AI
Overview
About this model
DeepSeek V4.1 Flash uses a sparse MoE Causal Encoder-Decoder architecture with 552B total parameters, activating 8B during input processing and 16B during output generation. It natively understands text and images and targets coding, computer-use agents, and long-running tasks. Its context window is 1,048,576 tokens; output limits depend on the serving provider.
- Context window
- 1048576
- Category
- -
- Last updated
- 2026-10-03
- Providers
- -
Performance
Usage and availability
Last 14 days
Requests over timeDaily volume
Availability over timeDaily success rate
Cache hit rateDaily cache reads
API endpoints
Supported parameters
Availability
Providers
-
| Provider | Route | Pricing | Cache hit | TTFT | Output speed (TPS) | Availability |
|---|
Provider performanceAll active provider routes
API access
Request example
Choose a protocol and copy a ready-to-run request.
POST/v1/responses