
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 | 0.35s | 455 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 0.93s | 185 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.53s | 184 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.50s | 179 tok/s | ||
| $0.60000 | $2.4000 | $0.014000 | 1.30s | 177 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.69s | 173 tok/s | ||
| $0.45000 | $1.8000 | $0.009000 | 0.75s | 173 tok/s | ||
| $0.06600 | $0.5000 | $0.006500 | 0.41s | 167 tok/s | ||
| $0.03600 | $0.5000 | $0.010000 | 0.40s | 167 tok/s | ||
| $0.12000 | $0.5000 | $0.003000 | 0.74s | 162 tok/s | ||
| $0.18000 | $0.7200 | $0.003600 | 0.75s | 162 tok/s | ||
| $0.30000 | $1.2000 | $0.006000 | 0.50s | 162 tok/s | ||
20% off | $0.30$0.24000 | $1.20$0.9600 | $0.007$0.005600 | 1.39s | 155 tok/s | |
40% off | $0.30$0.18000 | $1.20$0.7200 | $0.006$0.003600 | 0.97s | 154 tok/s | |
| $0.17000 | $0.6700 | $0.006000 | 0.71s | 152 tok/s | ||
| $0.08000 | $0.6000 | $0.030000 | 0.75s | 151 tok/s | ||
| $0.09000 | $1.2000 | $0.005000 | 0.88s | 148 tok/s | ||
| $0.25000 | $1.0000 | $0.005000 | 0.68s | 143 tok/s | ||
| $0.15000 | $0.5000 | $0.003000 | 0.80s | 136 tok/s | ||
| $0.30000 | $1.2000 | $0.007500 | 1.11s | 135 tok/s | ||
65% off | $0.30$0.10500 | $1.20$0.4200 | $0.006$0.002100 | 1.01s | 132 tok/s | |
| $0.29000 | $1.2000 | $0.007000 | 1.48s | 130 tok/s | ||
| $0.30000 | $1.2000 | $0.007000 | 0.70s | 125 tok/s | ||
| $0.18$0.09000 | $0.72$0.3600 | $0.0036$0.001800 | 0.80s | 124 tok/s | ||
| $0.15000 | $0.6000 | $0.003000 | 1.12s | 124 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.26s | 122 tok/s | ||
| $0.24000 | $0.9600 | $0.004800 | 1.71s | 122 tok/s | ||
| $0.12000 | $0.4800 | $0.002400 | 0.96s | 119 tok/s | ||
| $0.04368 | $0.7000 | $0.002400 | 0.75s | 115 tok/s | ||
| $0.18000 | $0.6800 | $0.006000 | 1.96s | 113 tok/s | ||
| $0.08000 | $0.6050 | $0.008000 | 0.24s | 112 tok/s | ||
| $0.05900 | $0.5200 | $0.005000 | 0.52s | 110 tok/s | ||
| $0.10000 | $0.6000 | $0.003000 | 1.87s | 101 tok/s | ||
| $0.30$0.14700 | $0.90$0.4410 | $0.009$0.004410 | 1.01s | 97 tok/s | ||
60% off | $0.30$0.12000 | $1.20$0.4800 | $0.006$0.002400 | 1.62s | 94 tok/s | |
| $0.21000 | $0.6200 | $0.010500 | 1.53s | 94 tok/s | ||
| $0.19500 | $0.7800 | $0.003900 | 2.10s | 90 tok/s | ||
| $0.20$0.09800 | $0.60$0.2940 | $0.006$0.002940 | 0.91s | 83 tok/s | ||
| $0.12000 | $0.4000 | $0.006000 | 0.72s | 83 tok/s | ||
| $0.21000 | $0.8400 | $0.004200 | 2.99s | 76 tok/s | ||
65% off | $0.28$0.09772 | $1.13$0.3944 | $0.006$0.002094 | 1.26s | 73 tok/s | |
| $0.09800 | $0.2940 | $0.002900 | 0.71s | 67 tok/s | ||
| $0.30000 | $0.5500 | $0.006000 | 1.10s | 63 tok/s | ||
63% off | $0.30$0.11100 | $1.20$0.4440 | $0.006$0.002220 | 1.75s | 58 tok/s | |
| $0.30000 | $1.2000 | $0.006000 | 0.90s | 42 tok/s | ||
| $0.04000 | $0.0700 | $0.007000 | -- | -- | ||
