DeepSeek V4 Flash Vision Exp
The 30th most-used model on the router over the last 7 days, with 0.45% of tokens. Weekly share peaked at 0.39% in the week of Aug 31, 2026, with 0.66T tokens processed since Aug 17, 2026.
- Launch
- Aug 21, 2026
- Context
- 1M tokens
- Modality
- text and image → text
- Reasoning
- yes
- License
- Open weights
- Input
- $0.22 / 1M
- Output
- $0.66 / 1M
Weekly token share
Share of the router's weekly volume, since the first week with volume
See the numbers
| Week | Share |
|---|---|
| Aug 31, 2026 | 0.394% |
| Aug 24, 2026 | 0.159% |
| Aug 17, 2026 | 0.031% |
Debuted in the week of Aug 17, 2026 and peaked at 0.39% 2 weeks later. The latest full week is the peak so far. Over the last 7 days, which already reach into the current week, it stands at 0.45%, above the weekly peak.
What this model is used for new
Tasks where the model ranks among the leaders, and its share of each
This model is not among the leaders in any of the 29 tasks classified in the Sep 10, 2026 snapshot. That does not mean it goes unused: the source lists only the largest models in each task.
Snapshot of the rolling 7-day window through Sep 10, 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 |
|---|---|---|---|---|---|
| DeepInfra | $0.216 | $0.647 | 1M | fp8 | yes |
| Fireworks | $0.22 | $0.66 | 1M | not reported | yes |
| GMICloud | $0.44 | $1.32 | 1M | fp8 | no |
| SiliconFlow | $0.44 | $1.32 | 1M | fp8 | yes |
| AtlasCloud | $0.44 | $1.32 | 1M | fp8 | no |
| Novita | $0.44 | $1.32 | 1M | not reported | yes |
6 endpoints across 6 providers, with input from $0.216 to $0.44 per 1M tokens. 4 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 88.2%
$0.023 per task, 396 tasks. 22nd of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.
τ-bench verified, airline 74.0%
$0.031 per task, 50 tasks. 38th of 122 evaluated. Median of evaluated models: 70.7%, $0.056 per task.
Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 11, 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-5.6 LunaOpenAI | OpenAI | 11.5% | $0.45 | 1M | 37.5 | 6 |
| Gemini 3.8 FlashGoogle | 2.1% | $1.50 | 1M | 41.2 | 0 | |
| Muse Spark 1.3 ContributorMeta | Meta | 1.5% | $0.125 | 1M | — | 0 |
| Claude Opus 5Anthropic | Anthropic | 1.4% | $10.00 | 1M | 50.7 | 1 |
| GPT-5.6 SolOpenAI | OpenAI | 1.4% | $4.00 | 1M | 47.1 | 0 |
| Open weights | ||||||
| Hy4 previewTencent | Tencent | 15.5% | $1.25 | 1M | — | 1 |
| DeepSeek V4 Flash 0731DeepSeek | DeepSeek | 10.0% | $0.094 | 1.31M | 34.5 | 5 |
| GLM 5.3 FlashZ.ai (GLM) | Z.ai (GLM) | 10.0% | $0.237 | 1.31M | 41.9 | 2 |
| MiMo-V2.5Xiaomi | Xiaomi | 4.2% | $0.175 | 1M | 22.3 | 15 |
| DeepSeek V4 Flash 0423DeepSeek | DeepSeek | 3.9% | $0.111 | 1M | 24.8 | 19 |
| DeepSeek V4 Flash Vision Expthis pageDeepSeek | DeepSeek | 0.45% | $0.33 | 1M | — | 0 |
Share over the last 7 days (Sep 4, 2026 to Sep 10, 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.