OpenAI- and Anthropic-compatible inference for coding agents. Call DeepSeek-V4.1-Flash and DeepSeek-V4-Flash with zero data retention.
1 comment
martianvoid6 days ago
> Input Output
> Kimi K3 $3.00 $15.00
> Qwen3.8 2.4T-A95B $2.00 $6.00
Why is kimi priced at twice that of qwen 3.8? If I remember correctly both of them are of the same 2.5T param family. I wonder kind of optimizations or hardware they have that make such pricing differences for the same sizes of models
Read the full thread on Hacker News →
Related stories
- Ars Technica · 0 points · 8 days ago
- Hacker News · 55 points · 4 days ago
- Researchers used Claude to hack OpenAIarstechnica.comArs Technica · 0 points · 13 days ago
- OpenAI says planned GPT-6.1 is too insecure to releasearstechnica.comArs Technica · 0 points · 1 day ago
- The Verge · 0 points · 8 days ago
- The Verge · 0 points · 1 day ago