Uncensored · FP8 · Available
Uncensored · FP8 DeepSeek V4.1 Flash 1017 API
DeepSeek V4.1 Flash 1017. Available. Check the connected Router for current availability.
126,976 output tokens by default and maximum · 1,048,576-token shared context. 200 shared concurrent requests across two replicas. Account limits and available credit apply. Requests can queue within the 14-minute deadline.
Model facts
- Model ID
deepseek-v4.1-flash-1017-abliterated- Weights
- Uncensored · FP8
- Published rate snapshot
- $0.29 / $0.99USD per 1 million tokens · fresh input / outputCached input: $0.029 per 1M tokens
- Served precision
- FP8
- Access
- Verified account access. Live Router metadata supplies current readiness, supported features and immutable billing version.
- Status
- Available
The Router’s published price version governs billing.
Choose your model.
Check live availability in Chat or connect Codex and Hermes.
We work directly with model researchers and verify modified weights, commercial hosting rights, features and completed answers. Each served model’s identity stays explicit. We never substitute another model for your explicit choice.