DeepSeek V4.1 Flash
The 2nd most-used model on the router over the last 7 days, with 9.6% of tokens. Weekly share peaked at 23.8% in the week of Oct 5, 2026, with 158T tokens processed since Sep 7, 2026.
- Launch
- Sep 10, 2026
- Context
- 1M tokens
- Modality
- text and image → text
- Reasoning
- yes
- License
- Open weights
- Input
- $0.02 / 1M
- Output
- $1.00 / 1M
Weekly token share
Share of the router's weekly volume, since the first week with volume
See the numbers
| Week | Share |
|---|---|
| Oct 19, 2026 | 9.570% |
| Oct 12, 2026 | 20.014% |
| Oct 5, 2026 | 23.843% |
| Sep 28, 2026 | 15.441% |
| Sep 21, 2026 | 13.422% |
| Sep 14, 2026 | 12.234% |
| Sep 7, 2026 | 3.895% |
Debuted in the week of Sep 7, 2026 and peaked at 23.8% 4 weeks later. The latest full week came in at 9.6%, 40% of peak.
What this model is used for new
Tasks where the model ranks among the leaders, and its share of each
Plus 17 more tasks with a smaller share.
Ranks among the leaders in 29 of the 29 classified tasks. Its largest share is in DevOps, 17.4% of the task's tokens; in the heaviest task where it appears, workflow execution (22.9% of classified volume), it holds 10.2%.
Snapshot of the rolling 7-day window through Oct 25, 2026. Share: the model's tokens in the task over the task's total tokens. Weight: the task's share of classified volume.
Where to run it
Endpoints in the source's catalog, from cheapest to most expensive on input
| Provider | Input | Output | Context | Quantization | Zero retention |
|---|---|---|---|---|---|
| OpenInference | $0.02 | $1.00 | 1M | fp4 | yes |
| Relace | $0.07 | $0.50 | 1M | not reported | yes |
| Decart | $0.09 | $0.18 | 1M | fp4 | yes |
| Sail Research | $0.09 | $0.25 | 1M | fp4 | yes |
| Sail Research | $0.09 | $0.25 | 1M | fp4 | yes |
| Morph | $0.098 | $0.80 | 1M | fp8 | yes |
| InferenceNet | $0.103 | $0.645 | 1M | fp8 | yes |
| InferenceNet | $0.103 | $0.645 | 1M | fp8 | yes |
| Reka | $0.105 | $0.84 | 1M | not reported | yes |
| DeepInfra | $0.112 | $0.336 | 1M | fp8 | yes |
| AtlasCloud | $0.135 | $0.54 | 1M | fp8 | no |
| Baidu | $0.14 | $0.559 | 1M | fp8 | no |
| DeepInfra | $0.14 | $0.42 | 1M | fp8 | yes |
| StreamLake | $0.147 | $0.588 | 1.02M | fp8 | no |
| CoreWeave | $0.15 | $0.65 | 1M | fp8 | yes |
| DigitalOcean | $0.165 | $0.66 | 1M | not reported | yes |
| Alibaba | $0.165 | $0.66 | 1M | not reported | no |
| ModelRun | $0.17 | $0.67 | 1M | fp4 | yes |
| GMICloud | $0.18 | $0.72 | 1M | fp8 | no |
| Wafer | $0.19 | $0.65 | 1M | mxfp4 | yes |
| Novita | $0.195 | $0.78 | 1M | fp8 | yes |
| Mancer 2 | $0.20 | $1.00 | 1M | fp8 | yes |
| DeepInfra | $0.21 | $0.63 | 1M | fp8 | yes |
| Fireworks | $0.21 | $0.84 | 1M | not reported | yes |
| Phala | $0.21 | $0.84 | 1M | not reported | yes |
| Makora | $0.26 | $1.17 | 1M | fp8 | yes |
| Crusoe | $0.29 | $1.20 | 1M | fp8 | yes |
| $0.30 | $1.20 | 1M | not reported | yes | |
| Nebius | $0.30 | $1.20 | 1M | fp8 | yes |
| PrimeIntellect | $0.30 | $1.20 | 1M | not reported | yes |
| Cohere | $0.30 | $1.20 | 1M | not reported | yes |
| BaseTen | $0.30 | $1.20 | 1M | not reported | yes |
| Together | $0.30 | $1.20 | 1M | not reported | yes |
| SiliconFlow | $0.30 | $1.20 | 1M | fp8 | yes |
| Modal | $0.30 | $1.20 | 1M | not reported | yes |
| BaseTen | $0.30 | $1.20 | 1M | not reported | yes |
| Parasail | $0.30 | $1.20 | 1M | fp8 | yes |
| Fireworks | $0.30 | $1.20 | 1M | not reported | yes |
| Venice | $0.30 | $1.20 | 1M | fp8 | yes |
| Fireworks | $0.45 | $1.80 | 1M | not reported | yes |
| BaseTen | $0.60 | $2.40 | 1M | not reported | yes |
41 endpoints across 33 providers, with input from $0.02 to $0.60 per 1M tokens. 36 offer zero data retention.
Prices in US dollars per million tokens, from the latest archived endpoint catalog.
Benchmarks
Artificial Analysis indexes and benchmarks run by the source, with cost per task
GPQA Diamond 89.2%
$0.024 per task, 1188 tasks. 39th of 169 evaluated. Median of evaluated models: 83.4%, $0.025 per task.
τ-bench verified, airline 75.8%
$0.034 per task, 300 tasks. 24th of 150 evaluated. Median of evaluated models: 71.2%, $0.064 per task.
Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Oct 26, 2026. The gray mark is the median of evaluated models.
Against the week's largest models
The five largest proprietary and five largest open-weights models over the last 7 days
| Model | Lab | 7-day share | Blended price | Context | Intelligence | Weeks in top 10 |
|---|---|---|---|---|---|---|
| Proprietary | ||||||
| GPT-6 LunaOpenAI | OpenAI | 4.4% | $0.20 | 1M | 38.1 | 5 |
| Claude Opus 5.5Anthropic | Anthropic | 4.4% | $8.00 | 1M | 57.6 | 3 |
| jev-1.13Typesafe | Typesafe | 1.6% | — | — | — | 0 |
| GPT-6.1 SolOpenAI | OpenAI | 1.5% | $4.00 | 1M | 51.8 | 0 |
| Muse Spark 1.3 ContributorMeta | Meta | 1.5% | $0.125 | 1M | — | 0 |
| Open weights | ||||||
| DeepSeek V4.1 Flash 1017DeepSeek | DeepSeek | 17.9% | $0.263 | 1M | 39.5 | 1 |
| DeepSeek V4.1 Flashthis pageDeepSeek | DeepSeek | 9.6% | $0.265 | 1M | 24.7 | 7 |
| MiniMax M3.1 FlashMiniMax | MiniMax | 7.7% | $0.263 | 1M | 42.7 | 1 |
| GLM 5.3 FlashZ.ai (GLM) | Z.ai (GLM) | 7.0% | $0.237 | 1M | 41.8 | 9 |
| Hy4 previewTencent | Tencent | 4.8% | $1.25 | 1M | — | 8 |
Share over the last 7 days (Oct 19, 2026 to Oct 25, 2026). Blended price in US dollars per million tokens, weighted 75% input and 25% output. A dash means the number is not published, not zero.