Use Kimi K2.6 and K3 through an OpenAI-compatible API: curl, the OpenAI SDK, Cline and Aider
One base URL, one key, two Kimi model IDs, and the exact settings for your coding agent
Latest articles
How do you use DeepSeek V4.1 Flash and Kimi K3 in opencode through a custom OpenAI-compatible provider?
One provider block in opencode.json, four exact model IDs, a sanity check from the openai package, and the fixes for the errors you are likely to hit
Use DeepSeek V4 in Cursor, Continue, Cline and aider through one OpenAI-compatible base URL
One key, one base URL, three DeepSeek model IDs, and the values to paste into each coding agent
Save Your Work Before You Destroy a Cloud GPU: Checkpoints, rsync and Hub Uploads (2026)
Destroying a rented GPU deletes its disk. Copy checkpoints, LoRA adapters and outputs off the machine with rsync, scp, Hugging Face or rclone.
Self-Host an LLM on a Rented GPU or Pay per Token? A Break-Even Calculator (2026)
When does renting a GPU beat a per-token API? The break-even formula, a Qwen3 32B example on a 32 GB card, utilisation and a script.
KV Cache VRAM Calculator: How Much Memory Does Context Length Need? (2026)
KV cache memory for any context length: the formula, per-token sizes for Qwen3, Llama 3 and Mistral from config.json, and what fits on 24–80 GB.
