NotHoly Vector
Backing model, capabilities and customer rates from the published catalog.
Based on DeepSeek V4.1 Flash 1017 Abliterated
- Public API ID
notholy-vector- Context capacity
- 32,768 tokens
- Maximum output
- 4,096 tokens
- Capabilities
- streaming
Per million tokens
| Token type | API USD | Chat CU |
|---|---|---|
| Input | $0.66 | 66 |
| Cached input | $0.14 | 14 |
| Output | $2.25 | 225 |
Rate version retail-2026-10-30-v1. Cached input replaces ordinary input for that subset. Output may include billable reasoning; no hidden chain of thought is exposed.
Catalog identity
The NotHoly name is a stable product alias. The catalog identifies its backing model and current limits; NotHoly does not claim to have trained these weights.
Usage and availability
Input, cached input and output have distinct versioned rates. Cached input replaces ordinary input for that subset; it is never counted twice. A published capability belongs to this model, not automatically to every mode or client.