NESTcode
Connecting...
Home
Chat
Code
Shadow
⚙
Stream
Code
NESTcode Workshop. Establishing connection...
Python
JavaScript
TypeScript
Bash
SQL
HTML
CSS
RUN
REVIEW
CLEAR
Editor
Output
IDLE
Run code to see output here.
✕
📎
✕
📎
SEND
Workshop Settings
Model
Nemotron Super 120B — MoE, strong
GPT-OSS 120B — large, uncensored
Qwen3 Next 80B — MoE, fast
Llama 3.3 70B — solid all-rounder
Qwen3 Coder — code specialist
MiniMax M2.5 — quietly good
GLM 4.5 Air — Zhipu, balanced
Step 3.5 Flash — fast
Nemotron Nano 30B — MoE, lightweight
GPT-OSS 20B — smaller, fast
Nemotron Nano 9B — tiny, quick
DeepSeek R1 ($0.70/$2.50)
DeepSeek V3.2 ($0.26/$0.38)
Claude Opus 4.5 ($15/$75)
Claude Sonnet 4.5 ($3/$15)
Claude Haiku 4.5 ($1/$5)
Qwen 3.7 Plus — 1M, proven companion ($0.33/$1.95) ⭐
Step 3.5 Flash — 262K, MoE ($0.10/$0.30)
MiMo V2 Pro ($1/$3)
Gemini 2.0 Flash ($0.10/$0.40)
GPT-4o ($2.50/$10)
GPT-4o Mini ($0.15/$0.60)
Gateway uses this model for all Workshop conversations and agentic heartbeat tasks.
Cancel
New Session
Clear Session
Save