
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).
65% off | $0.30$0.10500 | $1.20$0.4200 | $0.006$0.002100 | 0.65s | 154 tok/s | |
|---|---|---|---|---|---|---|
| $0.12000 | $0.5000 | $0.003000 | 0.67s | 148 tok/s | ||
| $0.04000 | $0.0700 | $0.007000 | 1.33s | 131 tok/s | ||
| $0.06600 | $0.5000 | $0.006500 | 0.35s | 178 tok/s | ||
| $0.18000 | $0.7200 | $0.003600 | 0.68s | 177 tok/s | ||
| $0.03600 | $0.5000 | $0.010000 | 0.33s | 169 tok/s | ||
| $0.04000 | $0.0700 | $0.007000 | 1.28s | 116 tok/s | ||
| $0.15000 | $0.5000 | $0.003000 | 0.88s | 123 tok/s | ||
| $0.12000 | $0.4800 | $0.002400 | 0.94s | 111 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.24s | 125 tok/s | ||
| $0.17000 | $0.6700 | $0.006000 | 0.66s | 137 tok/s | ||
| $0.20$0.09800 | $0.60$0.2940 | $0.006$0.002940 | 0.70s | 104 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.30s | 116 tok/s | ||
| $0.30$0.14700 | $0.90$0.4410 | $0.009$0.004410 | 0.79s | 121 tok/s | ||
| $0.21000 | $0.6200 | $0.010500 | 0.67s | 162 tok/s | ||
60% off | $0.30$0.12000 | $1.20$0.4800 | $0.006$0.002400 | 1.39s | 112 tok/s | |
| $0.09000 | $1.2000 | $0.005000 | 0.91s | 145 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.60s | 182 tok/s | ||
| $0.25000 | $1.0000 | $0.005000 | 0.62s | 142 tok/s | ||
| $0.18000 | $0.7200 | $0.003600 | 1.64s | 112 tok/s | ||
| $0.05900 | $0.5200 | $0.005000 | 0.62s | 110 tok/s | ||
| $0.18000 | $0.6800 | $0.006000 | 0.96s | 109 tok/s | ||
| $0.10000 | $0.6000 | $0.003000 | 2.20s | 96 tok/s | ||
| $0.29000 | $1.2000 | $0.007000 | 0.86s | 169 tok/s | ||
| $0.08000 | $0.6000 | $0.030000 | 0.43s | 121 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 1.37s | 165 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.45s | 154 tok/s | ||
| $0.12000 | $0.4000 | $0.006000 | 0.42s | 93 tok/s | ||
| $0.09800 | $0.2940 | $0.002900 | 0.33s | 59 tok/s | ||
| $0.45000 | $1.8000 | $0.009000 | 0.95s | 154 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.56s | 157 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 0.88s | 108 tok/s | ||
40% off | $0.30$0.18000 | $1.20$0.7200 | $0.006$0.003600 | 0.90s | 175 tok/s | |
| $0.04368 | $0.7000 | $0.002400 | 2.13s | 66 tok/s | ||
63% off | $0.30$0.11100 | $1.20$0.4440 | $0.006$0.002220 | 2.03s | 49 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 3.14s | 76 tok/s | ||
| $0.30000 | $1.2000 | $0.007500 | 1.45s | 112 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 5.64s | 41 tok/s | ||
| $0.19500 | $0.7800 | $0.003900 | 2.44s | 103 tok/s | ||
| $0.24000 | $0.9600 | $0.004800 | 0.67s | 179 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.59s | 43 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 1.20s | 113 tok/s | ||
| $0.28000 | $1.1300 | $0.006000 | 1.98s | 90 tok/s | ||
| $0.60000 | $2.4000 | $0.014000 | 0.45s | 200 tok/s | ||
Fast | $0.60000 | $2.4000 | $0.014000 | 0.36s | 477 tok/s | |
| $0.30000 | $0.5500 | $0.006000 | 1.75s | 45 tok/s | ||
