OpenRouter 模型 ↗ · 2026-09-10
deepseek/deepseek-v4.1-flash
模型发布 OpenRouter 模型 原文语言:中文
OpenRouter 于 2026-09-10 收录该模型(收录时间不等于模型正式发布日期);上下文:1,048,576 tokens;输入价:$0.0507/百万 tokens;输出价:$0.2028/百万 tokens;定位(来源描述):DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the…
全文
DeepSeek: DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
Model weights
Compare
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 ExpOpens in new tab.
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 ProOpens in new tab on performance, speed, and task completion time.
Modalities
In / out price
$0.051 / $0.567per 1M
Context
1.0M
Released
Sep 10, 2026
Compare
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
Latency / throughput
$0.0510$0.567$0.018000.28s181 tok/s
100.00%
$0.1950$0.660$0.003000.30s149 tok/s
99.93%
$0.1900$0.650$0.012000.24s168 tok/s
100.00%
$0.0960$0.384$0.001920.82s124 tok/s
100.00%
$0.1300$0.650$0.002000.64s139 tok/s
96.56%
30% off
$0.20$0.1400$0.60$0.420$0.006$0.004200.59s117 tok/s
100.00%
$0.1200$0.500$0.003000.52s107 tok/s
100.00%
$0.2250$0.900$0.006000.64s165 tok/s
100.00%
$0.3000$1.200$0.007000.53s204 tok/s
99.76%
$0.1030$0.600$0.008000.22s110 tok/s
99.96%
Priority30% off
$0.30$0.2100$0.90$0.630$0.009$0.006300.53s120 tok/s
99.96%
$0.3000$1.200$0.006000.23s238 tok/s
100.00%
$0.2900$1.200$0.007000.53s174 tok/s
100.00%
$0.1030$0.600$0.008000.24s97 tok/s
100.00%
$0.3000$1.200$0.007500.75s185 tok/s
99.41%
$0.3000$1.200$0.006000.57s165 tok/s
100.00%
$0.0700$1.200$0.006000.74s154 tok/s
100.00%
$0.2600$1.170$0.005800.59s157 tok/s
100.00%
$0.3000$1.200$0.030000.28s174 tok/s
100.00%
$0.3000$1.200$0.006000.31s154 tok/s
99.86%
$0.4500$1.800$0.009000.34s196 tok/s
100.00%
35% off
$0.30$0.1950$1.20$0.780$0.006$0.003900.95s104 tok/s
100.00%
51% off
$0.30$0.1470$1.20$0.588$0.006$0.002941.07s79 tok/s
100.00%
$0.2125$0.750$0.050000.64s93 tok/s
99.84%
$0.2100$0.840$0.004201.02s89 tok/s
99.45%
Fast
$0.4500$1.800$0.009000.35s193 tok/s
100.00%
$0.3000$1.200$0.030000.82s64 tok/s
99.88%
$0.3000$1.200$0.006001.25s48 tok/s
99.96%
$0.3000$1.200$0.007000.24s189 tok/s
99.76%
20% off
$0.15$0.1200$0.80$0.640$0.01$0.008000.29s80 tok/s
99.06%
$0.1350$0.540$0.013500.57s56 tok/s
100.00%
40% off
$0.30$0.1800$1.20$0.720$0.006$0.003602.17s50 tok/s
99.96%
$0.3000$1.200$0.006001.30s98 tok/s
100.00%
$0.2100$0.840$0.004200.63s110 tok/s
99.93%
Not used in Standard routing:Why these endpoints are not used
Flex30% off
$0.16$0.1120$0.48$0.336$0.0048$0.003361.63s98 tok/s
99.96%
Ultrafast
$3.0000$12.000$0.060000.45s310 tok/s
100.00%
ProviderInput / Output /M
Input $0.051 / Output $0.567
181 tok/s100.00% uptime
Input $0.195 / Output $0.66
149 tok/s99.93% uptime
Input $0.19 / Output $0.65
168 tok/s100.00% uptime
Input $0.096 / Output $0.384
124 tok/s100.00% uptime
Input $0.13 / Output $0.65
139 tok/s96.56% uptime
Input $0.14 / Output $0.42
30% off
117 tok/s100.00% uptime
Input $0.12 / Output $0.50
107 tok/s100.00% uptime
Input $0.225 / Output $0.90
165 tok/s100.00% uptime
Input $0.30 / Output $1.20
204 tok/s99.76% uptime
Input $0.103 / Output $0.60
110 tok/s99.96% uptime
Input $0.21 / Output $0.63
Priority
+11 more label
120 tok/s99.96% uptime
Input $0.30 / Output $1.20
238 tok/s100.00% uptime
Input $0.29 / Output $1.20
174 tok/s100.00% uptime
Input $0.103 / Output $0.60
97 tok/s100.00% uptime
Input $0.30 / Output $1.20
185 tok/s99.41% uptime
