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 |
|---|---|---|---|---|---|---|
| OpenRouterBatch | deepseek/deepseek-v4.1-flash:batch | $0.05 | $0.004 | $0.15 | 1.05M | OpenRouter API ↗ |
| OpenRouterStandard | deepseek/deepseek-v4.1-flash | $0.3 | $0.006 | $1.2 | 1.05M | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
44 verified price changes since Aug 26, 2026
2 route availability changes recorded. No earlier prices are inferred.
- Nov 20, 2026OpenRouter · Standard
Input $0.0507 → $0.3 · Cached input $0.001014 → $0.006 · Output $0.2028 → $1.2
- Nov 20, 2026OpenRouter · Batch
Input $0.112 → $0.05 · Cached input $0.00336 → $0.004 · Output $0.336 → $0.15
- Nov 18, 2026OpenRouter · Standard
Input $0.3 → $0.0507 · Cached input $0.006 → $0.001014 · Output $1.2 → $0.2028
- Nov 17, 2026OpenRouter · Standard
Input $0.14 → $0.3 · Cached input $0.0042 → $0.006 · Output $0.42 → $1.2
- Nov 16, 2026OpenRouter · Standard
Input $0.0507 → $0.14 · Cached input $0.001014 → $0.0042 · Output $0.2028 → $0.42
- Nov 14, 2026OpenRouter · Standard
Input $0.3 → $0.0507 · Cached input $0.006 → $0.001014 · Output $1.2 → $0.2028