
DeepSeek: DeepSeek V4.1 Flash 1017 (nitro)
deepseek/deepseek-v4.1-flash-1017:nitro
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.
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 | 462 tok/s | |
40% off | $0.30$0.18000 | $1.20$0.7200 | $0.006$0.003600 | 0.61s | 242 tok/s | |
| $0.60000 | $2.4000 | $0.014000 | 0.36s | 242 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.27s | 215 tok/s | ||
| $0.08000 | $0.6350 | $0.008000 | 0.17s | 192 tok/s | ||
20% off | $0.30$0.24000 | $1.20$0.9600 | $0.007$0.005600 | 1.10s | 188 tok/s | |
| $0.29000 | $1.2000 | $0.007000 | 0.69s | 186 tok/s | ||
40% off | $0.30$0.18000 | $1.20$0.7200 | $0.006$0.003600 | 0.80s | 181 tok/s | |
| $0.21000 | $0.6200 | $0.010500 | 0.55s | 177 tok/s | ||
| $0.05000 | $0.3000 | $0.003000 | 0.86s | 176 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.48s | 170 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.86s | 167 tok/s | ||
| $0.12000 | $0.5000 | $0.003000 | 0.72s | 165 tok/s | ||
| $0.08000 | $0.6350 | $0.008000 | 0.15s | 164 tok/s | ||
| $0.09000 | $1.2000 | $0.005000 | 0.73s | 163 tok/s | ||
| $0.06600 | $0.5000 | $0.006500 | 0.34s | 162 tok/s | ||
| $0.18000 | $0.7200 | $0.003600 | 0.69s | 161 tok/s | ||
| $0.25000 | $1.0000 | $0.005000 | 0.62s | 159 tok/s | ||
| $0.03600 | $0.5000 | $0.010000 | 0.36s | 156 tok/s | ||
| $0.17000 | $0.6700 | $0.006000 | 0.75s | 155 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.44s | 153 tok/s | ||
| $0.15000 | $0.5000 | $0.003000 | 0.92s | 150 tok/s | ||
| $0.06000 | $0.5000 | $0.020000 | 0.45s | 150 tok/s | ||
| $0.15000 | $0.6000 | $0.003000 | 0.84s | 141 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.99s | 135 tok/s | ||
| $0.18$0.09000 | $0.72$0.3600 | $0.0036$0.001800 | 0.88s | 130 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 0.65s | 130 tok/s | ||
65% off | $0.30$0.10500 | $1.20$0.4200 | $0.006$0.002100 | 1.01s | 125 tok/s | |
| $0.45000 | $1.8000 | $0.009000 | 0.95s | 125 tok/s | ||
| $0.04368 | $0.7000 | $0.002400 | 0.58s | 122 tok/s | ||
65% off | $0.28$0.09772 | $1.13$0.3944 | $0.006$0.002094 | 1.04s | 120 tok/s | |
| $0.30000 | $1.2000 | $0.007500 | 1.40s | 113 tok/s | ||
| $0.15000 | $0.6000 | $0.003000 | 1.10s | 113 tok/s | ||
| $0.24000 | $0.9600 | $0.004800 | 1.73s | 110 tok/s | ||
| $0.12000 | $0.4800 | $0.002400 | 0.81s | 105 tok/s | ||
60% off | $0.30$0.12000 | $1.20$0.4800 | $0.006$0.002400 | 1.31s | 105 tok/s | |
| $0.05900 | $0.5200 | $0.005000 | 0.74s | 95 tok/s | ||
| $0.12000 | $0.4000 | $0.006000 | 0.62s | 84 tok/s | ||
| $0.18000 | $0.6800 | $0.006000 | 1.74s | 75 tok/s | ||
| $0.19500 | $0.7800 | $0.003900 | 2.62s | 74 tok/s | ||
| $0.30$0.14700 | $0.90$0.4410 | $0.009$0.004410 | 1.02s | 66 tok/s | ||
60% off | $0.30$0.12000 | $1.20$0.4800 | $0.006$0.002400 | 2.15s | 64 tok/s | |
| $0.20$0.09800 | $0.60$0.2940 | $0.006$0.002940 | 0.92s | 61 tok/s | ||
63% off | $0.30$0.11100 | $1.20$0.4440 | $0.006$0.002220 | 1.51s | 53 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 0.87s | 38 tok/s | ||
| $0.10000 | $0.6000 | $0.003000 | 11.03s | 37 tok/s | ||
| $0.03500 | $0.1500 | $0.001500 | 3.34s | 22 tok/s | ||
| $0.21000 | $0.8400 | $0.004200 | -- | -- | ||
Not used in Nitro routing:Why these endpoints are not used | ||||||
| $0.03000 | $0.2500 | $0.010000 | 0.61s | 158 tok/s | ||
| $0.16$0.07840 | $0.48$0.2352 | $0.0048$0.002352 | 2.91s | 59 tok/s | ||
- Input $0.60 / Output $2.40462 tok/s100.00% uptimeFast
- Input $0.18 / Output $0.7240% off242 tok/s100.00% uptime
- Input $0.60 / Output $2.40242 tok/s99.62% uptimeFast
