
DeepSeek: DeepSeek V4.1 Flash 1017 (nitro)
deepseek/deepseek-v4.1-flash-1017:nitro
Model weightsDeepSeek 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.
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).
| Provider | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
Fast | $0.60000 | $2.4000 | $0.014000 | 0.34s | 479 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 0.45s | 191 tok/s | ||
| $0.18000 | $0.7200 | $0.006000 | 0.82s | 181 tok/s | ||
| $0.29000 | $1.2000 | $0.007000 | 0.65s | 181 tok/s | ||
40% off | $0.30$0.18000 | $1.20$0.7200 | $0.006$0.003600 | 0.96s | 179 tok/s | |
| $0.45000 | $1.8000 | $0.009000 | 0.37s | 179 tok/s | ||
| $0.06600 | $0.5000 | $0.006500 | 0.42s | 176 tok/s | ||
| $0.03600 | $0.5000 | $0.010000 | 0.37s | 176 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 1.61s | 174 tok/s | ||
| $0.21000 | $0.6200 | $0.010500 | 0.65s | 173 tok/s | ||
| $0.24000 | $0.9600 | $0.004800 | 0.97s | 169 tok/s | ||
| $0.25000 | $1.0000 | $0.005000 | 0.65s | 164 tok/s | ||
| $0.07272 | $0.1080 | $0.007000 | 2.26s | 162 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 1.06s | 156 tok/s | ||
65% off | $0.30$0.10500 | $1.20$0.4200 | $0.006$0.002100 | 1.31s | 151 tok/s | |
| $0.07000 | $0.8000 | $0.006000 | 0.81s | 148 tok/s | ||
| $0.12000 | $0.5000 | $0.003000 | 0.56s | 146 tok/s | ||
| $0.15000 | $1.2000 | $0.006000 | 0.65s | 145 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 0.60s | 144 tok/s | ||
| $0.21000 | $0.8400 | $0.004200 | 0.77s | 143 tok/s | ||
| $0.15000 | $0.5000 | $0.003000 | 0.81s | 139 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.51s | 128 tok/s | ||
| $0.15000 | $0.6000 | $0.003000 | 1.06s | 127 tok/s | ||
| $0.08640 | $0.3456 | $0.001728 | 0.78s | 122 tok/s | ||
| $0.18000 | $0.6800 | $0.006000 | 0.97s | 119 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.20s | 118 tok/s | ||
| $0.05700 | $0.5060 | $0.005000 | 0.61s | 116 tok/s | ||
| $0.30$0.14700 | $0.90$0.4410 | $0.009$0.004410 | 0.91s | 116 tok/s | ||
| $0.04368 | $0.7000 | $0.002400 | 1.01s | 114 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.51s | 109 tok/s | ||
| $0.02000 | $0.1080 | $0.007000 | 1.33s | 108 tok/s | ||
| $0.06000 | $0.5000 | $0.010000 | 0.70s | 107 tok/s | ||
| $0.20$0.09800 | $0.60$0.2940 | $0.006$0.002940 | 0.86s | 105 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.29s | 104 tok/s | ||
| $0.30000 | $1.2000 | $0.007500 | 1.23s | 103 tok/s | ||
45% off | $0.30$0.16500 | $1.20$0.6600 | $0.006$0.003300 | 1.67s | 97 tok/s | |
| $0.28000 | $1.1300 | $0.006000 | 1.59s | 94 tok/s | ||
| $0.16000 | $1.1000 | $0.008000 | 0.98s | 92 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 1.69s | 90 tok/s | ||
| $0.21000 | $0.8400 | $0.004200 | 2.89s | 86 tok/s | ||
| $0.30000 | $0.5500 | $0.006000 | 0.95s | 81 tok/s | ||
| $0.10000 | $0.6000 | $0.003000 | 2.32s | 80 tok/s | ||
| $0.19500 | $0.7800 | $0.003900 | 2.66s | 74 tok/s | ||
63% off | $0.30$0.11100 | $1.20$0.4440 | $0.006$0.002220 | 2.00s | 47 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 1.14s | 39 tok/s | ||
Not used in Nitro routing:Why these endpoints are not used | ||||||
Flex | $0.07750 | $0.2325 | $0.002325 | 0.63s | 164 tok/s | |
| $0.03000 | $0.2500 | $0.005000 | 0.48s | 116 tok/s | ||
| $0.16$0.07840 | $0.48$0.2352 | $0.0048$0.002352 | 2.23s | 90 tok/s | ||
- Input $0.60 / Output $2.40479 tok/s100.00% uptimeFast
- Input $0.30 / Output $1.20191 tok/s99.58% uptime
- Input $0.18 / Output $0.72181 tok/s100.00% uptime