| $0.04000 | $0.0700 | $0.007000 | -- | -- | ||
Not used in Nitro routing:Why these endpoints are not used | ||||||
| $0.04000 | $0.3000 | $0.015000 | 0.45s | 164 tok/s | ||
Flex | $0.07750 | $0.2325 | $0.002325 | 0.69s | 150 tok/s | |
| $0.16$0.07840 | $0.48$0.2352 | $0.0048$0.002352 | 9.08s | 54 tok/s | ||
- Input $0.60 / Output $2.40455 tok/s100.00% uptimeFast
- Input $0.30 / Output $1.20185 tok/s100.00% uptime
- Input $0.30 / Output $1.20184 tok/s100.00% uptime
- Input $0.30 / Output $1.20179 tok/s95.73% uptime
- Input $0.60 / Output $2.40177 tok/s99.42% uptimeFast
Input $0.30 / Output $1.20173 tok/s99.94% uptime
Input $0.45 / Output $1.80173 tok/s100.00% uptime- Input $0.066 / Output $0.50167 tok/s100.00% uptime
- Input $0.036 / Output $0.50167 tok/s100.00% uptime
- Input $0.12 / Output $0.50162 tok/s99.97% uptime
- Input $0.18 / Output $0.72162 tok/s100.00% uptime
- Input $0.30 / Output $1.20162 tok/s99.95% uptime
Input $0.24 / Output $0.9620% off155 tok/s99.97% uptime- Input $0.18 / Output $0.7240% off154 tok/s99.80% uptime

Input $0.17 / Output $0.67152 tok/s100.00% uptime- Input $0.08 / Output $0.60151 tok/s99.49% uptime
- Input $0.09 / Output $1.20148 tok/s99.68% uptime
- Input $0.25 / Output $1.00143 tok/s100.00% uptime
Input $0.15 / Output $0.50136 tok/s99.95% uptime- Input $0.30 / Output $1.20135 tok/s100.00% uptime
- Input $0.105 / Output $0.4265% off132 tok/s99.92% uptime
- Input $0.29 / Output $1.20130 tok/s100.00% uptime
- Input $0.30 / Output $1.20125 tok/s100.00% uptime
- Input $0.09 / Output $0.36124 tok/s99.83% uptime
Input $0.15 / Output $0.60124 tok/s100.00% uptime- Input $0.08 / Output $0.605122 tok/s100.00% uptime
Input $0.24 / Output $0.96122 tok/s98.39% uptime- Input $0.12 / Output $0.48119 tok/s100.00% uptime
- Input $0.04368 / Output $0.70115 tok/s99.29% uptime
- Input $0.18 / Output $0.68113 tok/s99.21% uptime
- Input $0.08 / Output $0.605112 tok/s100.00% uptime
- Input $0.059 / Output $0.52110 tok/s99.70% uptime
- Input $0.10 / Output $0.60101 tok/s100.00% uptime
Input $0.147 / Output $0.44197 tok/s99.58% uptimePriority+11 more label- Input $0.12 / Output $0.4860% off94 tok/s99.90% uptime
- Input $0.21 / Output $0.6294 tok/s99.63% uptime
- Input $0.195 / Output $0.7890 tok/s100.00% uptime
Input $0.098 / Output $0.29451% off83 tok/s99.83% uptime- Input $0.12 / Output $0.4083 tok/s99.97% uptime
Input $0.21 / Output $0.8476 tok/s94.29% uptime- Input $0.09772 / Output $0.394465% off73 tok/s99.97% uptime
- Input $0.098 / Output $0.29467 tok/s99.49% uptime
- Input $0.30 / Output $0.5563 tok/s99.86% uptime
- Input $0.111 / Output $0.44463% off58 tok/s100.00% uptime
Input $0.30 / Output $1.2042 tok/s100.00% uptime- Input $0.04 / Output $0.07-- tok/s96.23% uptime
- Input $0.04 / Output $0.07-- tok/s91.40% uptime
- Not used in Nitro routing:Why these endpoints are not used