- Input $0.30 / Output $1.20215 tok/s99.97% uptime
- Input $0.08 / Output $0.635192 tok/s100.00% uptime
Input $0.24 / Output $0.9620% off188 tok/s99.95% uptime- Input $0.29 / Output $1.20186 tok/s100.00% uptime
- Input $0.18 / Output $0.7240% off181 tok/s99.85% uptime
- Input $0.21 / Output $0.62177 tok/s99.59% uptime
- Input $0.05 / Output $0.30176 tok/s100.00% uptime
- Input $0.30 / Output $1.20170 tok/s100.00% uptime
- Input $0.30 / Output $1.20167 tok/s99.32% uptime
- Input $0.12 / Output $0.50165 tok/s100.00% uptime
- Input $0.08 / Output $0.635164 tok/s100.00% uptime
- Input $0.09 / Output $1.20163 tok/s99.69% uptime
- Input $0.066 / Output $0.50162 tok/s100.00% uptime
- Input $0.18 / Output $0.72161 tok/s100.00% uptime
- Input $0.25 / Output $1.00159 tok/s100.00% uptime
- Input $0.036 / Output $0.50156 tok/s100.00% uptime

Input $0.17 / Output $0.67155 tok/s100.00% uptime- Input $0.30 / Output $1.20153 tok/s99.95% uptime
Input $0.15 / Output $0.50150 tok/s99.92% uptime- Input $0.06 / Output $0.50150 tok/s99.57% uptime
- Input $0.15 / Output $0.60141 tok/s99.50% uptime
Input $0.30 / Output $1.20135 tok/s99.95% uptime- Input $0.09 / Output $0.36130 tok/s99.85% uptime
- Input $0.30 / Output $1.20130 tok/s100.00% uptime
- Input $0.105 / Output $0.4265% off125 tok/s99.69% uptime
Input $0.45 / Output $1.80125 tok/s100.00% uptime- Input $0.04368 / Output $0.70122 tok/s99.23% uptime
- Input $0.09772 / Output $0.394465% off120 tok/s99.55% uptime
- Input $0.30 / Output $1.20113 tok/s100.00% uptime
Input $0.15 / Output $0.60113 tok/s98.46% uptime
Input $0.24 / Output $0.96110 tok/s98.31% uptime- Input $0.12 / Output $0.48105 tok/s100.00% uptime
- Input $0.12 / Output $0.4860% off105 tok/s99.97% uptime
- Input $0.059 / Output $0.5295 tok/s99.66% uptime
- Input $0.12 / Output $0.4084 tok/s99.97% uptime
- Input $0.18 / Output $0.6875 tok/s99.30% uptime
- Input $0.195 / Output $0.7874 tok/s100.00% uptime
Input $0.147 / Output $0.44166 tok/s99.36% uptimePriority+11 more label
Input $0.12 / Output $0.4860% off64 tok/s100.00% uptime
Input $0.098 / Output $0.29451% off61 tok/s99.69% uptime- Input $0.111 / Output $0.44463% off53 tok/s100.00% uptime
Input $0.30 / Output $1.2038 tok/s100.00% uptime- Input $0.10 / Output $0.6037 tok/s99.88% uptime
- Input $0.035 / Output $0.1522 tok/s97.37% uptime
Input $0.21 / Output $0.84-- tok/s88.02% uptime- Not used in Nitro routing:Why these endpoints are not used
- Input $0.03 / Output $0.25158 tok/s99.16% uptimeFlex
Input $0.0784 / Output $0.235259 tok/s76.25% 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
| $0.00437 | $0.6996 | 95.2% | 4.2% | ||
| $0.00605 | $0.2996 | 93.5% | 0.1% | ||
| $0.00755 | $0.5997 | 95.3% | 1.3% | ||
| $0.00838 | $1.1998 | 96.0% | 3.0% | ||
| $0.00860 | $0.4797 | 94.7% | 1.8% | ||
| $0.00863 | $0.3080 | 94.4% | 10.8% | ||
| $0.00868 | $0.7623 | 97.5% | 18.7% | ||
| $0.00900 | $0.4198 | 93.3% | 2.3% | ||
| $0.00918 | $0.5197 | 92.3% | 3.5% | ||
| $0.00999 | $0.4999 | 94.0% | 4.3% | ||
| $0.01021 | $0.4842 | 93.5% | 1.0% | ||
| $0.01039 | $0.7796 | 96.6% | 0.1% | ||
| $0.01062 | $0.4467 | 95.8% | 1.2% | ||
| $0.01068 | $0.0700 | 88.8% | 0.4% | ||
| $0.01122 | $0.5164 | 92.8% | 1.4% | ||
| $0.01140 | $0.0714 | 86.6% | 1.2% | ||
| $0.01249 | $0.4998 | 90.4% | 5.5% | ||
| $0.01308 | $0.6244 | 92.9% | 5.1% | ||
| $0.01330 | $0.6239 | 92.6% | 2.8% | ||
| $0.01381 | $0.4998 | 91.1% | 1.5% | ||
| $0.01397 | $0.4999 | 92.5% | 1.9% | ||
| $0.01430 | $0.7197 | 93.9% | 2.8% | ||
| $0.01438 | $0.5975 | 92.9% | 0.5% | ||
| $0.01446 | $0.4436 | 88.7% | 0.2% | ||
| $0.01537 | $0.6963 | 92.9% | 6.1% | ||
