GitHub Copilot auto model selection adds efficiency, balance, intelligence tiers
0xkarasy · x · 2026-09-15
GitHub Copilot's auto model selection now offers three tiers — efficiency (low cost, fast tasks), balance (cost/quality/latency for everyday work), and intelligence (quality-first for complex tasks).
Details:
- All tiers draw from the same model pool; auto evaluates each prompt individually, so a simple task like adding a docstring may use a small model even on the intelligence tier
- Usage is billed based on the model auto picks, regardless of tier; paid subscribers keep a 10% discount on auto-billed usage
- Rolling out in VS Code, Copilot CLI, and the GitHub Copilot app, billed as step one toward customizable model-selection tradeoffs
Related event: GitHub Copilot Adds Three-Tier Auto Model Selection(2 posts)→
More from coding & agent
- Simlock: open-source control plane gives parallel coding agents their own iOS/Android simulators — Scobleizer · 2026-10-30
- Keyfleet launches open canvas where personal AI agents team up with a shared USDC treasury — seanwbren · 2026-10-30
- Clear Thought MCP Server adds structured reasoning and mental models to AI clients — modelcontextprotocol · 2026-10-30
- NSE Stock Insights MCP brings AI analysis to India's Nifty 500 stocks — modelcontextprotocol · 2026-10-30
- OpenRouter rebuilds provider routing: 46% fewer capacity errors, 16.9% faster TTFT — steipete · 2026-10-30
- Databricks launches Agent Memory, tripling agent pass rates with 31% fewer tokens — matei_zaharia · 2026-10-30