DeepSeek V4.1 Flash
deepseek/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...
Modalities
Text
Image
In / Out price
$0.15 / $0.60 per 1M
Context
1.05M · 384K out
Released
Sep 10, 2026
Providers
Live list prices and uptime across 22 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| Morph | $0.12 | $0.48 | $0.004 | 1.05M | 944K | 98.43% |
| Relacefp4 | $0.13 | $0.52 | $0.01 | 1.05M | 944K | 99.70% |
| DeepInfrafp8 | $0.14 | $0.42 | $0.004 | 1.05M | 131K | 99.79% |
| Alibaba | $0.15 | $0.60 | $0.015 | 1M | 393K | 99.90% |
| DeepSeek | $0.15 | $0.60 | $0.003 | 1.05M | 384K | 100.00% |
| Sail Researchfp4 | $0.20 | $0.60 | $0.04 | 1.05M | 384K | 99.96% |
| Wafer | $0.20 | $0.60 | $0.006 | 1.05M | 944K | 99.83% |
| StreamLakefp8 | $0.22 | $0.879 | $0.004 | 1.02M | 384K | 99.14% |
| Fireworks | $0.22 | $0.66 | $0.007 | 1.05M | 944K | 99.90% |
| Phala | $0.276 | $1.104 | $0.006 | 1.05M | 393K | 99.12% |
| GMICloudfp8 | $0.285 | $1.14 | $0.006 | 1.05M | 944K | 99.35% |
| Novitafp8 | $0.285 | $1.14 | $0.006 | 1.05M | 393K | 99.99% |
| AtlasCloudfp8 | $0.30 | $1.20 | $0.03 | 1.05M | 393K | 99.11% |
| BaseTenfp8 | $0.30 | $1.20 | $0.03 | 1.05M | 33K | 98.15% |
| Makora | $0.30 | $1.20 | $0.006 | 1.05M | 393K | 98.75% |
| DigitalOcean | $0.30 | $1.20 | $0.006 | 1.05M | 944K | 99.02% |
| Together | $0.30 | $1.20 | $0.006 | 1.05M | 944K | 99.89% |
| SiliconFlowfp8 | $0.30 | $1.20 | $0.006 | 1.05M | 393K | 99.44% |
| Modal | $0.30 | $1.20 | $0.03 | 1.05M | 944K | 99.95% |
| BaseTenfp8 | $0.30 | $1.20 | $0.03 | 1.05M | 33K | 98.20% |
| Parasailfp8 | $0.30 | $1.20 | $0.006 | 1.05M | 944K | 91.74% |
| Venicefp8 | $0.375 | $1.50 | $0.007 | 1M | 131K | 99.22% |
Implicit prompt caching available — repeated context bills at the cache read rate.
Capabilities
Tool calling
Reasoning
Frequency penalty
Include reasoning
Logit bias
Logprobs
Max tokens
Min p
Presence penalty
Reasoning effort
Repetition penalty
Response format
Seed
Stop
Structured outputs
Temperature
Tool choice
Top K
Top logprobs
Top P
Pricing detail
- Input
- $0.15
- Output
- $0.60
- Cache read
- $0.003
- Cache write
- —
USD per 1M tokens.