D
Deckard 40B
deckard-40b
Dense 40B model expanded from Qwen3.6-27B architecture with 96 layers. Deep thinking and uncensored reasoning capabilities.
Show more ↓
Modalities
Text→Text
In / Out Price
$3.00 / $9.00 per 1M
Context
16K
Size Tier
Flagship (40B)
Providers
This model is hosted by the Unces infrastructure. We forward every request directly to our self-hosted GPU cluster endpoints.
| Provider | Input /M | Output /M | Cache Read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| Unces Self-Host | $3.00 | $9.00 | $0.00 | 0.14s | 48 tps | 100.0% |
Effective Pricing
The chart below shows the average price customers pay. Standard rate structures are optimized for flat usage caps.
Weighted Avg Input Price$3.00
Weighted Avg Output Price$9.00