- Input $0.29 / Output $1.20181 tok/s100.00% uptime
- Input $0.18 / Output $0.7240% off179 tok/s99.83% uptime
Input $0.45 / Output $1.80179 tok/s100.00% uptime- Input $0.066 / Output $0.50176 tok/s100.00% uptime
- Input $0.036 / Output $0.50176 tok/s100.00% uptime
Input $0.30 / Output $1.20174 tok/s99.74% uptime- Input $0.21 / Output $0.62173 tok/s99.18% uptime
Input $0.24 / Output $0.96169 tok/s98.81% uptime- Input $0.25 / Output $1.00164 tok/s100.00% uptime
- Input $0.07272 / Output $0.108162 tok/s99.83% uptime
Input $0.30 / Output $1.20156 tok/s100.00% uptime- Input $0.105 / Output $0.4265% off151 tok/s100.00% uptime
- Input $0.07 / Output $0.80148 tok/s100.00% uptime
- Input $0.12 / Output $0.50146 tok/s99.95% uptime
- Input $0.15 / Output $1.20145 tok/s99.97% uptime
- Input $0.30 / Output $1.20144 tok/s100.00% uptime
- Input $0.21 / Output $0.84143 tok/s98.81% uptime
Input $0.15 / Output $0.50139 tok/s100.00% uptime- Input $0.30 / Output $1.20128 tok/s100.00% uptime
Input $0.15 / Output $0.60127 tok/s100.00% uptime- Input $0.0864 / Output $0.3456122 tok/s100.00% uptime
- Input $0.18 / Output $0.68119 tok/s99.55% uptime
- Input $0.08 / Output $0.605118 tok/s100.00% uptime
- Input $0.057 / Output $0.506116 tok/s99.81% uptime
Input $0.147 / Output $0.441116 tok/s99.97% uptimePriority+11 more label- Input $0.04368 / Output $0.70114 tok/s100.00% uptime
- Input $0.30 / Output $1.20109 tok/s95.90% uptime
- Input $0.02 / Output $0.108108 tok/s99.90% uptime
- Input $0.06 / Output $0.50107 tok/s99.90% uptime
Input $0.098 / Output $0.29451% off105 tok/s99.93% uptime- Input $0.08 / Output $0.605104 tok/s99.97% uptime
- Input $0.30 / Output $1.20103 tok/s100.00% uptime
- Input $0.165 / Output $0.6645% off97 tok/s99.93% uptime
- Input $0.28 / Output $1.1394 tok/s99.85% uptime
- Input $0.16 / Output $1.1092 tok/s99.80% uptime
- Input $0.30 / Output $1.2090 tok/s100.00% uptime
Input $0.21 / Output $0.8486 tok/s97.59% uptime- Input $0.30 / Output $0.5581 tok/s99.97% uptime
- Input $0.10 / Output $0.6080 tok/s100.00% uptime
- Input $0.195 / Output $0.7874 tok/s99.97% uptime
- Input $0.111 / Output $0.44463% off47 tok/s100.00% uptime
Input $0.30 / Output $1.2039 tok/s100.00% uptime- Not used in Nitro routing:Why these endpoints are not used
- Input $0.0775 / Output $0.2325164 tok/s100.00% uptimeFlex
- Input $0.03 / Output $0.25116 tok/s100.00% uptimeFlex
Input $0.0784 / Output $0.235290 tok/s81.93% uptimeFlex+11 more label
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 1017 — Price history
| $0.00604 | $0.699 | 91.2% | 3.2% | ||
| $0.00720 | $0.420 | 95.0% | 0.7% | ||
| $0.00880 | $0.332 | 95.2% | 13.2% | ||
| $0.00914 | $0.800 | 95.1% | 4.0% | ||
| $0.00918 | $0.107 | 82.9% | 0.8% | ||
| $0.01016 | $0.599 | 95.1% | 22.7% | ||
| $0.01083 | $0.505 | 88.8% | 6.3% | ||
| $0.01110 | $0.500 | 93.1% | 4.0% | ||
| $0.01132 | $0.500 | 91.9% | 3.3% | ||
| $0.01133 | $0.345 | 88.6% | 0.7% | ||
| $0.01195 | $0.500 | 92.5% | 5.5% | ||
| $0.01221 | $0.661 | 94.5% | 1.1% | ||
| $0.01309 | $0.599 | 89.6% | 0.2% | ||
| $0.01319 | $0.778 | 95.1% | 0.0% | ||
| $0.01369 | $0.442 | 93.5% | 1.6% | ||
| $0.01392 | $0.500 | 92.6% | 2.4% | ||
| $0.01532 | $0.604 | 89.8% | 4.4% | ||
| $0.01764 | $0.549 | 96.0% | 0.2% | ||
| $0.01823 | $0.604 | 85.8% | 0.6% | ||
| $0.01969 | $0.442 | 83.9% | 0.2% | ||
| $0.01988 | $0.839 | 92.4% | 2.9% | ||
| $0.02078 | $1.099 | 91.6% | 0.0% | ||
| $0.02090 | $1.199 | 95.4% | 0.0% | ||
| $0.02204 | $0.500 | 75.8% | 0.2% | ||
