deepseek/deepseek-v4.1-flash-1017

Model release OpenRouter 模型 Source language: Chinese

OpenRouter 于 2026-10-17 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:$0.0200/百万 tokens;输出价:$0.1080/百万 tokens;定位(来源描述):DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by…

Full text

DeepSeek: DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017

Model weights

Compare

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. 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

$0.02 / $0.108per 1M

Context

1.0M

Released

Oct 17, 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

65% off

$0.30$0.10500$1.20$0.4200$0.006$0.0021000.96s142 tok/s

100.00%

$0.15000$0.5000$0.0030000.70s154 tok/s

100.00%

$0.12000$0.5000$0.0030000.75s147 tok/s

99.95%

$0.21$0.10500$0.84$0.4200$0.0042$0.0021000.73s134 tok/s

98.75%

$0.18000$0.7200$0.0060000.69s186 tok/s

100.00%

$0.07000$0.8000$0.0060000.84s152 tok/s

100.00%

$0.07200$0.6410$0.0060000.50s129 tok/s

99.80%

68% off

$0.28$0.08876$1.13$0.3582$0.006$0.0019021.04s126 tok/s

99.85%

$0.04368$0.7000$0.0024000.98s110 tok/s

100.00%

$0.03600$0.5000$0.0100000.51s120 tok/s

100.00%

$0.08000$0.6050$0.0080000.20s124 tok/s

100.00%

$0.21000$0.6200$0.0105000.59s167 tok/s

99.13%

$0.06600$0.5000$0.0065000.60s119 tok/s

100.00%

$0.30000$1.2000$0.0060000.47s197 tok/s

99.56%

$0.10800$0.4320$0.0021600.91s107 tok/s

100.00%

Priority51% off

$0.30$0.14700$0.90$0.4410$0.009$0.0044100.96s112 tok/s

99.97%

$0.08000$0.6050$0.0080000.25s110 tok/s

99.97%

51% off

$0.20$0.09800$0.60$0.2940$0.006$0.0029400.83s95 tok/s

99.92%

$0.29000$1.2000$0.0070000.55s189 tok/s

100.00%

$0.18000$0.6800$0.0060000.93s120 tok/s

99.52%

$0.25000$1.0000$0.0050000.79s135 tok/s

100.00%

$0.15000$1.2000$0.0060000.93s140 tok/s

99.97%

$0.02000$0.1080$0.0070001.45s85 tok/s

99.90%

$0.10000$0.6000$0.0030002.07s92 tok/s

100.00%

$0.30000$1.2000$0.0060001.16s147 tok/s

100.00%

45% off

$0.30$0.16500$1.20$0.6600$0.006$0.0033001.60s93 tok/s

99.92%

40% off

$0.30$0.18000$1.20$0.7200$0.006$0.0036001.44s156 tok/s

99.82%

$0.30000$1.2000$0.0060000.49s136 tok/s

100.00%

$0.30000$1.2000$0.0070000.58s137 tok/s

100.00%

$0.16000$1.1000$0.0080000.60s137 tok/s

99.79%

$0.06000$0.5000$0.0100000.66s73 tok/s

99.90%

$0.45000$1.8000$0.0090000.59s185 tok/s

100.00%

63% off

$0.30$0.11100$1.20$0.4440$0.006$0.0022202.38s52 tok/s

100.00%

$0.07272$0.1080$0.0070001.59s143 tok/s

99.87%

$0.30000$1.2000$0.0075002.15s90 tok/s

100.00%

$0.30000$0.5500$0.0060000.56s76 tok/s

99.97%

$0.30000$1.2000$0.0060001.68s91 tok/s

100.00%

$0.30000$1.2000$0.0070001.08s133 tok/s

99.73%

$0.30000$1.2000$0.0060001.30s39 tok/s

100.00%

$0.15000$0.6000$0.0030001.12s124 tok/s

100.00%

$0.21000$0.8400$0.0042002.14s99 tok/s

97.79%

$0.19500$0.7800$0.0039002.30s73 tok/s

99.97%

$0.24000$0.9600$0.0048000.72s174 tok/s

98.75%

Fast

$0.60000$2.4000$0.0140000.30s496 tok/s

100.00%

$0.30000$1.2000$0.006000----

97.95%

Not used in Standard routing:Why these endpoints are not used

Flex

$0.03000$0.2500$0.0050000.60s90 tok/s

100.00%

Flex

$0.07750$0.2325$0.0023250.64s141 tok/s

100.00%

Flex51% off

$0.16$0.07840$0.48$0.2352$0.0048$0.0023522.33s102 tok/s

81.05%

ProviderInput / Output /M

Input $0.105 / Output $0.42

65% off

142 tok/s100.00% uptime

Input $0.15 / Output $0.50

154 tok/s100.00% uptime

Input $0.12 / Output $0.50

147 tok/s99.95% uptime

Input $0.105 / Output $0.42

134 tok/s98.75% uptime

Input $0.18 / Output $0.72

186 tok/s100.00% uptime

Input $0.07 / Output $0.80

152 tok/s100.00% uptime

Input $0.072 / Output $0.641

129 tok/s99.80% uptime

Input $0.08876 / Output $0.3582

68% off

126 tok/s99.85% uptime

