DeepSeek V4 Flash at 90% Off on Nous Portal
Melvin Vivas · X post · 2026-08-05 · Open on X
Topics: LLM Fundamentals, LLMOps, Deployment & Monitoring · Level: beginner
Summary
A heads-up that DeepSeek V4 Flash (0731) has a 90% discount on Nous Portal for about one more week. That makes it a very cheap model for experimenting with projects.
Key points
- DeepSeek V4 Flash 0731 is 90% off on Nous Portal for a limited time (about one week from 2026-08-05).
- Discounted API access is a cheap way to prototype projects.
Resources mentioned
- Nous Portal · tool · portal.nousresearch.com · paid
Nous Research's model-access portal, where you can sign up and use hosted models such as Hy3.
Also in: Alternative Coding Plans for Open Models: OpenCode Go, Ollama Cloud, Nous (Melvin Vivas on X · notes), Connecting Hermes Agent to the Buzz Agent-First Chat App via the Native Gateway (Melvin Vivas on X · notes), Hy3 (Tencent Hunyuan) Free on Nous Portal for a Limited Week (Melvin Vivas on X · notes) - DeepSeek V4 Flash · tool · huggingface.co · free
DeepSeek model used as the comparison baseline in the tool-calling benchmark.
Also in: Low-Cost Agent Run: DeepSeek V4 Flash via OpenRouter in ohmypi (Melvin Vivas on X · notes), Running Codex with DeepSeek V4 Flash through OpenRouter (Melvin Vivas on X · notes), LFM2.5-2.6B Matches DeepSeek-V4-Flash on Tool Calling; LEAP Fine-Tuning (Melvin Vivas on X · notes), Qwen3.8-Max on the Frontend Code Arena cost-performance frontier (Melvin Vivas on X · notes) and 3 more
Try this
- Use the discounted DeepSeek V4 Flash on Nous Portal before the offer ends.
More in LLM Fundamentals
- Running Liquid AI Models On-Device with the Apollo iPhone App
- Muse Glimmer 30B: Unsloth GGUF Release and Run Guide
- Transferable KV Cache: Reusing One Model's Cache in Another
- Qwen3.8-Max on the Frontend Code Arena cost-performance frontier
- Running a 28.9M-Parameter LLM on an $8 ESP32 Microcontroller
- GPT 5.6 Luna: Good, Fast and Cheap