- Input $0.04 / Output $0.30164 tok/s99.15% uptimeFlex
- Input $0.0775 / Output $0.2325150 tok/s100.00% uptimeFlex
Input $0.0784 / Output $0.235254 tok/s76.67% 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
| $0.00505 | $0.6996 | 93.6% | 3.5% | ||
| $0.00719 | $1.1997 | 97.5% | 3.4% | ||
| $0.00723 | $0.4461 | 95.4% | 2.3% | ||
| $0.00873 | $0.5996 | 94.1% | 1.1% | ||
| $0.00878 | $0.4196 | 93.5% | 2.4% | ||
| $0.00891 | $0.5858 | 95.2% | 2.2% | ||
| $0.00908 | $0.3185 | 94.4% | 10.8% | ||
| $0.00926 | $0.7783 | 97.2% | 18.1% | ||
| $0.00967 | $0.5400 | 92.0% | 3.5% | ||
| $0.00977 | $0.7796 | 96.9% | 0.1% | ||
| $0.00979 | $0.4998 | 94.2% | 4.7% | ||
| $0.00982 | $0.4837 | 93.8% | 0.8% | ||
| $0.01179 | $0.4998 | 94.0% | 2.9% | ||
| $0.01239 | $0.4998 | 90.8% | 7.8% | ||
| $0.01269 | $0.4998 | 91.4% | 2.5% | ||
| $0.01273 | $0.4480 | 94.3% | 1.3% | ||
| $0.01373 | $0.7196 | 94.3% | 3.5% | ||
| $0.01396 | $0.6047 | 91.7% | 1.3% | ||
| $0.01439 | $0.6046 | 91.1% | 5.0% | ||
| $0.01439 | $0.2930 | 87.9% | 0.0% | ||
| $0.01632 | $0.4431 | 87.0% | 0.1% | ||
| $0.01943 | $0.6695 | 91.8% | 0.6% | ||
| $0.01980 | $1.1997 | 95.3% | 7.4% | ||
| $0.02193 | $1.0000 | 93.1% | 0.5% | ||
| $0.02257 | $0.6795 | 90.5% | 0.1% | ||
| $0.02390 | $1.1995 | 94.4% | 0.1% | ||
| $0.02422 | $1.1347 | 93.6% | 0.8% | ||
| $0.02474 | $0.7202 | 88.0% | 0.2% | ||
| $0.02700 | $0.9591 | 90.6% | 0.0% | ||
| $0.02868 | $0.8396 | 88.1% | 0.5% | ||
| $0.03026 | $1.1997 | 91.8% | 1.4% | ||
| $0.03055 | $0.6196 | 89.9% | 0.8% | ||
| $0.03095 | $1.1996 | 91.8% | 0.6% | ||
| $0.03212 | $1.1997 | 91.1% | 0.6% | ||
| $0.03351 | $1.7996 | 94.4% | 0.9% | ||
| $0.04330 | $1.1997 | 87.3% | 1.8% | ||
| $0.04343 | $0.5993 | 73.1% | 0.1% | ||
| $0.04481 | $0.3996 | 65.9% | 0.2% | ||
| $0.05614 | $1.1997 | 82.9% | 0.3% | ||
| $0.06888 | $1.1986 | 78.6% | 0.0% | ||
| $0.07786 | $0.8825 | 69.8% | 0.0% | ||
| $0.08650 | $1.1996 | 72.6% | 0.5% | ||
| $0.08733 | $0.5497 | 72.3% | 0.0% | ||
| $0.12116 | $2.3994 | 81.7% | 0.1% | ||
Fast | $0.12683 | $2.3994 | 80.7% | 0.3% | |
| $0.00943 | $0.0697 | 92.7% | 1.2% | ||
| $0.00990 | $0.0697 | 91.4% | 1.6% | ||
Not used in Nitro routing:Why these endpoints are not used | |||||
Flex | $0.00767 | $0.2321 | 92.9% | 0.3% | |
| $0.02457 | $0.2998 | 61.7% | 1.1% | ||
| $0.00530 | $0.2359 | 96.2% | 0.8% | ||
- Effective in $0.00505 / Effective out $0.6996Token share3.5%
- Effective in $0.00719 / Effective out $1.1997Token share3.4%
- Effective in $0.00723 / Effective out $0.4461Token share2.3%
- Effective in $0.00873 / Effective out $0.5996Token share1.1%
- Effective in $0.00878 / Effective out $0.4196Token share2.4%
- Effective in $0.00891 / Effective out $0.5858Token share2.2%
- Effective in $0.00908 / Effective out $0.3185Token share10.8%
- Effective in $0.00926 / Effective out $0.7783Token share18.1%
- Effective in $0.00967 / Effective out $0.5400Token share3.5%
