DeepSeek V4
DeepSeek's fourth-generation open-weight model family, including the low-cost V4.1 Flash with a 1M-token context, often used as the cheap executor under a frontier planner.
0 members list DeepSeek V4, unchanged over the last 12 weeks, data as of 9 November 2026
Members who list DeepSeek V4 in their Stack, by week.
Members who list DeepSeek V4
Be the first to add DeepSeek V4
Nobody on Stackness runs DeepSeek V4 yet. Add it to your stack and you're the first member running it.
About DeepSeek V4
DeepSeek V4 is a family of open-weight large language models developed by DeepSeek. The model family includes V4.1 Flash, a variant designed for low-cost inference with a 1 million token context window, commonly deployed as an economical execution layer beneath more capable planning models. These models are built to handle text-based tasks and support agentic workflows. DeepSeek V4 includes native multimodal capabilities for visual understanding alongside text processing.
The models are open-source and available through multiple interfaces, including a web-based chat application, desktop software, and an API platform. Developers can integrate DeepSeek V4 into their applications via the API, with usage priced according to a published pricing structure. The tool is positioned as an accessible option for developers seeking capable language models at reduced computational cost compared to alternative solutions in the market.
Checked 9 November 2026.
Nobody on Stackness runs DeepSeek V4 yet.
Sign up and add itPosts about DeepSeek V4
- Run Claude Code with a different model provider: the variables per vendor, what CC Switch and magpie write, and what breaks
Point ANTHROPIC_BASE_URL at DeepSeek, Kimi, GLM or Ollama, set all four model tiers, test with curl and /status. Check the cache before the bill.
- Claude Haiku 5.5 vs GPT-6 Luna cost per task: the 100k cliff, the tokenizer and which calls each one should take
Haiku 5.5 and GPT-6 Luna list at the same price, but Haiku costs 2.5-5x more per task and 5x above 100k tokens. Which calls each one should take.
- Llama.cpp alternatives for running local agents: ds4, Magnitude and Strata against llama.cpp, vLLM and Ollama
ds4 runs big MoE models on 96 GB Macs, Magnitude tunes kernels to your device, Strata puts one model on a gaming PC. Every speed claim is self-reported.