DeepSeek V4 Flash Vision Exp
DeepSeekKey deepseek-v4-flash-vision-expAlso reported as opencode-go/deepseek-v4-flash-vision-exp, deepseek-ai/deepseek-v4-flash-vision-exp, deepseek/deepseek-v4-flash-vision-exp, bai/deepseek-v4-flash-vision-exp, ocg/deepseek-v4-flash-vision-exp, b.ai/deepseek-v4-flash-vision-exp, self-dploy/deepseek-v4-flash-vision-exp
- Rank
- #199
- by active users
- Active users
- 1
- Down 1 from 2 active users in the previous 7 days. vs previous 7 days
- Adoption
- 0.2%
- of 613 accounts
- Tokens
- 108.1M
- cache included
- Est. cost
- $1
- at public list prices
- First seen
- Jul 14, 2026
- in any submission
Nov 7–13, 2026 (UTC)613 accounts100% of tokens from an identified modelData through Nov 13, 2026, 07:16 UTCHow we count
Daily active users
Distinct accounts that used this model on each UTC day.
0 active users on Nov 13, 2026
Show daily values
| Date (UTC) | Active users | Tokens |
|---|---|---|
| Nov 7, 2026 | 0 | 0 |
| Nov 8, 2026 | 1 | 5.1M |
| Nov 9, 2026 | 0 | 0 |
| Nov 10, 2026 | 0 | 0 |
| Nov 11, 2026 | 1 | 102.9M |
| Nov 12, 2026 | 0 | 0 |
| Nov 13, 2026 | 0 | 0 |
Token mix
How the 108.1M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.
- Input1.2%
- Output<0.1%
- Cache read99%
- Cache write0%
- Reasoning0%
Agents that carry DeepSeek V4 Flash Vision Exp
Each agent's share of this model's tokens, and how many accounts used the model through it.
Oh My Pi100% of this model's tokens1active users
Benchmarks
The best result for DeepSeek V4 Flash Vision Exp in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.
No benchmark that Tokscale tracks has a result for DeepSeek V4 Flash Vision Exp yet.
Pricing
List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. OpenRouter is the reference price for the estimates below. It is the first provider listed; models.dev lists no price from the lab's own API.
Price at real agent usageEstimate at list prices
What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.
- At this model's mix
- $0.02
- Est. per 1M tokens
99% cache reads - At the community mix
- $0.03
- Est. per 1M tokens
96% cache reads - 3:1 input/output blend
- $0.66
- Per 1M tokens at list prices
No cache
Cache reads were 99% of DeepSeek V4 Flash Vision Exp tokens in the last 7 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.
Assumptions
- OpenRouter list prices per 1M tokens: input $0.44, output $1.32, cache read $0.01.
- This model's mix is its own input, output, cache and reasoning tokens in the last 7 days.
- The community mix is the tokens of every identified model in the last 7 days.
- This is an estimate at list prices, not what anyone paid.
- Reasoning tokens are priced as output.
- Long-context tiers, batch pricing and discounts are not applied.
- Token mixes come from public Tokscale submissions. Hidden accounts are excluded.
- No cache-write price is listed, so cache writes are priced as input.
List prices by provider
- OpenRouterReference
deepseek/deepseek-v4-flash-vision-exp$0.44 input per 1M tokens$1.32 output per 1M tokens$0.01 cache read per 1M tokensCache write not listed1.05M tokens of context - Vercel AI Gateway
deepseek/deepseek-v4-flash-vision-exp$0.22 input per 1M tokens$0.65 output per 1M tokens$0.007 cache read per 1M tokensCache write not listed1.05M tokens of context - Deep Infra
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp$0.44 input per 1M tokens$1.32 output per 1M tokens$0.01 cache read per 1M tokensCache write not listed1.05M tokens of context
Specs
From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.
- Context window
- 1.05M tokens
- Max output
- 944K tokens
- Input
- Text, Image
- Output
- Text
- Knowledge cutoff
- — not listed
- Release date
- Aug 21, 2026
- Open weights
- Yes
- Reasoning
- Yes
- Tool calling
- Yes
Top public profiles
Public profiles that used DeepSeek V4 Flash Vision Exp most in this period, by tokens. Hidden accounts are never listed.
- 1
Brad Lishman@bradlishman108.1Mtokens$1est. cost2active days$1 est. cost · 2 active days
More from DeepSeek
Other DeepSeek models in the same period, by active users.
- DeepSeek V4.1 Flash15% adoption94active users
- DeepSeek Flash6.2% adoption38active users
- DeepSeek V4.1 Flash Free5.5% adoption34active users
- DeepSeek V4.1 Flash 10174.9% adoption30active users
- DeepSeek V4 Pro1.5% adoption9active users
- DeepSeek V4 Flash1.3% adoption8active users
Sources and attribution
Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.