Input $0.04368 / Output $0.70

110 tok/s100.00% uptime

Input $0.036 / Output $0.50

120 tok/s100.00% uptime

Input $0.08 / Output $0.605

124 tok/s100.00% uptime

Input $0.21 / Output $0.62

167 tok/s99.13% uptime

Input $0.066 / Output $0.50

119 tok/s100.00% uptime

Input $0.30 / Output $1.20

197 tok/s99.56% uptime

Input $0.108 / Output $0.432

107 tok/s100.00% uptime

Input $0.147 / Output $0.441

Priority

+11 more label

112 tok/s99.97% uptime

Input $0.08 / Output $0.605

110 tok/s99.97% uptime

Input $0.098 / Output $0.294

51% off

95 tok/s99.92% uptime

Input $0.29 / Output $1.20

189 tok/s100.00% uptime

Input $0.18 / Output $0.68

120 tok/s99.52% uptime

Input $0.25 / Output $1.00

135 tok/s100.00% uptime

Input $0.15 / Output $1.20

140 tok/s99.97% uptime

Input $0.02 / Output $0.108

85 tok/s99.90% uptime

Input $0.10 / Output $0.60

92 tok/s100.00% uptime

Input $0.30 / Output $1.20

147 tok/s100.00% uptime

Input $0.165 / Output $0.66

45% off

93 tok/s99.92% uptime

Input $0.18 / Output $0.72

40% off

156 tok/s99.82% uptime

Input $0.30 / Output $1.20

136 tok/s100.00% uptime

Input $0.30 / Output $1.20

137 tok/s100.00% uptime

Input $0.16 / Output $1.10

137 tok/s99.79% uptime

Input $0.06 / Output $0.50

73 tok/s99.90% uptime

Input $0.45 / Output $1.80

185 tok/s100.00% uptime

Input $0.111 / Output $0.444

63% off

52 tok/s100.00% uptime

Input $0.07272 / Output $0.108

143 tok/s99.87% uptime

Input $0.30 / Output $1.20

90 tok/s100.00% uptime

Input $0.30 / Output $0.55

76 tok/s99.97% uptime

Input $0.30 / Output $1.20

91 tok/s100.00% uptime

Input $0.30 / Output $1.20

133 tok/s99.73% uptime

Input $0.30 / Output $1.20

39 tok/s100.00% uptime

Input $0.15 / Output $0.60

124 tok/s100.00% uptime

Input $0.21 / Output $0.84

99 tok/s97.79% uptime

Input $0.195 / Output $0.78

73 tok/s99.97% uptime

Input $0.24 / Output $0.96

174 tok/s98.75% uptime

Input $0.60 / Output $2.40

Fast

496 tok/s100.00% uptime

Input $0.30 / Output $1.20

-- tok/s97.95% uptime

Not used in Standard routing:Why these endpoints are not used

Input $0.03 / Output $0.25

Flex

90 tok/s100.00% uptime

Input $0.0775 / Output $0.2325

Flex

141 tok/s100.00% uptime

Input $0.0784 / Output $0.2352

Flex

+11 more label

102 tok/s81.05% 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

$0.01198/M tokens

Output

$0.5801/M tokens

DeepSeek V4.1 Flash 1017 — Price history

Price history

No effective price data for this selection

$0.00414$0.69995.8%4.1%

$0.00688$0.60097.4%22.4%

$0.00778$0.41994.5%2.4%

$0.00788$0.59995.0%0.6%

$0.00816$0.80096.6%4.8%

$0.00818$0.33196.0%12.4%

$0.00872$0.44394.0%0.3%

$0.00971$0.50094.3%4.0%

$0.00982$0.52092.1%3.2%

$0.00998$0.10789.1%1.0%

$0.01043$0.50093.4%3.0%

Priority

$0.01082$0.44395.6%1.7%

$0.01083$0.44592.1%0.5%

$0.01140$0.10793.3%0.6%

$0.01177$0.50094.0%2.9%

$0.01188$0.50093.1%6.2%

$0.01201$0.62794.0%0.9%

$0.01301$0.77995.2%0.0%

$0.01400$0.36486.4%1.0%

$0.01433$0.60491.2%0.9%

$0.01477$0.60490.6%5.2%

$0.01562$0.71994.5%3.3%

$0.01608$0.66292.2%0.7%

$0.01872$0.67992.7%0.1%

$0.01934$1.20095.5%6.2%

$0.02063$1.09991.7%0.0%

$0.02077$1.00093.6%0.7%

$0.02219$1.20088.8%0.5%

$0.02270$1.20094.8%0.0%

$0.02321$0.72088.9%0.3%

$0.02458$0.50070.8%0.2%

$0.02597$0.95991.0%0.0%

$0.03083$0.61989.8%0.8%

$0.03154$0.84086.7%0.5%

$0.03217$1.20091.1%0.9%

$0.03357$1.20090.6%0.2%

$0.03452$1.19990.3%0.2%

$0.03745$1.20089.6%0.3%

$0.03798$1.20089.4%1.0%

$0.03820$1.79993.4%0.4%

$0.04509$1.19986.7%0.0%

Fast

$0.08928$2.39987.2%0.3%

$0.11017$0.55064.6%0.0%

$0.19888$1.20034.4%0.1%

$0.03579$1.19989.9%1.2%

Not used in Standard routing:Why these endpoints are not used

