DeepSeek V4-Pro, V4-Flash and V4.1-Flash arrive on SageMaker JumpStart: MIT-licensed MoE models with a 1M-token context
Three DeepSeek open-weight models can now be deployed into your own AWS account in a few clicks. How they differ and what each suits.
// Key points
- V4-Pro has 1.6T total parameters with 49B active per token, aimed at complex reasoning and high-quality generation.
- V4-Flash has 284B total parameters with 13B active per token, aimed at latency- and cost-sensitive production.
- V4.1-Flash uses a Causal Encoder-Decoder (CED) architecture on a 552B backbone, activating 8B in prefill and 16B in decode, with native multimodality and up to 384K output tokens; CSA2 attention and FP4 KV caching cut the global KV cache to about a quarter of V4-Flash's.
- All three support a 1M-token context and deploy from the SageMaker console or Python SDK.
Builder's takeFor teams whose data must stay in their own cloud account but who want cheap open models, this removes the step of building inference yourself. I would look first at V4.1-Flash: a KV cache a quarter the size matters most for long-context agent work. Before going live, compare per-task cost between on-demand Bedrock and an always-on JumpStart endpoint on your own workload; with uneven traffic the endpoint may not pay off.