
DeepSeek: DeepSeek V4.1 Flash
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 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.
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).
| $0.1950 | $0.660 | $0.00300 | 0.50s | 186 tok/s | ||
| $0.1200 | $0.500 | $0.00300 | 0.70s | 129 tok/s | ||
| $0.1030 | $0.600 | $0.00800 | 0.25s | 160 tok/s | ||
| $0.1300 | $0.650 | $0.00200 | 0.83s | 136 tok/s | ||
| $0.1900 | $0.650 | $0.01200 | 0.19s | 158 tok/s | ||
| $0.2250 | $0.900 | $0.00600 | 0.67s | 180 tok/s | ||
| $0.1030 | $0.600 | $0.00800 | 0.21s | 132 tok/s | ||
| $0.0510 | $0.567 | $0.01800 | 0.32s | 137 tok/s | ||
| $0.1200 | $0.480 | $0.00240 | 1.04s | 117 tok/s | ||
| $0.20$0.1400 | $0.60$0.420 | $0.006$0.00420 | 0.65s | 105 tok/s | ||
| $0.1800 | $0.720 | $0.00360 | 0.93s | 129 tok/s | ||
60% off | $0.30$0.1200 | $1.20$0.480 | $0.006$0.00240 | 1.08s | 103 tok/s | |
| $0.3000 | $1.200 | $0.00600 | 0.45s | 204 tok/s | ||
| $0.3000 | $1.200 | $0.00700 | 0.59s | 186 tok/s | ||
| $0.3000 | $1.200 | $0.00600 | 0.22s | 264 tok/s | ||
| $0.2100 | $0.840 | $0.00420 | 0.65s | 123 tok/s | ||
| $0.2900 | $1.200 | $0.00700 | 0.57s | 178 tok/s | ||
| $0.0500 | $0.900 | $0.00200 | 0.61s | 154 tok/s | ||
| $0.30$0.2100 | $0.90$0.630 | $0.009$0.00630 | 0.81s | 101 tok/s | ||
51% off | $0.30$0.1470 | $1.20$0.588 | $0.006$0.00294 | 1.43s | 100 tok/s | |
| $0.3000 | $1.200 | $0.00750 | 0.64s | 163 tok/s | ||
| $0.2600 | $1.170 | $0.00580 | 0.52s | 161 tok/s | ||
| $0.3000 | $1.200 | $0.00600 | 0.43s | 150 tok/s | ||
| $0.2125 | $0.750 | $0.05000 | 0.76s | 99 tok/s | ||
| $0.4500 | $1.800 | $0.00900 | 0.35s | 166 tok/s | ||
| $0.1350 | $0.540 | $0.01350 | 0.69s | 62 tok/s | ||
Fast | $0.4500 | $1.800 | $0.00900 | 0.36s | 179 tok/s | |
20% off | $0.15$0.1200 | $0.80$0.640 | $0.01$0.00800 | 1.80s | 57 tok/s | |
| $0.3000 | $1.200 | $0.00600 | 1.59s | 104 tok/s | ||
| $0.3000 | $1.200 | $0.03000 | 0.83s | 67 tok/s | ||
| $0.2000 | $0.700 | $0.02000 | 0.38s | 200 tok/s | ||
| $0.3000 | $1.200 | $0.01000 | 0.47s | 243 tok/s | ||
| $0.3000 | $1.200 | $0.00700 | 0.49s | 164 tok/s | ||
40% off | $0.30$0.1800 | $1.20$0.720 | $0.006$0.00360 | 1.68s | 74 tok/s | |
| $0.1000 | $0.900 | $0.03000 | 1.60s | 93 tok/s | ||
| $0.3000 | $1.200 | $0.00600 | 1.60s | 47 tok/s | ||
| $0.3000 | $1.200 | $0.03000 | 0.60s | 98 tok/s | ||
Not used in Standard routing:Why these endpoints are not used | ||||||
| $0.16$0.1120 | $0.48$0.336 | $0.0048$0.00336 | 2.16s | 106 tok/s | ||
Ultrafast | $3.0000 | $12.000 | $0.06000 | 0.36s | 248 tok/s | |
Input $0.195 / Output $0.66186 tok/s100.00% uptime- Input $0.12 / Output $0.50129 tok/s100.00% uptime
- Input $0.103 / Output $0.60160 tok/s100.00% uptime
- Input $0.13 / Output $0.65136 tok/s100.00% uptime
- Input $0.19 / Output $0.65158 tok/s100.00% uptime
- Input $0.225 / Output $0.90180 tok/s100.00% uptime
- Input $0.103 / Output $0.60132 tok/s100.00% uptime
- Input $0.051 / Output $0.567137 tok/s100.00% uptime
- Input $0.12 / Output $0.48117 tok/s99.97% uptime