| $0.21000 | $0.8400 | $0.004200 | 2.72s | 94 tok/s | ||
Not used in Standard routing:Why these endpoints are not used | ||||||
| $0.04000 | $0.3000 | $0.015000 | 0.52s | 123 tok/s | ||
Flex | $0.07750 | $0.2325 | $0.002325 | 0.94s | 137 tok/s | |
| $0.16$0.07840 | $0.48$0.2352 | $0.0048$0.002352 | 2.13s | 101 tok/s | ||
- Input $0.105 / Output $0.4265% off154 tok/s99.90% uptime
- Input $0.12 / Output $0.50148 tok/s99.96% uptime
- Input $0.04 / Output $0.07131 tok/s89.78% uptime
- Input $0.066 / Output $0.50178 tok/s100.00% uptime
- Input $0.18 / Output $0.72177 tok/s100.00% uptime
- Input $0.036 / Output $0.50169 tok/s100.00% uptime
- Input $0.04 / Output $0.07116 tok/s97.12% uptime
Input $0.15 / Output $0.50123 tok/s99.93% uptime- Input $0.12 / Output $0.48111 tok/s100.00% uptime
- Input $0.08 / Output $0.605125 tok/s100.00% uptime

Input $0.17 / Output $0.67137 tok/s100.00% uptime
Input $0.098 / Output $0.29451% off104 tok/s99.78% uptime- Input $0.08 / Output $0.605116 tok/s100.00% uptime
Input $0.147 / Output $0.441121 tok/s99.48% uptimePriority+11 more label- Input $0.21 / Output $0.62162 tok/s99.90% uptime
- Input $0.12 / Output $0.4860% off112 tok/s99.87% uptime
- Input $0.09 / Output $1.20145 tok/s99.81% uptime
- Input $0.30 / Output $1.20182 tok/s100.00% uptime
- Input $0.25 / Output $1.00142 tok/s100.00% uptime
- Input $0.18 / Output $0.72112 tok/s99.78% uptime
- Input $0.059 / Output $0.52110 tok/s99.63% uptime
- Input $0.18 / Output $0.68109 tok/s99.06% uptime
- Input $0.10 / Output $0.6096 tok/s100.00% uptime
- Input $0.29 / Output $1.20169 tok/s100.00% uptime
- Input $0.08 / Output $0.60121 tok/s99.87% uptime
Input $0.30 / Output $1.20165 tok/s99.96% uptime- Input $0.30 / Output $1.20154 tok/s99.93% uptime
- Input $0.12 / Output $0.4093 tok/s99.96% uptime
- Input $0.098 / Output $0.29459 tok/s99.51% uptime
Input $0.45 / Output $1.80154 tok/s100.00% uptime- Input $0.30 / Output $1.20157 tok/s94.66% uptime
- Input $0.30 / Output $1.20108 tok/s100.00% uptime
- Input $0.18 / Output $0.7240% off175 tok/s99.78% uptime
- Input $0.04368 / Output $0.7066 tok/s99.12% uptime
- Input $0.111 / Output $0.44463% off49 tok/s100.00% uptime
- Input $0.30 / Output $1.2076 tok/s100.00% uptime
- Input $0.30 / Output $1.20112 tok/s100.00% uptime
Input $0.30 / Output $1.2041 tok/s99.93% uptime- Input $0.195 / Output $0.78103 tok/s100.00% uptime
Input $0.24 / Output $0.96179 tok/s97.93% uptime
Input $0.30 / Output $1.2043 tok/s100.00% uptime
Input $0.30 / Output $1.20113 tok/s100.00% uptime- Input $0.28 / Output $1.1390 tok/s99.96% uptime
- Input $0.60 / Output $2.40200 tok/s99.47% uptimeFast
- Input $0.60 / Output $2.40477 tok/s100.00% uptimeFast
- Input $0.30 / Output $0.5545 tok/s99.83% uptime
Input $0.21 / Output $0.8494 tok/s93.91% uptime- Not used in Standard routing:Why these endpoints are not used
- Input $0.04 / Output $0.30123 tok/s100.00% uptimeFlex
