BREAKING
DeepSeek cuts cached input price 90%
0
$/M
cache hit
0
$/M
cache miss
0
$/M
output
Why it matters for AI agents
1
Static system prompt
↓
2
Fixed tool definitions
↓
3
RAG context reused
↓
4
Served near-free
V4-Pro vs Grok 4.5 at scale
V4-Pro
63
Grok 4.5
757
The caveats behind the cuts
Upside
●
Blended near $0.18 per million
●
1M-token context window
Caveats
●
Surge pricing at peak hours
●
Poor prompts erode cache gains
Will rivals cut cache prices too?
AI NEWS BLITZ
DeepSeek has slashed cached input prices by roughly 90 percent, shaking up AI agent economics.