Input $0.14 / Output $0.4230% off105 tok/s100.00% uptime- Input $0.18 / Output $0.72129 tok/s100.00% uptime
- Input $0.12 / Output $0.4860% off103 tok/s100.00% uptime
- Input $0.30 / Output $1.20204 tok/s100.00% uptime
- Input $0.30 / Output $1.20186 tok/s100.00% uptime
- Input $0.30 / Output $1.20264 tok/s99.97% uptime
Input $0.21 / Output $0.84123 tok/s98.75% uptime- Input $0.29 / Output $1.20178 tok/s99.94% uptime
- Input $0.05 / Output $0.90154 tok/s99.85% uptime
Input $0.21 / Output $0.63101 tok/s99.94% uptimePriority+11 more label- Input $0.147 / Output $0.58851% off100 tok/s99.85% uptime
- Input $0.30 / Output $1.20163 tok/s100.00% uptime
- Input $0.26 / Output $1.17161 tok/s100.00% uptime
Input $0.30 / Output $1.20150 tok/s99.97% uptime- Input $0.2125 / Output $0.7599 tok/s99.71% uptime
Input $0.45 / Output $1.80166 tok/s99.77% uptime- Input $0.135 / Output $0.5462 tok/s100.00% uptime
- Input $0.45 / Output $1.80179 tok/s100.00% uptimeFast
- Input $0.12 / Output $0.6420% off57 tok/s99.73% uptime
- Input $0.30 / Output $1.20104 tok/s99.77% uptime
- Input $0.30 / Output $1.2067 tok/s96.42% uptime
- Input $0.20 / Output $0.70200 tok/s100.00% uptime
- Input $0.30 / Output $1.20243 tok/s100.00% uptime
- Input $0.30 / Output $1.20164 tok/s100.00% uptime
- Input $0.18 / Output $0.7240% off74 tok/s99.97% uptime
- Input $0.10 / Output $0.9093 tok/s99.44% uptime
- Input $0.30 / Output $1.2047 tok/s99.39% uptime
- Input $0.30 / Output $1.2098 tok/s100.00% uptime
- Not used in Standard routing:Why these endpoints are not used
Input $0.112 / Output $0.336106 tok/s77.97% uptimeFlex+11 more label- Input $3.00 / Output $12.00248 tok/s100.00% uptimeUltrafast
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
DeepSeek V4.1 Flash — Price history
| $0.00494 | $0.586 | 98.6% | 3.2% | ||
| $0.00707 | $0.987 | 92.9% | 10.0% | ||
| $0.01371 | $0.500 | 90.8% | 3.2% | ||
| $0.01423 | $0.480 | 89.9% | 4.2% | ||
| $0.01524 | $0.422 | 91.9% | 12.7% | ||
| $0.01570 | $0.600 | 91.9% | 6.5% | ||
| $0.01590 | $0.720 | 93.0% | 1.7% | ||
| $0.01591 | $0.600 | 91.7% | 6.2% | ||
| $0.01900 | $0.660 | 91.7% | 7.0% | ||
| $0.01946 | $0.650 | 86.4% | 6.9% | ||
| $0.02169 | $0.567 | 88.8% | 8.3% | ||
| $0.02241 | $0.519 | 84.3% | 0.7% | ||
| $0.02282 | $0.900 | 92.3% | 4.1% | ||
| $0.02601 | $0.840 | 89.4% | 2.2% | ||
| $0.02630 | $1.200 | 93.4% | 0.2% | ||
| $0.02899 | $0.638 | 81.1% | 0.1% | ||
| $0.03090 | $1.200 | 91.6% | 2.4% | ||
| $0.03188 | $0.649 | 88.8% | 2.7% | ||
| $0.03297 | $0.630 | 86.9% | 0.5% | ||
| $0.03422 | $1.200 | 90.7% | 1.1% | ||
| $0.03554 | $1.170 | 88.3% | 0.6% | ||
| $0.03594 | $1.200 | 89.8% | 2.3% | ||
| $0.04153 | $0.899 | 83.5% | 0.1% | ||
| $0.04776 | $0.724 | 75.3% | 0.0% | ||
| $0.05086 | $1.199 | 92.3% | 0.0% | ||
| $0.05398 | $0.537 | 66.6% | 0.2% | ||
| $0.05736 | $1.200 | 83.0% | 0.4% | ||
| $0.06403 | $1.200 | 80.3% | 0.1% | ||
| $0.06476 | $1.200 | 81.1% | 0.1% | ||
| $0.06988 | $1.799 | 86.2% | 0.2% | ||
| $0.07592 | $0.700 | 68.9% | 0.1% | ||
| $0.08373 | $1.200 | 73.6% | 0.1% | ||