Flex

$0.00447$0.23597.2%1.3%

Flex

$0.00788$0.23292.6%0.4%

Flex

$0.00961$0.24981.4%2.2%

ProviderInput / Output /M

Token share

Effective in $0.00414 / Effective out $0.699

Token share

4.1%

Effective in $0.00688 / Effective out $0.600

Token share

22.4%

Effective in $0.00778 / Effective out $0.419

Token share

2.4%

Effective in $0.00788 / Effective out $0.599

Token share

0.6%

Effective in $0.00816 / Effective out $0.800

Token share

4.8%

Effective in $0.00818 / Effective out $0.331

Token share

12.4%

Effective in $0.00872 / Effective out $0.443

Token share

0.3%

Effective in $0.00971 / Effective out $0.500

Token share

4.0%

Effective in $0.00982 / Effective out $0.520

Token share

3.2%

Effective in $0.00998 / Effective out $0.107

Token share

1.0%

Effective in $0.01043 / Effective out $0.500

Token share

3.0%

Effective in $0.01082 / Effective out $0.443

PriorityToken share

1.7%

Effective in $0.01083 / Effective out $0.445

Token share

0.5%

Effective in $0.01140 / Effective out $0.107

Token share

0.6%

Effective in $0.01177 / Effective out $0.500

Token share

2.9%

Effective in $0.01188 / Effective out $0.500

Token share

6.2%

Effective in $0.01201 / Effective out $0.627

Token share

0.9%

Effective in $0.01301 / Effective out $0.779

Token share

0.0%

Effective in $0.01400 / Effective out $0.364

Token share

1.0%

Effective in $0.01433 / Effective out $0.604

Token share

0.9%

Effective in $0.01477 / Effective out $0.604

Token share

5.2%

Effective in $0.01562 / Effective out $0.719

Token share

3.3%

Effective in $0.01608 / Effective out $0.662

Token share

0.7%

Effective in $0.01872 / Effective out $0.679

Token share

0.1%

Effective in $0.01934 / Effective out $1.200

Token share

6.2%

Effective in $0.02063 / Effective out $1.099

Token share

0.0%

Effective in $0.02077 / Effective out $1.000

Token share

0.7%

Effective in $0.02219 / Effective out $1.200

Token share

0.5%

Effective in $0.02270 / Effective out $1.200

Token share

0.0%

Effective in $0.02321 / Effective out $0.720

Token share

0.3%

Effective in $0.02458 / Effective out $0.500

Token share

0.2%

Effective in $0.02597 / Effective out $0.959

Token share

0.0%

Effective in $0.03083 / Effective out $0.619

Token share

0.8%

Effective in $0.03154 / Effective out $0.840

Token share

0.5%

Effective in $0.03217 / Effective out $1.200

Token share

0.9%

Effective in $0.03357 / Effective out $1.200

Token share

0.2%

Effective in $0.03452 / Effective out $1.199

Token share

0.2%

Effective in $0.03745 / Effective out $1.200

Token share

0.3%

Effective in $0.03798 / Effective out $1.200

Token share

1.0%

Effective in $0.03820 / Effective out $1.799

Token share

0.4%

Effective in $0.04509 / Effective out $1.199

Token share

0.0%

Effective in $0.08928 / Effective out $2.399

FastToken share

0.3%

Effective in $0.11017 / Effective out $0.550

Token share

0.0%

Effective in $0.19888 / Effective out $1.200

Token share

0.1%

Effective in $0.03579 / Effective out $1.199

Token share

1.2%

Not used in Standard routing:Why these endpoints are not used

Effective in $0.00447 / Effective out $0.235

FlexToken share

1.3%

Effective in $0.00788 / Effective out $0.232

FlexToken share

0.4%

Effective in $0.00961 / Effective out $0.249

FlexToken share

2.2%

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

496tok/s

P50, best across providers

Latency

0.20s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchTenstorrent92.8%--PrimaLabs91.7%--Baseten (Fast)90.6%--AtlasCloud90.4%77.8%CoreWeave91.5%76.3%Baseten89.8%76.5%

+37 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.