- Effective in $0.00977 / Effective out $0.7796Token share0.1%
- Effective in $0.00979 / Effective out $0.4998Token share4.7%
- Effective in $0.00982 / Effective out $0.4837Token share0.8%
- Effective in $0.01179 / Effective out $0.4998Token share2.9%
- Effective in $0.01239 / Effective out $0.4998Token share7.8%
- Effective in $0.01269 / Effective out $0.4998Token share2.5%
- Effective in $0.01273 / Effective out $0.4480PriorityToken share1.3%
- Effective in $0.01373 / Effective out $0.7196Token share3.5%
- Effective in $0.01396 / Effective out $0.6047Token share1.3%
- Effective in $0.01439 / Effective out $0.6046Token share5.0%
- Effective in $0.01439 / Effective out $0.2930Token share0.0%
- Effective in $0.01632 / Effective out $0.4431Token share0.1%
- Effective in $0.01943 / Effective out $0.6695Token share0.6%
- Effective in $0.01980 / Effective out $1.1997Token share7.4%
- Effective in $0.02193 / Effective out $1.0000Token share0.5%
- Effective in $0.02257 / Effective out $0.6795Token share0.1%
- Effective in $0.02390 / Effective out $1.1995Token share0.1%
- Effective in $0.02422 / Effective out $1.1347Token share0.8%
- Effective in $0.02474 / Effective out $0.7202Token share0.2%
- Effective in $0.02700 / Effective out $0.9591Token share0.0%
- Effective in $0.02868 / Effective out $0.8396Token share0.5%
- Effective in $0.03026 / Effective out $1.1997Token share1.4%
- Effective in $0.03055 / Effective out $0.6196Token share0.8%
- Effective in $0.03095 / Effective out $1.1996Token share0.6%
- Effective in $0.03212 / Effective out $1.1997Token share0.6%
- Effective in $0.03351 / Effective out $1.7996Token share0.9%
- Effective in $0.04330 / Effective out $1.1997Token share1.8%
- Effective in $0.04343 / Effective out $0.5993Token share0.1%
- Effective in $0.04481 / Effective out $0.3996Token share0.2%
- Effective in $0.05614 / Effective out $1.1997Token share0.3%
- Effective in $0.06888 / Effective out $1.1986Token share0.0%
- Effective in $0.07786 / Effective out $0.8825Token share0.0%
- Effective in $0.08650 / Effective out $1.1996Token share0.5%
- Effective in $0.08733 / Effective out $0.5497Token share0.0%
- Effective in $0.12116 / Effective out $2.3994FastToken share0.1%
- Effective in $0.12683 / Effective out $2.3994FastToken share0.3%
- Effective in $0.00943 / Effective out $0.0697Token share1.2%
- Effective in $0.00990 / Effective out $0.0697Token share1.6%
- Not used in Nitro routing:Why these endpoints are not used
- Effective in $0.00767 / Effective out $0.2321FlexToken share0.3%
- Effective in $0.02457 / Effective out $0.2998FlexToken share1.1%
- Effective in $0.00530 / Effective out $0.2359FlexToken share0.8%
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 (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 $0.036/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.