Free-coding-models 0.5.89 is out !
Use deepseek v4, glm, gpt oss 120b, nemotron, minimax for free, thanks to 223 free API endpoints listed in this little tool I made to ping / test them all. 0.5.89 update is just some minor fixes, router v2, and prepping for something big
I used it all night, if you don’t believe me
I used it all night, if you don’t believe me, try it! It is strongly recommended to choose deepseek-v4.1-flash-expires-on-0910 for ordinary tasks, which has 300+ tokens/s, and give up OpenAI Astra, which has only 36 tokens/s without Fast! Astra is strong, but very slow. 4.1 Flash beats Astra in regular task efficiency! I also connected flash to Codex, and browser use and computer use are also very fast!
This is called Speculative Decoding.
It speeds up LLMs by ~100%. References: OpenAI: Deepseek: Gemini: AI Engineering Website:
DeepSeek V4.1 Flash, let’s start with a traditional project.
You have reached the end of the archive
All of deepseek