Input $0.30 / Output $1.20
165 tok/s100.00% uptime
Input $0.07 / Output $1.20
154 tok/s100.00% uptime
Input $0.26 / Output $1.17
157 tok/s100.00% uptime
Input $0.30 / Output $1.20
174 tok/s100.00% uptime
Input $0.30 / Output $1.20
154 tok/s99.86% uptime
Input $0.45 / Output $1.80
196 tok/s100.00% uptime
Input $0.195 / Output $0.78
35% off
104 tok/s100.00% uptime
Input $0.147 / Output $0.588
51% off
79 tok/s100.00% uptime
Input $0.2125 / Output $0.75
93 tok/s99.84% uptime
Input $0.21 / Output $0.84
89 tok/s99.45% uptime
Input $0.45 / Output $1.80
Fast
193 tok/s100.00% uptime
Input $0.30 / Output $1.20
64 tok/s99.88% uptime
Input $0.30 / Output $1.20
48 tok/s99.96% uptime
Input $0.30 / Output $1.20
189 tok/s99.76% uptime
Input $0.12 / Output $0.64
20% off
80 tok/s99.06% uptime
Input $0.135 / Output $0.54
56 tok/s100.00% uptime
Input $0.18 / Output $0.72
40% off
50 tok/s99.96% uptime
Input $0.30 / Output $1.20
98 tok/s100.00% uptime
Input $0.21 / Output $0.84
110 tok/s99.93% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.112 / Output $0.336
Flex
+11 more label
98 tok/s99.96% uptime
Input $3.00 / Output $12.00
Ultrafast
310 tok/s100.00% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Input
$0.02722/M tokens
Output
$0.7043/M tokens
DeepSeek V4.1 Flash — Price history
Price history
No effective price data for this selection
$0.00387$0.58399.4%3.3%
$0.00972$0.97994.2%7.7%
$0.01341$0.42093.2%17.1%
$0.01356$0.39888.3%4.9%
$0.01419$0.78994.6%1.1%
$0.01436$0.50090.3%2.6%
$0.01551$0.64989.4%6.4%
$0.01777$0.59989.7%2.9%
$0.01860$0.84093.0%1.6%
$0.01905$0.59988.3%2.6%
$0.02062$0.65990.8%5.0%
$0.02140$0.56689.6%13.3%
$0.02141$0.89993.0%5.4%
Priority
$0.02728$0.63089.7%1.0%
$0.02784$0.75386.4%0.1%
$0.02881$1.20092.2%2.0%
$0.03009$1.16990.4%0.7%
$0.03154$0.64989.0%3.3%
$0.03261$1.20091.4%1.6%
$0.03294$1.19990.8%2.0%
$0.03543$1.20090.3%1.8%
$0.03913$1.19989.0%0.1%
$0.04910$0.83978.2%1.2%
$0.05281$0.63559.5%0.0%
$0.05621$1.19982.9%0.1%
$0.05661$0.53764.5%0.3%
$0.06225$1.19980.9%0.2%
$0.06284$1.79987.8%0.3%
$0.08530$1.19879.5%0.1%
$0.09445$1.19969.9%10.6%
$0.09545$0.74671.6%0.0%
Fast
$0.09792$1.80079.8%0.2%
$0.12576$1.19959.2%0.1%
$0.12833$1.20063.6%0.1%
Not used in Standard routing:Why these endpoints are not used
Flex
$0.00744$0.33696.2%0.6%
Ultrafast
$1.87113$12.00038.4%0.0%
ProviderInput / Output /M
Token share
Effective in $0.00387 / Effective out $0.583
Token share
3.3%
Effective in $0.00972 / Effective out $0.979
Token share
7.7%
Effective in $0.01341 / Effective out $0.420
Token share
17.1%
Effective in $0.01356 / Effective out $0.398
Token share
4.9%
Effective in $0.01419 / Effective out $0.789
Token share
1.1%
Effective in $0.01436 / Effective out $0.500
Token share
2.6%
Effective in $0.01551 / Effective out $0.649
Token share
6.4%
Effective in $0.01777 / Effective out $0.599
Token share
2.9%
Effective in $0.01860 / Effective out $0.840
Token share
1.6%
Effective in $0.01905 / Effective out $0.599
Token share
2.6%
Effective in $0.02062 / Effective out $0.659
Token share
5.0%
Effective in $0.02140 / Effective out $0.566
Token share
13.3%
Effective in $0.02141 / Effective out $0.899
Token share
5.4%
Effective in $0.02728 / Effective out $0.630
PriorityToken share
1.0%
Effective in $0.02784 / Effective out $0.753
Token share
0.1%
Effective in $0.02881 / Effective out $1.200
Token share
2.0%