| $0.01641 | $0.7206 | 92.8% | 0.2% | ||
| $0.01672 | $0.2753 | 77.7% | 0.1% | ||
| $0.01855 | $0.4790 | 86.3% | 0.0% | ||
| $0.02073 | $1.0000 | 93.6% | 0.5% | ||
| $0.02164 | $0.6697 | 90.5% | 0.4% | ||
| $0.02168 | $0.9597 | 93.1% | 0.9% | ||
| $0.02250 | $1.1997 | 94.4% | 7.0% | ||
| $0.02377 | $0.6798 | 89.8% | 0.0% | ||
| $0.02498 | $0.5484 | 84.3% | 0.1% | ||
| $0.02535 | $1.1997 | 93.5% | 1.0% | ||
| $0.02962 | $0.9593 | 89.4% | 0.0% | ||
| $0.02967 | $1.1996 | 92.3% | 0.7% | ||
| $0.02973 | $1.1998 | 91.9% | 0.7% | ||
| $0.02979 | $1.7996 | 95.3% | 1.1% | ||
| $0.03096 | $0.6198 | 89.7% | 0.8% | ||
| $0.03323 | $1.1998 | 91.2% | 0.0% | ||
| $0.04056 | $0.3997 | 69.7% | 0.1% | ||
| $0.04097 | $0.5875 | 74.4% | 0.1% | ||
| $0.04801 | $1.1996 | 85.7% | 0.0% | ||
| $0.04826 | $1.1997 | 85.6% | 0.4% | ||
| $0.05985 | $1.1996 | 81.7% | 0.0% | ||
| $0.07223 | $1.1999 | 77.5% | 1.3% | ||
| $0.08642 | $2.3996 | 87.6% | 0.3% | ||
Fast | $0.13834 | $2.3996 | 78.8% | 0.2% | |
| $0.02345 | $0.8396 | 90.6% | 0.1% | ||
Not used in Nitro routing:Why these endpoints are not used | |||||
| $0.00507 | $0.2356 | 96.4% | 1.5% | ||
| $0.02391 | $0.2969 | 61.5% | 0.9% | ||
- Effective in $0.00437 / Effective out $0.6996Token share4.2%
- Effective in $0.00605 / Effective out $0.2996Token share0.1%
- Effective in $0.00755 / Effective out $0.5997Token share1.3%
- Effective in $0.00838 / Effective out $1.1998Token share3.0%
- Effective in $0.00860 / Effective out $0.4797Token share1.8%
- Effective in $0.00863 / Effective out $0.3080Token share10.8%
- Effective in $0.00868 / Effective out $0.7623Token share18.7%
- Effective in $0.00900 / Effective out $0.4198Token share2.3%
- Effective in $0.00918 / Effective out $0.5197Token share3.5%
- Effective in $0.00999 / Effective out $0.4999Token share4.3%
- Effective in $0.01021 / Effective out $0.4842Token share1.0%
- Effective in $0.01039 / Effective out $0.7796Token share0.1%
- Effective in $0.01062 / Effective out $0.4467PriorityToken share1.2%
- Effective in $0.01068 / Effective out $0.0700Token share0.4%
- Effective in $0.01122 / Effective out $0.5164Token share1.4%
- Effective in $0.01140 / Effective out $0.0714Token share1.2%
- Effective in $0.01249 / Effective out $0.4998Token share5.5%
- Effective in $0.01308 / Effective out $0.6244Token share5.1%
- Effective in $0.01330 / Effective out $0.6239Token share2.8%
- Effective in $0.01381 / Effective out $0.4998Token share1.5%
- Effective in $0.01397 / Effective out $0.4999Token share1.9%
- Effective in $0.01430 / Effective out $0.7197Token share2.8%
- Effective in $0.01438 / Effective out $0.5975Token share0.5%
- Effective in $0.01446 / Effective out $0.4436Token share0.2%
- Effective in $0.01537 / Effective out $0.6963Token share6.1%
- Effective in $0.01641 / Effective out $0.7206Token share0.2%
- Effective in $0.01672 / Effective out $0.2753Token share0.1%
- Effective in $0.01855 / Effective out $0.4790Token share0.0%
- Effective in $0.02073 / Effective out $1.0000Token share0.5%
- Effective in $0.02164 / Effective out $0.6697Token share0.4%
- Effective in $0.02168 / Effective out $0.9597Token share0.9%
- Effective in $0.02250 / Effective out $1.1997Token share7.0%
- Effective in $0.02377 / Effective out $0.6798Token share0.0%
- Effective in $0.02498 / Effective out $0.5484Token share0.1%
- Effective in $0.02535 / Effective out $1.1997Token share1.0%
- Effective in $0.02962 / Effective out $0.9593Token share0.0%
- Effective in $0.02967 / Effective out $1.1996Token share0.7%
- Effective in $0.02973 / Effective out $1.1998Token share0.7%
