by DeepSeek

DeepSeek V4.1 Flash.

multimodal open weights 1M ctx

DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters that natively processes images and text at up to 1M token context. Its Causal Encoder-Decoder architecture activates only 8B para

Where to use it

Cheapest hosted endpoints.

Provider	Access	$/M in	$/M out
Fireworks AI	hosted inference	—	—	Launch ↗

FAQ

Frequently asked.

How do I run DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.

Where can I access DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is available via Fireworks AI. Each access option lists its own pricing (per million tokens or hourly hosting).

How much does it cost to run DeepSeek V4.1 Flash?

Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.

Is DeepSeek V4.1 Flash open-source or proprietary?

DeepSeek V4.1 Flash is open-weight under the license. You can download and self-host it.