[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
DeepSeek released V4.1-Flash, an open-weight 763B-parameter model with a novel causal encoder-decoder architecture, 1M context, vision input, and MIT license.
DeepSeek launched V4.1-Flash, an open-weight MIT-licensed model using a novel causal encoder-decoder architecture with 763B total parameters and asymmetric active parameters: 8B for prefill and 16B for decode. It supports 1M-token context and text+image input, priced at $0.30 per 1M input and $1.20 per 1M output tokens with a 50% off-peak discount. Artificial Analysis scored it 40 on its Intelligence Index, above DeepSeek V4 Pro 0813, and Vals ranked it the #1 open-weight model ahead of Kimi K3. Baseten shipped day-0 support and Ollama began rolling it out to paid subscribers.
- Novel causal encoder-decoder design uses 8B active parameters for prefill and 16B for decode.
- KV cache footprint up to 1/8 of V4 Flash, improving speed and cost for long-running agents.
- Artificial Analysis Intelligence Index score of 40, surpassing DeepSeek V4 Pro 0813 at far lower cost.
- Ranked #1 open-weight model on the Vals Index, ahead of Kimi K3.
- MIT license with 1M context, vision input, and day-0 support from Baseten and Ollama.
- Tags
- deepseekencoder-decoderinference-efficiencylong-contextmixture-of-expertsopen-weightsv4.1-flashvision-language
- Products
- DeepSeek V4.1-Flash
- Organizations
- DeepSeekArtificial AnalysisValsBasetenOllama
- AI models
- DeepSeek V4.1-Flash
From the original article
13 min read at latent.space
We are late to this but better than never. Have been busy finalizing the second AIE NYC , which is happening in one month. Get your tix before prices go up - we will announce speakers from Bridgewater, Ramp, Coatue, Mastercard, Vanguard, Coinbase, Blackrock, Fidelity, Point72, Capital One, JPMC, Wells Fargo, Bloomberg, A24 (yes the movie studio) Labs, Two Sigma, Apollo Global, and more next week!
latent.space
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.