| $0.02393 | $0.719 | 88.5% | 0.3% | ||
| $0.02487 | $0.719 | 89.1% | 3.2% | ||
| $0.02913 | $1.200 | 92.1% | 8.4% | ||
| $0.03239 | $0.679 | 84.8% | 0.2% | ||
| $0.04085 | $1.000 | 85.4% | 0.6% | ||
| $0.04523 | $1.200 | 86.7% | 0.4% | ||
| $0.04547 | $1.199 | 86.6% | 0.3% | ||
| $0.04733 | $1.200 | 86.2% | 0.3% | ||
| $0.04874 | $0.620 | 80.8% | 0.5% | ||
| $0.05198 | $1.200 | 68.1% | 0.3% | ||
| $0.05849 | $1.799 | 88.8% | 0.5% | ||
| $0.05981 | $0.108 | 19.5% | 0.0% | ||
| $0.06520 | $0.840 | 70.4% | 0.5% | ||
| $0.07964 | $1.200 | 74.9% | 0.0% | ||
| $0.09618 | $1.199 | 68.5% | 2.7% | ||
Fast | $0.09827 | $2.399 | 85.6% | 0.4% | |
| $0.11218 | $0.959 | 54.3% | 0.0% | ||
| $0.11468 | $1.129 | 60.3% | 0.0% | ||
| $0.20556 | $1.200 | 32.1% | 0.1% | ||
| $0.26191 | $1.200 | 13.0% | 0.1% | ||
| — | — | — | — | ||
Not used in Nitro routing:Why these endpoints are not used | |||||
| $0.00423 | $0.238 | 97.8% | 0.4% | ||
Flex | $0.00466 | $0.232 | 96.9% | 0.1% | |
| $0.01158 | $0.249 | 73.5% | 2.1% | ||
- Effective in $0.00604 / Effective out $0.699Token share3.2%
- Effective in $0.00720 / Effective out $0.420Token share0.7%
- Effective in $0.00880 / Effective out $0.332Token share13.2%
- Effective in $0.00914 / Effective out $0.800Token share4.0%
- Effective in $0.00918 / Effective out $0.107Token share0.8%
- Effective in $0.01016 / Effective out $0.599Token share22.7%
- Effective in $0.01083 / Effective out $0.505Token share6.3%
- Effective in $0.01110 / Effective out $0.500Token share4.0%
- Effective in $0.01132 / Effective out $0.500Token share3.3%
- Effective in $0.01133 / Effective out $0.345Token share0.7%
- Effective in $0.01195 / Effective out $0.500Token share5.5%
- Effective in $0.01221 / Effective out $0.661Token share1.1%
- Effective in $0.01309 / Effective out $0.599Token share0.2%
- Effective in $0.01319 / Effective out $0.778Token share0.0%
- Effective in $0.01369 / Effective out $0.442PriorityToken share1.6%
- Effective in $0.01392 / Effective out $0.500Token share2.4%
- Effective in $0.01532 / Effective out $0.604Token share4.4%
- Effective in $0.01764 / Effective out $0.549Token share0.2%
- Effective in $0.01823 / Effective out $0.604Token share0.6%
- Effective in $0.01969 / Effective out $0.442Token share0.2%
- Effective in $0.01988 / Effective out $0.839Token share2.9%
- Effective in $0.02078 / Effective out $1.099Token share0.0%
- Effective in $0.02090 / Effective out $1.199Token share0.0%
- Effective in $0.02204 / Effective out $0.500Token share0.2%
- Effective in $0.02393 / Effective out $0.719Token share0.3%
- Effective in $0.02487 / Effective out $0.719Token share3.2%
- Effective in $0.02913 / Effective out $1.200Token share8.4%
- Effective in $0.03239 / Effective out $0.679Token share0.2%
- Effective in $0.04085 / Effective out $1.000Token share0.6%
- Effective in $0.04523 / Effective out $1.200Token share0.4%
- Effective in $0.04547 / Effective out $1.199Token share0.3%
- Effective in $0.04733 / Effective out $1.200Token share0.3%
- Effective in $0.04874 / Effective out $0.620Token share0.5%
- Effective in $0.05198 / Effective out $1.200Token share0.3%
- Effective in $0.05849 / Effective out $1.799Token share0.5%
- Effective in $0.05981 / Effective out $0.108Token share0.0%
- Effective in $0.06520 / Effective out $0.840Token share0.5%
- Effective in $0.07964 / Effective out $1.200Token share0.0%
- Effective in $0.09618 / Effective out $1.199Token share2.7%
- Effective in $0.09827 / Effective out $2.399FastToken share0.4%
