DeepSeek V4 Flash Vision ExpOpen weights
DeepSeek · released 2026-08-21
No price from the maker itself is on record for DeepSeek V4 Flash Vision Exp. The lowest of 15 providers is CommandCode: $0.15 per 1M input tokens and $0.6 per 1M output tokens (as of 2026-11-12). Context window: 1M tokens, up to 384K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 CommandCodeLowestdeepseek/ | $0.15 | $0.6 | $0.003 | Lowest | Official docs |
EEden AIdeepseek-v4-flash-vision-exp | $0.15 | $0.6 | $0.003 | Official docs | |
EEden AIdeepseek/ | $0.15 | $0.6 | $0.003 | Official docs | |
NNanoGPTdeepseek/ | $0.2156 | $0.6468 | $0.00686 | Official docs | |
 Vercel AI Gatewaydeepseek/ | $0.2156 | $0.6468 | $0.0068 | Official docs | |
OOrcaRouterdeepseek/ | $0.22 | $0.66 | $0.007 | Official docs | |
 AI/ML APIdeepseek/ | $0.44 | $1.32 | $0.014 | Official docs | |
 Deep Infradeepseek-ai/ | $0.44 | $1.32 | $0.014 | Official docs | |
 Hugging Facedeepseek-ai/ | $0.44 | $1.32 | — | Official docs | |
KKilo Gatewaydeepseek/ | $0.44 | $1.32 | $0.014 | Official docs | |
 OpenRouterdeepseek/ | $0.44 | $1.32 | $0.014 | Official docs | |
 SiliconFlowdeepseek-ai/ | $0.44 | $1.32 | $0.028 | Official docs |
4 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 OpenCodeDeprecateddeepseek-v4-flash-vision-exp | $0.14 | $0.28 | $0.028 | Deprecated | Official docs |
 AIHubMixDeprecateddeepseek-v4-flash-vision-exp | $0.155 | $0.62 | $0.0031 | Deprecated | Official docs |
CCrossModelDeprecateddeepseek/ | $0.3 | $1.2 | $0.006 | Deprecated | Official docs |
AAMDDeprecatedDeepSeek-V4-Flash-Vision-Exp | $0 | $0 | $0 | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
Description from models.dev.
Specs
- Type
- Text
- Context
- 1M
- Max output
- 384K
- Input
- Text, Image
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- Yes
- Released
- 2026-08-21
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.