Model catalogDeepSeek
DeepSeek V4.1 Flash
DeepSeek's newest Flash — frontier coding and agentic work at 1M context. Served with vLLM behind your own private, OpenAI-compatible /v1 endpoint — billed by the second, terminate anytime.
552B MoE · 8–16B act · MXFP4 · 1M context · 8× 96 GB · per-second billing
01Specifications
The specs the launcher enforces.
Architecture, served precision, max context, the minimum GPU shape, and the exact pinned weights — the facts that decide how DeepSeek V4.1 Flash runs and what it costs.
| Spec | Value |
|---|---|
| Architecture | 552B MoE · 8–16B act |
| Served precision | MXFP4 |
| Max context | 1M |
| Minimum GPU shape | 8× 96 GB |
| Weights served | deepseek-ai/DeepSeek-V4.1-Flash@dba1be0 |
Runs on 8× 96 GB · billed per second — final cost depends on the GPU shape.
Full pricing →02How it runs
A private endpoint, not a shared API.
Launching DeepSeek V4.1 Flash runs the model on your own instance and gives you a private, OpenAI-compatible /v1 endpoint and API key. Point any OpenAI-compatible SDK at your base URL, change the model name, and existing code works. The endpoint is yours alone — terminate the instance and it goes away with it.
Billing is by the second on the 8× 96 GB shape the launcher enforces, from boot to terminate. No commitment and no tier gates.
03Get started
Launch DeepSeek V4.1 Flash now.
One private OpenAI-compatible endpoint, one key, billed by the second. The console opens with DeepSeek V4.1 Flash preselected.