Deepseek V4.1 Flash
Deepseek
Designed for greater capability, faster inference, higher throughput, and scaling to larger models.
Token pricing and context
- Input
- $0.15 USD / 1M tokens
- Cached input
- $0.003 USD / 1M tokens
- Output
- $0.6 USD / 1M tokens
- Context window
- 1000000
Benchmark results
MM1.0
Overall score: 90.9 · Scale 0–100 · Higher is better
- Reasoning: 95
- Coding: 96
- Chat: 100
- Long Context: 94
- Vibe: 100
- Accuracy: 100
- General Knowledge: 37.5
Evaluated: 2026-10-18
Record exact model version, reasoning setting, temperature, tools, and evaluation setup.
Hallucimeter 1.0
Overall score: 20 · Scale 0–100 · Lower is better
- Hallucinations: 20
Evaluated: 2026-10-18
Record exact model version, reasoning setting, temperature, tools, and evaluation setup.
Updated 2026-10-18. Read benchmark methodology.