Explore more Chat models
Latest and popular AI models
README
Complete guide to using deepseek-v4-1-flash
DeepSeek-V4.1-Flash is a multimodal model designed for faster inference, higher throughput, and stronger performance across reasoning, coding, visual understanding, and agentic tasks. Its architecture improves efficiency while preserving the capabilities needed for complex, multi-step workloads.
| Option / usage | Provider list price | Our reference price |
|---|---|---|
| Off-peak ceiling · Input | $0.15 | $0.1125 |
| Off-peak ceiling · Output | $0.6 | $0.45 |
| Off-peak ceiling · Cache read | $0.003 | $0.00225 |
Off-peak official ceiling; the same lower quote remains below peak rates
Trials are not enabled on this page. Paid use follows the confirmed billing quote.
Provider pricing source · 2026-10-03Complete guide to using deepseek-v4-1-flash