
DeepSeek: DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017
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).
| $0.12000 | $0.5000 | $0.003000 | 0.79s | 151 tok/s | ||
| $0.15000 | $0.5000 | $0.003000 | 0.91s | 144 tok/s | ||
| $0.18000 | $0.7200 | $0.003600 | 0.77s | 163 tok/s | ||
65% off | $0.30$0.10500 | $1.20$0.4200 | $0.006$0.002100 | 1.26s | 128 tok/s | |
| $0.05900 | $0.5200 | $0.005000 | 0.60s | 123 tok/s | ||
| $0.18$0.09000 | $0.72$0.3600 | $0.0036$0.001800 | 1.10s | 118 tok/s | ||
| $0.12000 | $0.4800 | $0.002400 | 0.92s | 121 tok/s | ||
| $0.03600 | $0.5000 | $0.010000 | 0.41s | 128 tok/s | ||
| $0.17000 | $0.6700 | $0.006000 | 0.92s | 134 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.22s | 126 tok/s | ||
| $0.07000 | $0.5000 | $0.006900 | 0.46s | 126 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.26s | 118 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.61s | 180 tok/s | ||
| $0.09000 | $1.2000 | $0.005000 | 0.97s | 150 tok/s | ||
| $0.20$0.09800 | $0.60$0.2940 | $0.006$0.002940 | 0.84s | 86 tok/s | ||
| $0.04368 | $0.7000 | $0.002400 | 1.09s | 87 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.91s | 157 tok/s | ||
| $0.29000 | $1.2000 | $0.007000 | 0.83s | 176 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 1.36s | 172 tok/s | ||
| $0.30$0.14700 | $0.90$0.4410 | $0.009$0.004410 | 1.04s | 89 tok/s | ||
| $0.10000 | $0.6000 | $0.003000 | 1.97s | 88 tok/s | ||
60% off | $0.30$0.12000 | $1.20$0.4800 | $0.006$0.002400 | 1.52s | 83 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 0.50s | 189 tok/s | ||
| $0.18000 | $0.6800 | $0.006000 | 1.38s | 104 tok/s | ||
| $0.21000 | $0.6200 | $0.010500 | 1.05s | 187 tok/s | ||
40% off | $0.30$0.18000 | $1.20$0.7200 | $0.006$0.003600 | 1.04s | 157 tok/s | |
| $0.04000 | $0.0700 | $0.007000 | 1.17s | 116 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 0.84s | 111 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.53s | 159 tok/s | ||
| $0.12000 | $0.4000 | $0.006000 | 0.58s | 91 tok/s | ||
| $0.30000 | $1.2000 | $0.007500 | 2.50s | 105 tok/s | ||
| $0.25000 | $1.0000 | $0.005000 | 0.92s | 93 tok/s | ||
| $0.45000 | $1.8000 | $0.009000 | 0.89s | 139 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.94s | 213 tok/s | ||
63% off | $0.30$0.11100 | $1.20$0.4440 | $0.006$0.002220 | 1.83s | 57 tok/s | |
| $0.09800 | $0.2940 | $0.002900 | 0.76s | 67 tok/s | ||
| $0.08000 | $0.6000 | $0.030000 | 0.96s | 68 tok/s | ||
| $0.04000 | $0.0700 | $0.007000 | 1.47s | 112 tok/s | ||
47% off | $0.28$0.14980 | $1.13$0.6046 | $0.006$0.003210 | 1.51s | 95 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 1.87s | 41 tok/s | ||
| $0.30000 | $0.5500 | $0.006000 | 1.70s | 43 tok/s | ||
| $0.24000 | $0.9600 | $0.004800 | 1.19s | 139 tok/s | ||
| $0.19500 | $0.7800 | $0.003900 | 1.35s | 77 tok/s | ||
| $0.15000 | $0.6000 | $0.003000 | 1.15s | 115 tok/s | ||
| $0.60000 | $2.4000 | $0.014000 | 0.71s | 242 tok/s | ||
Fast | $0.60000 | $2.4000 | $0.014000 | 0.38s | 451 tok/s | |
| $0.21000 | $0.8400 | $0.004200 | 4.47s | 78 tok/s | ||
Not used in Standard routing:Why these endpoints are not used | ||||||
