.
| Criteria | deepseek-flash | deepseek-v4-pro |
|---|---|---|
| Model version | DeepSeek-V4.1-Flash | DeepSeek-V4-Pro-0813 |
| Context / output | 1M / 384K | 1M / 384K |
| Vision | Yes | No |
| Concurrency limit | 2,500 | 500 |
| Input price (cache miss) / 1M | $0.30 peak | $1.32 |
| Input price (cache hit) / 1M | $0.006 peak | $0.044 |
| Output price / 1M | $1.20 peak | $3.96 |
| Status | Recommended | Being retired |
Peak pricing is used for direct comparison; off-peak pricing is half. Figures from DeepSeek’s Models & Pricing page. Prices may change without notice.
Pricing
Priced per million tokens, in USD. DeepSeek uses time-of-day pricing: outside peak hours you pay only half the rate.
| Token type (per 1M) | deepseek-flash | deepseek-v4-pro |
|---|---|---|
| Input — cache hit repeated prompt already in cache | $0.006 off-peak $0.003 | $0.044 off-peak $0.022 |
| Input — cache miss new content never sent before | $0.30 off-peak $0.15 | $1.32 off-peak $0.66 |
| Output includes thinking tokens | $1.20 off-peak $0.60 | $3.96 off-peak $1.98 |
Peak hours (Vietnam time, UTC+7): 08:00–11:00 and 13:00–17:00 Monday – Friday (excluding Chinese public holidays) — that is 01:00–04:00 and 06:00–10:00 UTC. Every other window — including full weekends and holidays — is off-peak.
Adjust it to match your actual traffic.
Get started
Get an API key from the DeepSeek Platform, pick the base URL for the standard you already use, and set
model: "deepseek-flash".
No new SDK to learn.
https://api.deepseek.com
https://api.deepseek.com/anthropic
curl https://api.deepseek.com/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPSEEK_API_KEY" \
-d '{
"model": "deepseek-flash",
"messages": [
{"role": "system", "content": "You are a technical assistant. Answer concisely."},
{"role": "user", "content": "Explain the Causal-Encoder-Decoder architecture in 3 bullet points."}
],
"stream": false
}'
The examples illustrate syntax only; for details on parameters (thinking mode, tool calls, prefix completion) see the DeepSeek API Docs.
Roadmap
Two variants, V4-Pro and V4-Flash, launched via API.
The official release of the V4-Pro flagship model.
Multimodal API opened for the Flash line.
CED architecture, model ID deepseek-flash, new pricing in effect, weights released.
From 12:00 Beijing time, requests to deepseek-v4-pro are served by V4.1 Flash.
Tencent (WorkBuddy, CodeBuddy) and OpenCode have fully integrated V4.1 Flash.
deepseek-ai/DeepSeek-V4.1-Flash on Hugging Face, together with the technical report.
DeepSeek helps teams with suitable infrastructure (around 2k GPUs plus a storage cluster) run the model themselves.
FAQ
Can’t find the answer you need? Look it up in the API docs or the official FAQ.
deepseek-flash is the new name for DeepSeek-V4.1-Flash.
The older models deepseek-v4-flash and
deepseek-v4-flash-vision-exp have been retired, but they still
work for compatibility reasons — such requests are served by V4.1-Flash and billed at Flash rates.
No. Just change the model name in your payload and point the base URL at
https://api.deepseek.com (OpenAI-compatible) or
/anthropic. SDKs, message structure, and tool calls stay the same.
V4.1 Flash supports both modes, and thinking is the default. Non-thinking mode is for tasks that need low latency and costs less; it is also the only mode that supports FIM completion. See the Thinking Mode section of the docs for how to switch.
Measured in Vietnam time (UTC+7), peak hours are 08:00–11:00 and 13:00–17:00, Monday through Friday, excluding Chinese public holidays (01:00–04:00 and 06:00–10:00 UTC). Outside those windows — including full weekends and holidays — prices are halved. For teams in Vietnam, the cheapest hours of the day are the evening and overnight (after 17:00 until 08:00 the next day), plus the 11:00–13:00 lunch break.
DeepSeek is retiring V4 Pro. From 12:00 on Sep 14, 2026 (Beijing time) until V4.1 Pro launches, every request
to deepseek-v4-pro is served by V4.1 Flash and billed at Flash rates.
The weights are published publicly on Hugging Face. For large-scale needs, DeepSeek invites you to get in touch if you have the corresponding infrastructure (around 2k GPUs plus a storage cluster).
Flagship capability at small-model pricing. Start with a 1M-token context, native vision, and an API compatible with the OpenAI / Anthropic standards.