Effective in $0.03009 / Effective out $1.169
Token share
0.7%
Effective in $0.03154 / Effective out $0.649
Token share
3.3%
Effective in $0.03261 / Effective out $1.200
Token share
1.6%
Effective in $0.03294 / Effective out $1.199
Token share
2.0%
Effective in $0.03543 / Effective out $1.200
Token share
1.8%
Effective in $0.03913 / Effective out $1.199
Token share
0.1%
Effective in $0.04910 / Effective out $0.839
Token share
1.2%
Effective in $0.05281 / Effective out $0.635
Token share
0.0%
Effective in $0.05621 / Effective out $1.199
Token share
0.1%
Effective in $0.05661 / Effective out $0.537
Token share
0.3%
Effective in $0.06225 / Effective out $1.199
Token share
0.2%
Effective in $0.06284 / Effective out $1.799
Token share
0.3%
Effective in $0.08530 / Effective out $1.198
Token share
0.1%
Effective in $0.09445 / Effective out $1.199
Token share
10.6%
Effective in $0.09545 / Effective out $0.746
Token share
0.0%
Effective in $0.09792 / Effective out $1.800
FastToken share
0.2%
Effective in $0.12576 / Effective out $1.199
Token share
0.1%
Effective in $0.12833 / Effective out $1.200
Token share
0.1%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.00744 / Effective out $0.336
FlexToken share
0.6%
Effective in $1.87113 / Effective out $12.000
UltrafastToken share
0.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
310tok/s
P50, best across providers
Latency
0.22s
P50, best provider
Reasoning effortLatency / throughput
AutoExacto benchmarks
GPQA DiamondTAU-BenchBaseten (US)89.7%--Cloudflare87.7%--DeepInfra91.2%75.9%StreamLake90.9%75.9%DigitalOcean90.6%76.2%Baseten90.1%73.7%Baseten89.4%71.4%
+32 more providers
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.85%
Availability over the last 3 days
Last 72 hours
Availability 99.85%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.93%
Without Routing
99.42%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
Benchmark score summary for DeepSeek: DeepSeek V4.1 Flash (Artificial Analysis and Vals AI)
SourceBenchmarkScore
Artificial AnalysisDeepSeek V4.1 Flash (Non-reasoning) HLE10.8%
Artificial AnalysisDeepSeek V4.1 Flash (Non-reasoning) AA-LCR55.3%
Artificial AnalysisDeepSeek V4.1 Flash (Non-reasoning) GDPval-AA42.4%
Artificial AnalysisDeepSeek V4.1 Flash (Non-reasoning) CritPt0.3%
Artificial AnalysisDeepSeek V4.1 Flash (Non-reasoning) SciCode35.5%
Artificial AnalysisDeepSeek V4.1 Flash (Non-reasoning) Terminal-Bench 4.05.6%
Vals AIDeepSeek V4.1 Flash Access to Justice Benchmark72.9%
Vals AIDeepSeek V4.1 Flash BioMysteryBench67.8%
Vals AIDeepSeek V4.1 Flash Code Migration v1.158.9%
Vals AIDeepSeek V4.1 Flash CyberBench v1.173.7%
Vals AIDeepSeek V4.1 Flash EMB v1.167.8%
Vals AIDeepSeek V4.1 Flash Finance Agent v2.165.4%
Vals AIDeepSeek V4.1 Flash Vals Finance Index57.1%
Vals AIDeepSeek V4.1 Flash Financial Coaching Bench72.8%
Vals AIDeepSeek V4.1 Flash Harvey's Legal Agent Benchmark v16.7%
Vals AIDeepSeek V4.1 Flash Immigration65.6%
Vals AIDeepSeek V4.1 Flash Vals Inference Provider Index66.6%
Vals AIDeepSeek V4.1 Flash IOI40.3%
Vals AIDeepSeek V4.1 Flash LegalBench83.3%
Vals AIDeepSeek V4.1 Flash Legal Research Bench41.3%
Vals AIDeepSeek V4.1 Flash MedCode41.2%
Vals AIDeepSeek V4.1 Flash MedScribe85.5%
Vals AIDeepSeek V4.1 Flash MysteryMechanism21.2%
Vals AIDeepSeek V4.1 Flash ProgramBench0.5%
Vals AIDeepSeek V4.1 Flash ProofBench v1.154.0%