- Input $0.0775 / Output $0.2325137 tok/s100.00% uptimeFlex
Input $0.0784 / Output $0.2352101 tok/s72.43% 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
| $0.00515 | $0.6996 | 93.3% | 3.1% | ||
| $0.00600 | $0.3602 | 95.3% | 2.3% | ||
| $0.00710 | $1.1997 | 97.7% | 4.1% | ||
| $0.00935 | $0.0698 | 93.1% | 1.9% | ||
| $0.00947 | $0.4196 | 92.8% | 2.6% | ||
| $0.00963 | $0.4998 | 94.3% | 5.0% | ||
| $0.00972 | $0.4823 | 93.9% | 1.1% | ||
| $0.00989 | $0.0699 | 91.8% | 1.9% | ||
| $0.01002 | $0.3231 | 94.0% | 11.4% | ||
| $0.01052 | $0.7796 | 96.5% | 0.1% | ||
| $0.01062 | $0.6024 | 92.5% | 2.9% | ||
| $0.01084 | $0.7199 | 95.9% | 2.2% | ||
| $0.01120 | $0.5997 | 91.5% | 0.9% | ||
| $0.01166 | $0.8926 | 96.9% | 15.1% | ||
| $0.01253 | $0.4998 | 93.5% | 3.1% | ||
| $0.01265 | $0.4998 | 89.8% | 7.9% | ||
| $0.01297 | $0.2932 | 89.4% | 0.0% | ||
| $0.01329 | $0.4507 | 94.1% | 1.2% | ||
| $0.01421 | $0.7196 | 94.0% | 3.6% | ||
| $0.01452 | $0.6047 | 90.9% | 1.2% | ||
| $0.01478 | $0.6047 | 90.6% | 6.9% | ||
| $0.01600 | $0.4998 | 90.0% | 2.3% | ||
| $0.01950 | $0.4428 | 84.1% | 0.1% | ||
| $0.01997 | $1.1997 | 95.2% | 7.5% | ||
| $0.02043 | $1.0000 | 93.7% | 0.7% | ||
| $0.02132 | $0.6794 | 91.2% | 0.1% | ||
| $0.02162 | $0.6695 | 90.5% | 0.6% | ||
| $0.02411 | $1.1994 | 94.3% | 0.0% | ||
| $0.02729 | $1.1996 | 93.1% | 0.5% | ||
| $0.03049 | $0.6196 | 90.0% | 1.0% | ||
| $0.03131 | $1.1996 | 91.7% | 0.7% | ||
| $0.03232 | $0.7211 | 83.8% | 0.1% | ||
| $0.03256 | $1.7995 | 94.7% | 0.7% | ||
| $0.03273 | $1.1996 | 90.9% | 1.1% | ||
| $0.03683 | $0.3996 | 72.9% | 0.2% | ||
| $0.04448 | $0.5993 | 71.0% | 0.2% | ||
| $0.04522 | $1.1997 | 86.7% | 0.3% | ||
| $0.05249 | $1.1997 | 84.2% | 0.9% | ||
| $0.05940 | $1.1997 | 81.8% | 0.3% | ||
| $0.07300 | $0.9585 | 71.0% | 0.0% | ||
| $0.10659 | $1.1295 | 63.3% | 0.0% | ||
| $0.10883 | $0.5497 | 65.0% | 0.0% | ||
| $0.11589 | $1.1996 | 62.6% | 0.5% | ||
Fast | $0.11663 | $2.3995 | 82.5% | 0.4% | |
| $0.13007 | $2.3994 | 80.2% | 0.2% | ||
| $0.21159 | $1.1973 | 30.0% | 0.0% | ||
| $0.02024 | $0.8397 | 92.2% | 0.7% | ||
Not used in Standard routing:Why these endpoints are not used | |||||
| $0.00472 | $0.2376 | 97.0% | 0.6% | ||
Flex | $0.00748 | $0.2322 | 93.1% | 0.3% | |
| $0.02376 | $0.2998 | 64.9% | 1.2% | ||
- Effective in $0.00515 / Effective out $0.6996Token share3.1%
- Effective in $0.00600 / Effective out $0.3602Token share2.3%
- Effective in $0.00710 / Effective out $1.1997Token share4.1%
- Effective in $0.00935 / Effective out $0.0698Token share1.9%
- Effective in $0.00947 / Effective out $0.4196Token share2.6%
- Effective in $0.00963 / Effective out $0.4998Token share5.0%
- Effective in $0.00972 / Effective out $0.4823Token share1.1%
- Effective in $0.00989 / Effective out $0.0699Token share1.9%
- Effective in $0.01002 / Effective out $0.3231Token share11.4%
- Effective in $0.01052 / Effective out $0.7796Token share0.1%