99.90%

Availability over the last 3 days

Last 72 hours

Availability 99.90%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.94%

Without Routing

98.32%

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 1017 (Artificial Analysis, Design Arena and Vals AI)

SourceBenchmarkScore

Artificial AnalysisDeepSeek V4.1 Flash (Max) HLE39.2%

Artificial AnalysisDeepSeek V4.1 Flash (Max) AA-LCR84.0%

Artificial AnalysisDeepSeek V4.1 Flash (Max) GDPval-AA55.0%

Artificial AnalysisDeepSeek V4.1 Flash (Max) CritPt14.3%

Artificial AnalysisDeepSeek V4.1 Flash (Max) SciCode51.9%

Artificial AnalysisDeepSeek V4.1 Flash (Max) Terminal-Bench 4.026.8%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (High) Intelligence Index28.6

Artificial AnalysisDeepSeek V4.1 Flash 1017 (High) Terminal-Bench 4.028.8%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (High) AA-Omniscience Accuracy38.9%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (High) AA-Omniscience Non-Hallucination Rate38.8%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) Intelligence Index18.5

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) HLE11.5%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) AA-LCR57.3%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) CritPt0.3%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) SciCode38.5%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) Terminal-Bench 4.09.1%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) AA-Omniscience Accuracy21.9%

Artificial AnalysisDeepSeek V4.1 Flash 1017 (Non-reasoning) AA-Omniscience Non-Hallucination Rate74.7%

Design ArenaDeepSeek-V4.1-Flash (1017) Agents Arena Spreadsheet Elo1263

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena 3D Elo1344

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena Asciiart Elo1224

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena Code Categories Elo1286

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena Data Visualization Elo1264

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena Game Development Elo1252

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena SVG Elo1242

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena UI Component Elo1282

Design ArenaDeepSeek-V4.1-Flash (1017) Models Arena Website Elo1294

Vals AIDeepSeek V4.1 Flash 1017 Access to Justice Benchmark73.1%

Vals AIDeepSeek V4.1 Flash 1017 Code Migration v1.167.5%

Vals AIDeepSeek V4.1 Flash 1017 CyberOffense54.8%

Vals AIDeepSeek V4.1 Flash 1017 EMB v1.169.2%

Vals AIDeepSeek V4.1 Flash 1017 Finance Agent v2.162.9%

Vals AIDeepSeek V4.1 Flash 1017 Vals Finance Index60.9%

Vals AIDeepSeek V4.1 Flash 1017 HLAB-Vals-1.114.2%

Vals AIDeepSeek V4.1 Flash 1017 Vals Legal Index71.9%

Vals AIDeepSeek V4.1 Flash 1017 Legal Research Bench45.2%

Vals AIDeepSeek V4.1 Flash 1017 Tax Agent Bench44.4%

Vals AIDeepSeek V4.1 Flash 1017 Terminal-Bench 4.031.8%

Vals AIDeepSeek V4.1 Flash 1017 Vals Index61.3%

Vals AIDeepSeek V4.1 Flash 1017 Vibe Code Bench 1-100 v1.126.2%

Vals AIDeepSeek V4.1 Flash 1017 Vibe Code Bench v1.187.7%

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.

11.6Ttokens

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.

8.63Ttokens

3.

pi

There are many coding agents, but this one is yours.

7.28Ttokens

4.

Strix

Open-source AI hackers that find and validate vulnerabilities in your code, APIs, and infrastructure, and open fix PRs.

6.34Ttokens

5.

DeepSeek Harness

new

5.19Ttokens

Rest of OpenRouter

4.82T

Top 5 Apps

1.16T

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 1017 on OpenRouter.

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 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. 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.

The DeepSeek V4.1 Flash 1017 documentation on OpenRouter includes 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 1017 costs $0.02/M input tokens and $0.108/M output tokens, with separate rates for Cache Read at $0.007/M tokens.

DeepSeek V4.1 Flash 1017 has a 1,048,576 token context window. It supports up to 384,000 completion tokens.

Yes. DeepSeek V4.1 Flash 1017 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

DeepSeek V4.1 Flash 1017 accepts text and images as input and returns text.

DeepSeek V4.1 Flash 1017 is served by 38 providers on OpenRouter: Sail Research, Particle AI, Wafer, Prime Intellect, Open Inference, Morph, Ionstream, DeepInfra and 30 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 1017 was released on October 17, 2026.

Sources

← Back to the daily brief