- Effective in $0.02979 / Effective out $1.7996Token share1.1%
- Effective in $0.03096 / Effective out $0.6198Token share0.8%
- Effective in $0.03323 / Effective out $1.1998Token share0.0%
- Effective in $0.04056 / Effective out $0.3997Token share0.1%
- Effective in $0.04097 / Effective out $0.5875Token share0.1%
- Effective in $0.04801 / Effective out $1.1996Token share0.0%
- Effective in $0.04826 / Effective out $1.1997Token share0.4%
- Effective in $0.05985 / Effective out $1.1996Token share0.0%
- Effective in $0.07223 / Effective out $1.1999Token share1.3%
- Effective in $0.08642 / Effective out $2.3996FastToken share0.3%
- Effective in $0.13834 / Effective out $2.3996FastToken share0.2%
- Effective in $0.02345 / Effective out $0.8396Token share0.1%
- Not used in Nitro routing:Why these endpoints are not used
- Effective in $0.00507 / Effective out $0.2356FlexToken share1.5%
- Effective in $0.02391 / Effective out $0.2969FlexToken share0.9%
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) Finance & Accounting Index | 39.5 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Strategy & Ops Index | 48.4 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Legal Index | 33.9 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Engineering Index | 34.4 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Economics Index | 35.3 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Openness Index | 44.4 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) AutomationBench-AA | 68.5% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) GDP.pdf | 14.2% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) HLE-Diamond | 20.8% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Terminal-Bench 4.0 | 28.8% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) FrontierCode-AA 2.0 | 16.8% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) Terminal-Bench-Science | 10.5% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) CritPt v2 (Hard Subset) | 27.5% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (High) CritPt v2 | 52.3% |
| 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 1017 (High) MMMU-Pro | 79.7% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Intelligence Index | 32.6 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Finance & Accounting Index | 42.2 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Strategy & Ops Index | 49.2 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Legal Index | 37.7 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Healthcare & Medical Index | 41.3 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Engineering Index | 37.6 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Economics Index | 38.5 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Cyber Index | 56.8 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Openness Index | 44.4 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) AutomationBench-AA | 66.6% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) GDP.pdf | 17.2% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) HLE | 43.3% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) AA-LCR | 82.7% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) GDPval-AA | 62.3% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) CritPt | 24.0% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) HLE-Diamond | 25.3% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) SciCode | 55.9% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Terminal-Bench 4.0 | 33.8% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) FrontierCode-AA 2.0 | 