Hosted-gateway LLM router — save 67% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest ca...
Free-tier expansion (8→10 models): added DeepSeek V4 Pro/Flash and Nemotron-Omni (first vision-capable free model). Phased out DeepSeek V3.2 (redirected to V4 Pro). Plus Kimi K2.6 alias realignment from v0.12.170 — bare 'kimi' / 'moonshot' aliases now resolve to K2.6.