DeepSeek’s officially released new multimodal visual-understanding model, DeepSeek‑V4‑Flash‑Vision‑Exp, is experimental in nature and supports multimodal inputs. In pure-text capabilities (agents, reasoning, world knowledge, etc.), DeepSeek‑V4‑Flash‑Vision‑Exp is on par with the official DeepSeek‑V4‑Flash release.
Pricing
Input Modalities
- Text
- Vision
Output Modalities
- Text
Capabilities
- Thinking
- Tools
- Tool calling
- Structured outputs
Providers
DeepSeek deep-deepseek-v4-flash-vision-exp
Pricing$0.142$0.284
Web Search$0.00056/request
Cache Read$0.0284/M tokens
Context1M
Max output384K
Latency2.5S
Throughput68.9TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
100.00% uptime today
Performance for deepseek-v4-flash-vision-exp
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Uptime
Loading...
Latency
Loading...
Throughput
Loading...
Try this model
Python
