DeepSeek V4 Flash Vision Exp
by DeepSeek · deepseek/deepseek-v4-flash-vision-exp · #119 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:22 PM UTC · refreshed hourly
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.216
per 1M tokens
Output
$0.647
per 1M tokens
Blended (3:1)
$0.323
3 input : 1 output
Cache read
$0.0069
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for DeepSeek V4 Flash Vision Exp with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.323 | $0.0226 | — |
| 50% | $0.245 | $0.0122 | −46% |
| 90% | $0.183 | $0.003851 | −83% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000302 | $0.3018 |
| Document summary | 8,000 | 1,000 | $0.002372 | $2.37 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.007762 | $7.76 |
| Long-context analysis | 150,000 | 5,000 | $0.0356 | $35.57 |
Specs
Context window
1.05M
tokens
Max output
262K
tokens
Input modalities
text, image
Tokenizer
DeepSeek