All models
DeepSeek V4 Flash
Best value1,000,000 tokens of context
DeepSeek V4 Flash is a fast, cheap DeepSeek model for high-volume text tasks. 1M context, tool calling, optional thinking.
Provider
WellFlow Premium
Provider model
deepseek-v4-flash
Pricing
per 1M tokens
Input
Wellflow price: $0.02provider price: $0.22
Output
provider price: $0.66Wellflow price: $0.06
Savings
91%
Prompt caching
The repeated part of a request (system prompt, documents, chat history) is stored in the cache. Reading it back costs less than regular input.
- Cache read
- Wellflow price: $0.02
- Cache write
- Wellflow price: $0.02
Performance
Availability and speed of the model through Wellflow.
Uptime
OperationalPartial outageOutage
Cursor
Claude Code
VS Code
Codex