| $0.04000 | $0.3000 | $0.015000 | 0.63s | 98 tok/s | ||
Flex | $0.07750 | $0.2325 | $0.002325 | 0.92s | 152 tok/s | |
| $0.16$0.07840 | $0.48$0.2352 | $0.0048$0.002352 | 2.14s | 78 tok/s | ||
- Input $0.12 / Output $0.50151 tok/s99.97% uptime
Input $0.15 / Output $0.50144 tok/s99.94% uptime- Input $0.18 / Output $0.72163 tok/s100.00% uptime
- Input $0.105 / Output $0.4265% off128 tok/s99.92% uptime
- Input $0.059 / Output $0.52123 tok/s99.68% uptime
- Input $0.09 / Output $0.36118 tok/s99.81% uptime
- Input $0.12 / Output $0.48121 tok/s100.00% uptime
- Input $0.036 / Output $0.50128 tok/s100.00% uptime

Input $0.17 / Output $0.67134 tok/s100.00% uptime- Input $0.08 / Output $0.605126 tok/s100.00% uptime
- Input $0.07 / Output $0.50126 tok/s100.00% uptime
- Input $0.08 / Output $0.605118 tok/s100.00% uptime
- Input $0.30 / Output $1.20180 tok/s100.00% uptime
- Input $0.09 / Output $1.20150 tok/s99.71% uptime
Input $0.098 / Output $0.29451% off86 tok/s99.81% uptime- Input $0.04368 / Output $0.7087 tok/s99.23% uptime
Input $0.30 / Output $1.20157 tok/s99.94% uptime- Input $0.29 / Output $1.20176 tok/s100.00% uptime
Input $0.30 / Output $1.20172 tok/s99.97% uptime
Input $0.147 / Output $0.44189 tok/s99.55% uptimePriority+11 more label- Input $0.10 / Output $0.6088 tok/s100.00% uptime
- Input $0.12 / Output $0.4860% off83 tok/s99.89% uptime
- Input $0.30 / Output $1.20189 tok/s95.35% uptime
- Input $0.18 / Output $0.68104 tok/s99.19% uptime
- Input $0.21 / Output $0.62187 tok/s99.86% uptime
- Input $0.18 / Output $0.7240% off157 tok/s99.78% uptime
- Input $0.04 / Output $0.07116 tok/s97.18% uptime
- Input $0.30 / Output $1.20111 tok/s100.00% uptime
- Input $0.30 / Output $1.20159 tok/s99.94% uptime
- Input $0.12 / Output $0.4091 tok/s99.97% uptime
- Input $0.30 / Output $1.20105 tok/s100.00% uptime
- Input $0.25 / Output $1.0093 tok/s100.00% uptime
Input $0.45 / Output $1.80139 tok/s100.00% uptime- Input $0.30 / Output $1.20213 tok/s100.00% uptime
- Input $0.111 / Output $0.44463% off57 tok/s100.00% uptime
- Input $0.098 / Output $0.29467 tok/s99.54% uptime
- Input $0.08 / Output $0.6068 tok/s99.89% uptime
- Input $0.04 / Output $0.07112 tok/s90.93% uptime
- Input $0.1498 / Output $0.604647% off95 tok/s99.97% uptime
Input $0.30 / Output $1.2041 tok/s100.00% uptime- Input $0.30 / Output $0.5543 tok/s99.85% uptime
Input $0.24 / Output $0.96139 tok/s98.20% uptime- Input $0.195 / Output $0.7877 tok/s100.00% uptime
Input $0.15 / Output $0.60115 tok/s100.00% uptime- Input $0.60 / Output $2.40242 tok/s99.63% uptimeFast
- Input $0.60 / Output $2.40451 tok/s100.00% uptimeFast
Input $0.21 / Output $0.8478 tok/s94.21% uptime- Not used in Standard routing:Why these endpoints are not used
- Input $0.04 / Output $0.3098 tok/s100.00% uptimeFlex
- Input $0.0775 / Output $0.2325152 tok/s100.00% uptimeFlex
Input $0.0784 / Output $0.235278 tok/s75.98% 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
| $0.00509 | $0.6996 | 93.5% | 3.3% | ||
| $0.00708 | $0.4286 | 95.3% | 2.2% | ||
| $0.00722 | $1.1997 | 97.5% | 3.5% | ||
| $0.00886 | $0.4196 | 93.4% | 2.4% | ||
| $0.00915 | $0.3210 | 94.6% | 10.6% | ||
| $0.00942 | $0.8368 | 97.5% | 19.9% | ||
