We tested closed and open models by asking them to build small, playable games.
Open models were much cheaper and faster, while producing games that were often close in quality.
→ Opus 4.8 was 15x more expensive than MiniMax M3
→ GPT-5.5 was 10x more expensive than Nemotron…
Built a visual benchmark where I asked closed and open source models to build small games.
Main takeaway: OSS models were a lot faster, cheaper, & produced games with similar quality.
Specifically:
* Opus 4.8 was 15x more expensive than MiniMax M3
* GPT-5.5 was 10x more…
.@DecagonAI cut voice agent cost per turn nearly 6x with Together AI.
They moved from closed models to fine-tuned open models, while keeping latency low enough for real-time voice:
→ <400ms p95 model latency per turn
→ custom speculators and prompt caching
→ optimized…
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.