Sovereign inference — DeepSeek V4.1 Flash
Your sovereign, private DeepSeek V4.1 Flash
A reasoning model in the medium tier, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in Units of Intelligence at the published rates below. No training on your data, no vendor lock-in.
AU · EU · US resident0.43 UoI/1M input1.51 UoI/1M output0.01 UoI/1M cached input1049K context
How DeepSeek V4.1 Flash compares
Independent intelligence index for DeepSeek V4.1 Flash against every peer in the Medium tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Capability indexes
Domain-weighted agentic performance for DeepSeek V4.1 Flash.
Capability index vs medium peers
Finance & AccountingStrategy & OpsLegalHealthcare & MedicalEngineeringEconomics
The evaluations behind the index
Independent benchmark results for DeepSeek V4.1 Flash — Elo scores as published; pass rates shown as percentages.
Per-evaluation economics
| Evaluation | Score | Time / task | Output tokens / task |
|---|---|---|---|
| AA-Briefcase | 1431.79 | 9.1 min | 170690 |
| GDPval-AA | 1600.00 | 6.2 min | 116108 |
| AutomationBench-AA | 68.9% | 4.6 min | 87009 |
| Terminal-Bench 4.0 | 26.8% | 15.2 min | 285252 |
| SciCode | 51.9% | 0.5 min | 9753 |
| Humanity's Last Exam | 39.2% | 1.8 min | 34685 |
| GDP.pdf | 12.8% | 0.8 min | 15040 |
| CritPt | 14.3% | 5.9 min | 111624 |
| AA-Omniscience | -530.0% | 0.4 min | 8127 |
| AA-LCR (long context) | 84.0% | 0.2 min | 3097 |
Run DeepSeek V4.1 Flash privately
One key, one endpoint, three jurisdictions.
- Size tierMedium
- Input rate0.43 UoI/1M
- Output rate1.51 UoI/1M
- Cached input rate0.01 UoI/1M
- Context window1049K tokens
- Max output16K tokens
- ReasoningYes — emits thinking traces
- Vision & video inputSupports image input
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call
Copyright 2026 ToothFairyAI PTY LTD. All Rights Reserved.