Vals AIDeepSeek V4.1 Flash Public Benefits Bench v1.164.3%
Vals AIDeepSeek V4.1 Flash SAGE85.4%
Vals AIDeepSeek V4.1 Flash Vals Science Index29.6%
Vals AIDeepSeek V4.1 Flash SkillsBench69.8%
Vals AIDeepSeek V4.1 Flash SRE Bench0.8%
Vals AIDeepSeek V4.1 Flash SWE-bench Multimodal46.5%
Vals AIDeepSeek V4.1 Flash Tax Agent Bench26.6%
Vals AIDeepSeek V4.1 Flash Terminal-Bench 4.019.7%
Vals AIDeepSeek V4.1 Flash Terminal-Bench-Science0.0%
Vals AIDeepSeek V4.1 Flash Vals Index51.3%
Vals AIDeepSeek V4.1 Flash Vibe Code Bench 1-10016.4%
Vals AIDeepSeek V4.1 Flash Vibe Code Bench v1.184.7%
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
1.
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
9.19Ttokens
2.
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
3.87Ttokens
3.
pi
There are many coding agents, but this one is yours.
3.15Ttokens
4.
OpenHands
AI coding agent that can run commands, browse the web, call APIs
2.04Ttokens
5.
DeepSeek Harness
new
2.03Ttokens
Rest of OpenRouter
155B
Top 5 Apps
72.2B
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
DeepSeek: DeepSeek Flash versions
Not currently available through EU in-region routing. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with DeepSeek: DeepSeek V4.1 Flash on OpenRouter.
Self-Hosted LLM vs API: When Does Self-Hosting Pay OffBlog post
How to Benchmark LLMsBlog post
How to Stop an AI Agent Stuck in an Infinite LoopBlog post
LLM API Rate Limits: How to Fix OpenAI and Claude 429 ErrorsBlog post
How to Get Structured Output from Any LLM: JSON Schema, Tool Calls, or a Decision ModelBlog post
Best OCR Model for Scanned Documents, MeasuredBlog post
Build an AI Code Reviewer with OpenRouterBlog post
Open-Weight vs Closed-Weight Models: What's the Difference?Blog post
How to Extract Tables from a PDF with an LLMBlog post
Does DeepSeek V4 Have Vision?Blog post
Frequently asked questions
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.
The DeepSeek V4.1 Flash documentation on OpenRouter includes the Self-Hosted LLM vs API: When Does Self-Hosting Pay Off blog post, the How to Benchmark LLMs blog post, the How to Stop an AI Agent Stuck in an Infinite Loop blog post, the LLM API Rate Limits: How to Fix OpenAI and Claude 429 Errors blog post, the How to Get Structured Output from Any LLM: JSON Schema, Tool Calls, or a Decision Model blog post, the Best OCR Model for Scanned Documents, Measured blog post, the Build an AI Code Reviewer with OpenRouter blog post, the Open-Weight vs Closed-Weight Models: What's the Difference? blog post, the How to Extract Tables from a PDF with an LLM blog post, and the Does DeepSeek V4 Have Vision? blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.
DeepSeek V4.1 Flash costs $0.051/M input tokens and $0.567/M output tokens, with separate rates for Cache Read at $0.018/M tokens.
DeepSeek V4.1 Flash has a 1,048,576 token context window. It supports up to 1,048,576 completion tokens.
Yes. DeepSeek V4.1 Flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
DeepSeek V4.1 Flash accepts text and images as input and returns text.
DeepSeek V4.1 Flash is served by 27 providers on OpenRouter: Wafer, Open Inference, River, inference.net, DeepInfra, Relace, Reka AI, CoreWeave and 19 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
DeepSeek V4.1 Flash was released on September 10, 2026.
正文以来源语言显示。