HyperFlowAll models
Released: Sep 1, 2026
DeepSeek
DeepSeek V4.1 Flash
Modalities
deepseek/deepseek-flashDeepSeek's latest model, surpassing V4 Pro across performance, cost, speed, and task completion. Native multimodal support with 1M context window. Routed via Surplus Intelligence.
Context
1M tokens
Input / 1M
$0.24
Output / 1M
$0.96
Cache read / 1M
$0.006
Offers
1 seller
Surplus Intelligence
Offer / 1M
$0.96
Discount
—
Latency
—
Seller | Offer / 1M | Discount | Latency |
|---|---|---|---|
| Surplus Intelligence | $0.96 | — | — |
Usage · 30D
Oct 6
Nov 4
Get started
Chat completion
curl https://super.hyperflow.fun/v1/chat/completions \
-H "Authorization: Bearer $HYPERFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-flash",
"messages": [{ "role": "user", "content": "Hello!" }]
}'
