DeepSeek model product
DeepSeek-V4.1
1 is a DeepSeek Flash model for reasoning and agentic coding.
Updated Sep 25, 2026. Default version: DeepSeek-V4.1-Flash
LLMBoard Score83.2DeepSeek-V4.1-Flash
Coverage60%19 benchmark families
Context window1MTokens
Official input price$0.15DeepSeek API
DeepSeek-V4.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
DeepSeek-V4.1 Benchmark Results
Benchmark scores for DeepSeek-V4.1-Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAutomationBench | Score54.80% | Rank01 | Participants21 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBabyVision | Score89.60% | Rank01 | Participants13 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score64.00% | Rank01 | Participants23 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score90.60% | Rank01 | Participants42 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 3.0 | Score30.00% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools) | Score63.90% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkChartography | Score78.90% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score74.20% | Rank02 | Participants38 | Percentile97.30% | EvidenceC | Evaluated |
| BenchmarkZEROBench | Score0.49 points | Rank02 | Participants13 | Percentile91.67% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score100.00% | Rank03 | Participants20 | Percentile89.47% | EvidenceC | Evaluated |
| BenchmarkCyberGym | Score88.10% | Rank03 | Participants20 | Percentile89.47% | EvidenceC | Evaluated |
| BenchmarkSEC-bench Pro | Score62.80% | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkExploitGym | Score15.30% | Rank05 | Participants8 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (no tools, text-only) | Score39.10% | Rank05 | Participants8 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkMathArena Apex | Score65.60% | Rank05 | Participants11 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkAA LCR v1.1 | Score84.00% | Rank06 | Participants193 | Percentile97.40% | EvidenceB | EvaluatedN/A |
| BenchmarkProgram Bench | Score20.30% | Rank09 | Participants11 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score31.20% | Rank11 | Participants19 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score31.80% | Rank12 | Participants21 | Percentile45.00% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score90.90% | Rank23 | Participants250 | Percentile91.16% | EvidenceC | Evaluated |
| BenchmarkAA SciCode Subtasks | Score51.85% | Rank25 | Participants89 | Percentile72.73% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score46.40% | Rank26 | Participants201 | Percentile87.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score14.29% | Rank27 | Participants200 | Percentile86.93% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score39.25% | Rank33 | Participants200 | Percentile83.92% | EvidenceB | EvaluatedN/A |
| BenchmarkHumanity's Last Exam | Score36.80% | Rank43 | Participants104 | Percentile59.22% | EvidenceC | Evaluated |
DeepSeek-V4.1 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
DeepSeek-V4.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.15 input, $0.60 output per 1M
- Official provider
- DeepSeek
- Lowest third-party
- From $0.13 input, $0.52 output per 1M via NanoGPT
- Tracked offerings
- 46
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNaN | Provider model IDdeepseek-v4-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAlibaba Token Plan (China) | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAlibaba Token Plan | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderSCNet Token Plan | Provider model IDDeepSeek-V4.1-Flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderKenari | Provider model IDdeepseek-v4-1-flash | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderNanoGPT | Provider model IDdeepseek/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.13 | Output / 1M$0.52 | Context1M | Updated |
| ProviderAMD | Provider model IDDeepSeek-V4.1-Flash | Regionglobal | Input / 1M$0.14 | Output / 1M$0.28 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDdeepseek/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1.1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1.1M | Updated |
| ProviderMerge Gateway | Provider model IDdeepseek/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderDeepSeek | Provider model IDdeepseek-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDdeepseek/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderOpenCode Go | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderOllama Cloud | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderClinePass | Provider model IDcline-pass/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| Provider302.AI | Provider model IDdeepseek-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderNeuralwatt | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.155 | Output / 1M$0.62 | Context1M | Updated |
| Providerabove.dev | Provider model IDdeepseek-v4-flash | Regionglobal | Input / 1M$0.165 | Output / 1M$0.66 | Context1M | Updated |
| ProviderDeep Infra | Provider model IDdeepseek-ai/DeepSeek-V4.1-Flash | Regionglobal | Input / 1M$0.20 | Output / 1M$0.60 | Context1M | Updated |
| ProviderCoreWeave | Provider model IDdeepseek-ai/DeepSeek-V4.1-Flash | Regionglobal | Input / 1M$0.20 | Output / 1M$0.65 | Context1M | Updated |
| ProviderOfox | Provider model IDdeepseek/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.21 | Output / 1M$0.84 | Context1M | Updated |
| ProviderFireworks AI | Provider model IDaccounts/fireworks/models/deepseek-v4p1-flash | Regionglobal | Input / 1M$0.22 | Output / 1M$0.66 | Context1M | Updated |
| ProviderMelious | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.2318 | Output / 1M$1.16 | Context1M | Updated |
| ProviderVancine | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.24 | Output / 1M$0.96 | Context1M | Updated |
| ProviderGreenPT | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.2556 | Output / 1M$1.28 | Context1M | Updated |
| ProviderCrossModel | Provider model IDdeepseek/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.27 | Output / 1M$1.08 | Context1M | Updated |
| ProviderAlibaba (China) | Provider model IDdeepseek-v4.1-flash | Regionglobal | Input / 1M$0.2975 | Output / 1M$1.19 | Context1M | Updated |
| ProviderHugging Face | Provider model IDdeepseek-ai/DeepSeek-V4.1-Flash | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDdeepseek/deepseek-v4.1-flash | Regionglobal | Input / 1M$0.30 | Output / 1M$1.2 | Context1M | Updated |
DeepSeek-V4.1 Runtime Performance
Provider-specific output speed and catalog latency for DeepSeek-V4.1-Flash. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
DeepSeek-V4.1 Specifications
Technical details for the model's default version.
- Version
- DeepSeek-V4.1-Flash
- Released
- Sep 10, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 763.2B
- Context window
- 1M
- Max output
- 393.2K
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
DeepSeek-V4.1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionDeepSeek-V4.1-Flash | Released | LLMBoard83.17 | Parameters763.2B | Context1M | Max output393.2K | Open weightsYes | LicenseMIT |
Models similar to DeepSeek-V4.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
DE
DeepSeek-V4-Pro
DeepSeek
DE
DeepSeek-V4-Flash
DeepSeek
DE
DeepSeek-V3.2
DeepSeek
DE
DeepSeek-R1
DeepSeek
DE
DeepSeek-V3.1
DeepSeek
DE
DeepSeek-V3
DeepSeek
What is DeepSeek-V4.1?
Key information about DeepSeek-V4.1 and its available data.
1 is a large language model from DeepSeek. It is a Flash model designed for reasoning and agentic coding.
Data as of 2026-09-24.
FAQ
Common questions about DeepSeek-V4.1.
When was DeepSeek-V4.1 released?
DeepSeek-V4.1's default version was released on Sep 10, 2026.
How much does DeepSeek-V4.1 cost?
DeepSeek-V4.1's official API price is $0.15 per million input tokens and $0.60 per million output tokens via DeepSeek. The lowest tracked third-party offer starts at $0.13 input and $0.52 output via NanoGPT.
Who created DeepSeek-V4.1?
DeepSeek-V4.1 was created by DeepSeek.
What is the context window for DeepSeek-V4.1?
The default version has a 1M token context window.
Is DeepSeek-V4.1 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer DeepSeek-V4.1?
46 provider offerings are linked to the default version.