| $0.09034 | $1.200 | 71.3% | 10.9% | ||
| $0.09146 | $0.748 | 74.3% | 0.0% | ||
Fast | $0.10296 | $1.799 | 78.7% | 0.2% | |
| $0.17936 | $1.200 | 41.0% | 0.1% | ||
| $0.19875 | $1.200 | 37.5% | 0.1% | ||
Not used in Standard routing:Why these endpoints are not used | |||||
| $0.01678 | $0.336 | 87.6% | 0.4% | ||
Ultrafast | $1.72925 | $12.000 | 43.2% | 0.0% | |
- Effective in $0.00494 / Effective out $0.586Token share3.2%
- Effective in $0.00707 / Effective out $0.987Token share10.0%
- Effective in $0.01371 / Effective out $0.500Token share3.2%
- Effective in $0.01423 / Effective out $0.480Token share4.2%
- Effective in $0.01524 / Effective out $0.422Token share12.7%
- Effective in $0.01570 / Effective out $0.600Token share6.5%
- Effective in $0.01590 / Effective out $0.720Token share1.7%
- Effective in $0.01591 / Effective out $0.600Token share6.2%
- Effective in $0.01900 / Effective out $0.660Token share7.0%
- Effective in $0.01946 / Effective out $0.650Token share6.9%
- Effective in $0.02169 / Effective out $0.567Token share8.3%
- Effective in $0.02241 / Effective out $0.519Token share0.7%
- Effective in $0.02282 / Effective out $0.900Token share4.1%
- Effective in $0.02601 / Effective out $0.840Token share2.2%
- Effective in $0.02630 / Effective out $1.200Token share0.2%
- Effective in $0.02899 / Effective out $0.638Token share0.1%
- Effective in $0.03090 / Effective out $1.200Token share2.4%
- Effective in $0.03188 / Effective out $0.649Token share2.7%
- Effective in $0.03297 / Effective out $0.630PriorityToken share0.5%
- Effective in $0.03422 / Effective out $1.200Token share1.1%
- Effective in $0.03554 / Effective out $1.170Token share0.6%
- Effective in $0.03594 / Effective out $1.200Token share2.3%
- Effective in $0.04153 / Effective out $0.899Token share0.1%
- Effective in $0.04776 / Effective out $0.724Token share0.0%
- Effective in $0.05086 / Effective out $1.199Token share0.0%
- Effective in $0.05398 / Effective out $0.537Token share0.2%
- Effective in $0.05736 / Effective out $1.200Token share0.4%
- Effective in $0.06403 / Effective out $1.200Token share0.1%
- Effective in $0.06476 / Effective out $1.200Token share0.1%
- Effective in $0.06988 / Effective out $1.799Token share0.2%
- Effective in $0.07592 / Effective out $0.700Token share0.1%
- Effective in $0.08373 / Effective out $1.200Token share0.1%
- Effective in $0.09034 / Effective out $1.200Token share10.9%
- Effective in $0.09146 / Effective out $0.748Token share0.0%
- Effective in $0.10296 / Effective out $1.799FastToken share0.2%
- Effective in $0.17936 / Effective out $1.200Token share0.1%
- Effective in $0.19875 / Effective out $1.200Token share0.1%
- Not used in Standard routing:Why these endpoints are not used
- Effective in $0.01678 / Effective out $0.336FlexToken share0.4%
- Effective in $1.72925 / Effective out $12.000UltrafastToken share0.0%
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).
P50, best across providers
P50, best provider
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.
