DeepSeek V4 Flash
DeepSeek
deepseek-v4-flash284B MoE. 1M context. Fast + cheap V4 tier.
Best for: General, coding, long context, value
At a glance
Context window
1M
Input
$0.19/1M
$0.02/1M cached
Output
$0.38/1M
Speed
fast
Quality tier
strong
Per 1M tokens. All-in pricing, no hidden fees.
Capabilities
Tool calling
Connect to external tools and APIs
Reasoning
Extended thinking for complex problems
Prompt caching
Cache repeated prefixes for 90% discount
Streaming
Real-time token-by-token output
Structured outputs
JSON mode and function calling
Quick start
Get API Keycurl https://kymaapi.com/v1/chat/completions \
-H "Authorization: Bearer $KYMA_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'Details
CreatorDeepSeek
Model IDdeepseek-v4-flash
Quality tierstrong
Cost tiercheap
Input modalityText
Output modalityText
Prompt cachingSupported
Try DeepSeek V4 Flash now
$0.50 free credits on signup. No credit card required.