- Effective in $0.11218 / Effective out $0.959Token share0.0%
- Effective in $0.11468 / Effective out $1.129Token share0.0%
- Effective in $0.20556 / Effective out $1.200Token share0.1%
- Effective in $0.26191 / Effective out $1.200Token share0.1%
- Effective in — / Effective out —Token share —
- Not used in Nitro routing:Why these endpoints are not used
- Effective in $0.00423 / Effective out $0.238FlexToken share0.4%
- Effective in $0.00466 / Effective out $0.232FlexToken share0.1%
- Effective in $0.01158 / Effective out $0.249FlexToken share2.1%
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 1017 (High) Intelligence Index | 28.6 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Terminal-Bench 4.0 | 28.8% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) AA-Omniscience Accuracy | 38.9% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) AA-Omniscience Non-Hallucination Rate | 38.8% |
| 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) SciCode | 51.9% |
| Artificial Analysis | DeepSeek V4.1 Flash (Max) Terminal-Bench 4.0 | 26.8% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Intelligence Index | 18.5 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) HLE | 11.5% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) AA-LCR | 57.3% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) CritPt | 0.3% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) SciCode | 38.5% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Terminal-Bench 4.0 | 9.1% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) AA-Omniscience Accuracy | 21.9% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) AA-Omniscience Non-Hallucination Rate | 74.7% |
| Design Arena | DeepSeek-V4.1-Flash (1017) Agents Arena Spreadsheet Elo | 1263 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena 3D Elo | 1343 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Asciiart Elo | 1223 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Code Categories Elo | 1287 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Data Visualization Elo | 1273 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Game Development Elo | 1251 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena SVG Elo | 1241 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena UI Component Elo | 1283 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Website Elo | 1295 |
| Vals AI | DeepSeek V4.1 Flash 1017 Access to Justice Benchmark | 73.1% |
| Vals AI | DeepSeek V4.1 Flash 1017 Code Migration v1.1 | 67.5% |
| Vals AI | DeepSeek V4.1 Flash 1017 CyberOffense | 54.8% |
| Vals AI | DeepSeek V4.1 Flash 1017 EMB v1.1 | 69.2% |
| Vals AI | DeepSeek V4.1 Flash 1017 Finance Agent v2.1 | 62.9% |
| Vals AI | DeepSeek V4.1 Flash 1017 Vals Finance Index | 60.9% |
| Vals AI | DeepSeek V4.1 Flash 1017 HLAB-Vals-1.1 | 14.2% |
| Vals AI | DeepSeek V4.1 Flash 1017 Vals Legal Index | 71.9% |
| Vals AI | DeepSeek V4.1 Flash 1017 Legal Research Bench | 45.2% |
| Vals AI | DeepSeek V4.1 Flash 1017 Tax Agent Bench | 44.4% |
| Vals AI | DeepSeek V4.1 Flash 1017 Terminal-Bench 4.0 | 31.8% |
| Vals AI | DeepSeek V4.1 Flash 1017 Vals Index | 61.3% |
| Vals AI | DeepSeek V4.1 Flash 1017 Vibe Code Bench 1-100 v1.1 | 26.2% |
| Vals AI | DeepSeek V4.1 Flash 1017 Vibe Code Bench v1.1 | 87.7% |
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 1017 (nitro) on OpenRouter.
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, Morph, Open Inference, 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.