- Effective in $0.01062 / Effective out $0.6024Token share2.9%
- Effective in $0.01084 / Effective out $0.7199Token share2.2%
- Effective in $0.01120 / Effective out $0.5997Token share0.9%
- Effective in $0.01166 / Effective out $0.8926Token share15.1%
- Effective in $0.01253 / Effective out $0.4998Token share3.1%
- Effective in $0.01265 / Effective out $0.4998Token share7.9%
- Effective in $0.01297 / Effective out $0.2932Token share0.0%
- Effective in $0.01329 / Effective out $0.4507PriorityToken share1.2%
- Effective in $0.01421 / Effective out $0.7196Token share3.6%
- Effective in $0.01452 / Effective out $0.6047Token share1.2%
- Effective in $0.01478 / Effective out $0.6047Token share6.9%
- Effective in $0.01600 / Effective out $0.4998Token share2.3%
- Effective in $0.01950 / Effective out $0.4428Token share0.1%
- Effective in $0.01997 / Effective out $1.1997Token share7.5%
- Effective in $0.02043 / Effective out $1.0000Token share0.7%
- Effective in $0.02132 / Effective out $0.6794Token share0.1%
- Effective in $0.02162 / Effective out $0.6695Token share0.6%
- Effective in $0.02411 / Effective out $1.1994Token share0.0%
- Effective in $0.02729 / Effective out $1.1996Token share0.5%
- Effective in $0.03049 / Effective out $0.6196Token share1.0%
- Effective in $0.03131 / Effective out $1.1996Token share0.7%
- Effective in $0.03232 / Effective out $0.7211Token share0.1%
- Effective in $0.03256 / Effective out $1.7995Token share0.7%
- Effective in $0.03273 / Effective out $1.1996Token share1.1%
- Effective in $0.03683 / Effective out $0.3996Token share0.2%
- Effective in $0.04448 / Effective out $0.5993Token share0.2%
- Effective in $0.04522 / Effective out $1.1997Token share0.3%
- Effective in $0.05249 / Effective out $1.1997Token share0.9%
- Effective in $0.05940 / Effective out $1.1997Token share0.3%
- Effective in $0.07300 / Effective out $0.9585Token share0.0%
- Effective in $0.10659 / Effective out $1.1295Token share0.0%
- Effective in $0.10883 / Effective out $0.5497Token share0.0%
- Effective in $0.11589 / Effective out $1.1996Token share0.5%
- Effective in $0.11663 / Effective out $2.3995FastToken share0.4%
- Effective in $0.13007 / Effective out $2.3994FastToken share0.2%
- Effective in $0.21159 / Effective out $1.1973Token share0.0%
- Effective in $0.02024 / Effective out $0.8397Token share0.7%
- Not used in Standard routing:Why these endpoints are not used
- Effective in $0.00472 / Effective out $0.2376FlexToken share0.6%
- Effective in $0.00748 / Effective out $0.2322FlexToken share0.3%
- Effective in $0.02376 / Effective out $0.2998FlexToken share1.2%
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 | 1218 |
| 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 | 1252 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena SVG Elo | 1241 |
| Design Arena | DeepSeek-V4.1-Flash (1017) Models Arena UI Component Elo | 1281 |
| 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.