Stay up to date with Axecodi releases, NVIDIA NIM API changes, model updates, and how-to guides.
The NVIDIA NIM streaming endpoint now supports parallel tool calls mid-stream. No more waiting for full completion before executing functions.
Step-by-step guide to deploy your own Axecodi instance with custom domain, API key setup, and environment configuration.
Llama 3.3 70B and GLM-5.1 now support up to 128,000 tokens of context — analyze full codebases or entire documents in a single prompt.
A practical guide to crafting system prompts for GLM-5.1 and Llama 3.3 that produce consistent, high-quality outputs for your use case.
DeepSeek R1 joins the Axecodi model lineup. Its reinforcement learning approach achieves near-o1 performance on MATH and AIME benchmarks.
NVIDIA NIM API rate limits have been upgraded. Free tier now supports 1,000 requests/day. Pro tier gets 100,000 requests/day with burst support.
How to use Axecodi's file attachment feature effectively — supported formats, size limits, model compatibility, and best practices.
Axecodi v2.0 is here with a complete UI overhaul, multi-conversation support, slash commands, temperature control, and much more.
Alibaba's Qwen 2.5 72B joins Axecodi with best-in-class Chinese/English bilingual performance and 128K context window support.