DeepSeekOpen weights: deepseek-ai/DeepSeek-V4.1-Flash-1017Reasoning modelNewReleased 17 Oct 2026Compare with another modelDeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is a DeepSeek open-weights reasoning model, released 17 Oct 2026. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $0.300 per million tokens blended it is cheaper than most ranked models. Output speed of 51 tokens per second puts it slower than most, with a first token in 0.9 s.
- Blended price
- $0.300/M
- $0.200 in · $0.600 out
- Output speed
- 51 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.92 s
- Context
- 1.0M
- Full answer
- –
- Cost per run
- –
- Released
- 17 Oct 2026
Versions
DeepSeek has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| NewDeepSeek V4.1 Flash 1017this page | 17 Oct 2026 | – | – |
| DeepSeek V4.1 Flashmax | 10 Sept 2026 | 61.7 | #83 |
No independent quality benchmark results yet — only pricing and metadata.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Baseten | 253 tok/s | 0.31 s | $0.300 | $1.20 | 1.0M | – |
| inference.net | 158 tok/s | 0.42 s | $0.080 | $0.500 | 262k | fp8 |
| Relace | 154 tok/s | 1.18 s | $0.200 | $0.600 | 1.0M | – |
| Cloudflare | 145 tok/s | 0.96 s | $0.100 | $0.600 | 1.0M | – |
| Parasail | 140 tok/s | 0.94 s | $0.300 | $1.20 | 1.0M | fp8 |
| DeepInfra | 123 tok/s | 0.43 s | $0.098 | $0.294 | 1.0M | fp8 |
| DeepInfra | 114 tok/s | 1.46 s | $0.147 | $0.441 | 1.0M | fp8 |
| Morph | 101 tok/s | 0.49 s | $0.090 | $0.550 | 1.0M | fp8 |
| DeepSeek | 49 tok/s | 0.93 s | $0.150 | $0.600 | 1.0M | – |
| DeepInfra | 46 tok/s | 9.07 s | $0.078 | $0.235 | 1.0M | fp8 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.006 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0003 | $0.0002 | 6.9 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0028 | $0.0010 | 12.8 s |
| Code edit | 6,000 / 1,500 | $0.0021 | $0.0012 | 30.6 s |
| Agentic coding session | 60,000 / 4,000 | $0.014 | $0.0057 | 1.3 min |
| Structured extraction | 2,000 / 200 | $0.0005 | $0.0002 | 4.9 s |
More from DeepSeek
See also
Data as of 18 Oct 2026. Compare with another model.
Cite as: BenchLeader, “DeepSeek V4.1 Flash 1017: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/deepseek-v4-1-flash-1017, data as of 18 Oct 2026.