DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
What published route metadata supports
Only source-backed fields are filled
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | deepseek/deepseek-v4.1-flash | $0.045 | $0.006 | $0.5 | 1.05M | OpenRouter API ↗ |
| OpenRouterBatch | deepseek/deepseek-v4.1-flash:batch | $0.05 | $0.004 | $0.15 | 1.05M | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
32 verified price changes since Aug 26, 2026
2 route availability changes recorded. No earlier prices are inferred.
- Oct 29, 2026OpenRouter · Standard
Input $0.14 → $0.045 · Cached input $0.0042 → $0.006 · Output $0.42 → $0.5
- Oct 27, 2026OpenRouter · Standard
Input $0.02 → $0.14 · Cached input $0.015 → $0.0042 · Output $1 → $0.42
- Oct 24, 2026OpenRouter · Standard
Input $0.056 → $0.02 · Cached input $0.0016 → $0.015 · Output $0.12 → $1
- Oct 20, 2026OpenRouter · Standard
Input $0.0344 → $0.056 · Output $0.08 → $0.12
- Oct 19, 2026OpenRouter · Standard
Input $0.04 → $0.0344 · Output $0.144 → $0.08
- Oct 18, 2026OpenRouter · Standard
Input $0.15 → $0.04 · Cached input $0.003 → $0.0016 · Output $0.6 → $0.144