| $0.00942 | $0.7796 | 97.1% | 0.1% | ||
| $0.00942 | $0.0697 | 92.8% | 1.4% | ||
| $0.00957 | $0.4821 | 94.0% | 0.9% | ||
| $0.00970 | $0.5511 | 92.3% | 3.2% | ||
| $0.00973 | $0.4998 | 94.2% | 4.7% | ||
| $0.00978 | $0.5997 | 93.0% | 0.9% | ||
| $0.00984 | $0.0698 | 91.6% | 1.7% | ||
| $0.01090 | $0.6878 | 95.4% | 1.7% | ||
| $0.01177 | $0.4998 | 94.0% | 2.8% | ||
| $0.01259 | $0.4998 | 90.0% | 7.3% | ||
| $0.01273 | $0.4475 | 94.3% | 1.3% | ||
| $0.01362 | $0.6047 | 92.2% | 1.3% | ||
| $0.01398 | $0.4998 | 90.1% | 2.2% | ||
| $0.01406 | $0.2930 | 88.2% | 0.0% | ||
| $0.01422 | $0.7196 | 94.0% | 3.3% | ||
| $0.01434 | $0.6046 | 91.2% | 5.6% | ||
| $0.01699 | $0.4430 | 86.4% | 0.1% | ||
| $0.01880 | $0.6695 | 92.2% | 0.7% | ||
| $0.01973 | $1.1997 | 95.3% | 7.3% | ||
| $0.02122 | $1.0000 | 93.4% | 0.6% | ||
| $0.02256 | $0.6795 | 90.5% | 0.1% | ||
| $0.02442 | $1.1997 | 94.1% | 0.8% | ||
| $0.02518 | $1.1995 | 94.0% | 0.0% | ||
| $0.02700 | $0.8396 | 88.9% | 0.6% | ||
| $0.03002 | $1.1997 | 91.9% | 1.5% | ||
| $0.03032 | $0.6196 | 90.1% | 0.9% | ||
| $0.03066 | $0.7199 | 84.7% | 0.2% | ||
| $0.03107 | $1.1996 | 91.8% | 0.6% | ||
| $0.03108 | $1.7996 | 95.0% | 0.8% | ||
| $0.03432 | $1.1997 | 90.4% | 0.4% | ||
| $0.04293 | $0.9590 | 83.8% | 0.0% | ||
| $0.04297 | $0.5993 | 74.0% | 0.2% | ||
| $0.04447 | $0.3996 | 66.2% | 0.2% | ||
| $0.04584 | $1.1997 | 86.4% | 1.5% | ||
| $0.05642 | $1.1997 | 82.8% | 0.3% | ||
| $0.08761 | $1.1996 | 72.2% | 0.5% | ||
| $0.09382 | $0.5497 | 70.1% | 0.0% | ||
| $0.09615 | $1.0869 | 65.5% | 0.0% | ||
Fast | $0.12130 | $2.3995 | 81.7% | 0.3% | |
| $0.12871 | $2.3994 | 80.4% | 0.1% | ||
| $0.17767 | $1.1979 | 41.6% | 0.0% | ||
Not used in Standard routing:Why these endpoints are not used | |||||
| $0.00455 | $0.2363 | 97.2% | 0.8% | ||
Flex | $0.00738 | $0.2321 | 93.3% | 0.3% | |
| $0.02405 | $0.2998 | 63.7% | 0.9% | ||
- Effective in $0.00509 / Effective out $0.6996Token share3.3%
- Effective in $0.00708 / Effective out $0.4286Token share2.2%
- Effective in $0.00722 / Effective out $1.1997Token share3.5%
- Effective in $0.00886 / Effective out $0.4196Token share2.4%
- Effective in $0.00915 / Effective out $0.3210Token share10.6%
- Effective in $0.00942 / Effective out $0.8368Token share19.9%
- Effective in $0.00942 / Effective out $0.7796Token share0.1%
- Effective in $0.00942 / Effective out $0.0697Token share1.4%
- Effective in $0.00957 / Effective out $0.4821Token share0.9%
- Effective in $0.00970 / Effective out $0.5511Token share3.2%
- Effective in $0.00973 / Effective out $0.4998Token share4.7%
- Effective in $0.00978 / Effective out $0.5997Token share0.9%
- Effective in $0.00984 / Effective out $0.0698Token share1.7%
- Effective in $0.01090 / Effective out $0.6878Token share1.7%
- Effective in $0.01177 / Effective out $0.4998Token share2.8%
- Effective in $0.01259 / Effective out $0.4998Token share7.3%
- Effective in $0.01273 / Effective out $0.4475PriorityToken share1.3%
- Effective in $0.01362 / Effective out $0.6047Token share1.3%
- Effective in $0.01398 / Effective out $0.4998Token share2.2%
- Effective in $0.01406 / Effective out $0.2930Token share0.0%
