DeepSeek V4.1 Flash Heretic Thinking
pqhaz's Heretic checkpoint of DeepSeek V4.1 Flash 1017, served by Sable at original mixed precision (FP8 dense/Engram and MXFP4 experts). Supports text and image input, tools, structured output, and optional reasoning. Separate from the DeAlign uncensored checkpoint.
- Reasoning
- Vision
- Tool Calling
Added Oct 31, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.198
- Output
- $0.792
- Cache read
- $0.0132
Specifications
- Context window
- 512K
- Max output
- 128K
Benchmarks
No public benchmark scores for this model yet.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| Cache write /M | ||||||
|---|---|---|---|---|---|---|
| $0.198 | $0.792 | $0.0132 | $0.198 | N/A | N/A | |
| $0.198 | $0.792 | $0.0132 | $0.198 | N/A | N/A | |
| $0.173 | $0.693 | $0.0115 | $0.173 | N/A | N/A |
Privacy:ZDR, prompts not retainedNo training on prompts
Batch API
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.