28.5% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) FrontierCode 1.1 | 43.7% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) Terminal-Bench-Science | 12.9% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) CritPt v2 (Hard Subset) | 25.0% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) CritPt v2 | 50.6% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) AA-Omniscience Accuracy | 39.6% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) AA-Omniscience Non-Hallucination Rate | 35.9% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) CWE-Bench-AA | 69.2% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) DeepsecBench-AA | 24.9% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) CyberGym-E2E-AA | 76.3% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) MLCR-AA | 26.7% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) MMMU-Pro | 80.6% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Max) VIALS-AA | 40.4% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Intelligence Index | 18.5 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Finance & Accounting Index | 37.2 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Strategy & Ops Index | 39.7 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Legal Index | 31.7 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Engineering Index | 25.0 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Economics Index | 32.1 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Openness Index | 44.4 |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) AutomationBench-AA | 48.8% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) GDP.pdf | 4.4% |
| 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) GDPval-AA | 40.9% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) CritPt | 0.3% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) HLE-Diamond | 7.1% |
| 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) FrontierCode-AA 2.0 | 6.1% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) Terminal-Bench-Science | 2.4% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) CritPt v2 (Hard Subset) | 1.0% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) CritPt v2 | 4.9% |
| 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% |
| Artificial Analysis | DeepSeek V4.1 Flash 1017 (Non-reasoning) MMMU-Pro | 69.2% |
| Design Arena | DeepSeek-V4.1-Flash (1017) Agents Arena Spreadsheet Elo | 1261 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena 3D Elo | 1338 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Asciiart Elo | 1219 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Code Categories Elo | 1283 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Data Visualization Elo | 1271 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Game Development Elo | 1249 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena SVG Elo | 1241 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena UI Component Elo | 1279 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Website Elo | 1290 |
| 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 Robo-bench | 4.2% |
| 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 $0.035/M input tokens and $0.15/M output tokens, with separate rates for Cache Read at $0.0015/M tokens.
DeepSeek V4.1 Flash 1017 has a 1,048,576 token context window. It supports up to 1,048,576 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 42 providers on OpenRouter: Particle AI, Ambient, Wafer, Sail Research, Prime Intellect, Pearl Research, Morph, DeepInfra and 34 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.