OpenCode 2.3.2 released
A patch release that optimizes GPT-6.2 prompt caching to avoid re-billing system prompts on every step.
What changed in 2.3.2
- GPT-6.2 models now cache system prompts across steps, reducing uncached input tokens per step from about 14,000 to 3 on GitHub Copilot.
- Prompt caching improvements applied to OpenAI, GitHub Copilot, Zen, Azure and OpenRouter routes.
- webfetch structured output no longer includes duplicate url and format fields.
Summarised by AgentGid from Anomaly (SST team)'s official release notes on GitHub, as reported there; read the original before relying on it. Price, status and release dates come from our daily data.
OpenCode at a glance
| What it is | Open-source coding agent from Anomaly (the team behind SST) that runs as a terminal UI, desktop app or IDE extension and connects to 75+ model providers, including local models and existing ChatGPT or GitHub Copilot log… |
|---|---|
| Latest version | 2.3.2 is the latest stable release we track. |
| Release pace | 20 stable releases in the last 30 days; 2.3.2 came the same day as the previous one |
| Price | Free + $10/mo. OpenCode is free and open source, with free models under a daily request limit. Paid plans: OpenCode Go ($10/month) and Go Plus ($40/month) with monthly usage limits per curated m… Official pricing ↗ (checked Nov 17, 2026) |
| Downloads, last 7 days | 4M up 19.4% |
| Gid Score | 80 #3 in Terminal coding agents |