- Effective in $0.01422 / Effective out $0.7196Token share3.3%
- Effective in $0.01434 / Effective out $0.6046Token share5.6%
- Effective in $0.01699 / Effective out $0.4430Token share0.1%
- Effective in $0.01880 / Effective out $0.6695Token share0.7%
- Effective in $0.01973 / Effective out $1.1997Token share7.3%
- Effective in $0.02122 / Effective out $1.0000Token share0.6%
- Effective in $0.02256 / Effective out $0.6795Token share0.1%
- Effective in $0.02442 / Effective out $1.1997Token share0.8%
- Effective in $0.02518 / Effective out $1.1995Token share0.0%
- Effective in $0.02700 / Effective out $0.8396Token share0.6%
- Effective in $0.03002 / Effective out $1.1997Token share1.5%
- Effective in $0.03032 / Effective out $0.6196Token share0.9%
- Effective in $0.03066 / Effective out $0.7199Token share0.2%
- Effective in $0.03107 / Effective out $1.1996Token share0.6%
- Effective in $0.03108 / Effective out $1.7996Token share0.8%
- Effective in $0.03432 / Effective out $1.1997Token share0.4%
- Effective in $0.04293 / Effective out $0.9590Token share0.0%
- Effective in $0.04297 / Effective out $0.5993Token share0.2%
- Effective in $0.04447 / Effective out $0.3996Token share0.2%
- Effective in $0.04584 / Effective out $1.1997Token share1.5%
- Effective in $0.05642 / Effective out $1.1997Token share0.3%
- Effective in $0.08761 / Effective out $1.1996Token share0.5%
- Effective in $0.09382 / Effective out $0.5497Token share0.0%
- Effective in $0.09615 / Effective out $1.0869Token share0.0%
- Effective in $0.12130 / Effective out $2.3995FastToken share0.3%
- Effective in $0.12871 / Effective out $2.3994FastToken share0.1%
- Effective in $0.17767 / Effective out $1.1979Token share0.0%
- Not used in Standard routing:Why these endpoints are not used
- Effective in $0.00455 / Effective out $0.2363FlexToken share0.8%
- Effective in $0.00738 / Effective out $0.2321FlexToken share0.3%
- Effective in $0.02405 / Effective out $0.2998FlexToken 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) 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 | 1265 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena 3D Elo | 1344 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Asciiart Elo | 1219 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Code Categories Elo | 1286 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Data Visualization Elo | 1276 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Game Development Elo | 1253 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena SVG Elo | 1241 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena UI Component Elo | 1280 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena Website Elo | 1293 |
| 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 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 $0.036/M input tokens and $0.50/M output tokens, with separate rates for Cache Read at $0.01/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 39 providers on OpenRouter: Wafer, Sail Research, Particle AI, Prime Intellect, Morph, Ionstream, DeepInfra, inference.net and 31 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.