Availability over the last 3 days
Last 72 hoursAvailability over the last 24 hours
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.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | DeepSeek V4.1 Flash (Max) Cyber Index | 40.8 |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) Openness Index | 44.4 |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) AutomationBench-AA | 68.9% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) GDP.pdf | 12.8% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) AA-AnalystAgent | 35.0% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) ITBench-AA | 46.9% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) Harvey LAB-AA | 1.7% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) HLE | 39.2% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) AA-LCR | 84.0% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) GDPval-AA | 55.0% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) CritPt | 14.3% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) HLE-Diamond | 19.1% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) SciCode | 51.9% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) Terminal-Bench 4.0 | 26.8% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) FrontierCode 1.1 | 44.0% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) Terminal-Bench-Science | 9.0% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) CWE-Bench-AA | 68.3% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) DeepsecBench-AA | 31.2% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) CyberGym-E2E-AA | 22.9% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) MLCR-AA | 23.9% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) HealthBench | 60.9% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) HealthBench Professional | 50.7% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) MMMU-Pro | 77.0% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) Openness Index | 44.4 |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) AutomationBench-AA | 47.8% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) GDP.pdf | 3.8% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) HLE | 10.8% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) AA-LCR | 55.3% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) GDPval-AA | 42.4% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) CritPt | 0.3% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) HLE-Diamond | 6.3% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) SciCode | 35.5% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) Terminal-Bench 4.0 | 5.6% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) FrontierCode 1.1 | 40.8% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) Terminal-Bench-Science | 0.0% |
| Artificial Analysis | DeepSeek V4.1 Flash (Non-reasoning) MMMU-Pro | 65.6% |
| Vals AI | DeepSeek V4.1 Flash Access to Justice Benchmark | 72.9% |
| Vals AI | DeepSeek V4.1 Flash BioMysteryBench | 67.8% |
| Vals AI | DeepSeek V4.1 Flash Code Migration v1.1 | 58.9% |
| Vals AI | DeepSeek V4.1 Flash CyberBench v1.1 | 73.7% |
| Vals AI | DeepSeek V4.1 Flash EMB v1.1 | 67.8% |
| Vals AI | DeepSeek V4.1 Flash Finance Agent v2.1 | 65.4% |
| Vals AI | DeepSeek V4.1 Flash Vals Finance Index | 57.1% |
| Vals AI | DeepSeek V4.1 Flash Financial Coaching Bench | 72.8% |
| Vals AI | DeepSeek V4.1 Flash Harvey's Legal Agent Benchmark v1 | 6.7% |
| Vals AI | DeepSeek V4.1 Flash Immigration | 65.6% |
| Vals AI | DeepSeek V4.1 Flash Vals Inference Provider Index | 66.6% |
| Vals AI | DeepSeek V4.1 Flash IOI | 40.3% |
| Vals AI | DeepSeek V4.1 Flash LegalBench | 83.3% |
| Vals AI | DeepSeek V4.1 Flash Legal Research Bench | 41.3% |
| Vals AI | DeepSeek V4.1 Flash MedCode | 41.2% |
| Vals AI | DeepSeek V4.1 Flash MedScribe | 85.5% |
| Vals AI | DeepSeek V4.1 Flash MysteryMechanism | 21.2% |
| Vals AI | DeepSeek V4.1 Flash ProgramBench | 0.5% |
| Vals AI | DeepSeek V4.1 Flash ProofBench v1.1 | 54.0% |
| Vals AI | DeepSeek V4.1 Flash Public Benefits Bench v1.1 | 64.3% |
| Vals AI | DeepSeek V4.1 Flash SAGE | 85.4% |
| Vals AI | DeepSeek V4.1 Flash Vals Science Index | 29.6% |
| Vals AI | DeepSeek V4.1 Flash SkillsBench | 69.8% |
| Vals AI | DeepSeek V4.1 Flash SRE Bench | 0.8% |
| Vals AI | DeepSeek V4.1 Flash SWE-bench Multimodal | 46.5% |
| Vals AI | DeepSeek V4.1 Flash Tax Agent Bench | 26.6% |
| Vals AI | DeepSeek V4.1 Flash Terminal-Bench 4.0 | 19.7% |
| Vals AI | DeepSeek V4.1 Flash Terminal-Bench-Science | 0.0% |
| Vals AI | DeepSeek V4.1 Flash Vals Index | 51.3% |
| Vals AI | DeepSeek V4.1 Flash Vibe Code Bench 1-100 | 16.4% |
| Vals AI | DeepSeek V4.1 Flash Vibe Code Bench v1.1 | 84.7% |
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.
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 $0.05/M input tokens and $0.90/M output tokens, with separate rates for Cache Read at $0.002/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 30 providers on OpenRouter: Open Inference, Wafer, Cloudflare, inference.net, DeepInfra, River, NovitaAI, Relace and 22 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.