Open source AI coding agent for the terminal, desktop and IDE that works with models from more than 75 providers, complemented by the Zen and Go model access services.
OpenCode Pricing
Last edited: October 2026
OpenCode
Free
The open source agent itself, free of charge. Costs depend on the chosen model provider.
Open source
Available as terminal interface, desktop app and IDE extension
75+ LLM providers through Models.dev, including local models
Log in with GitHub Copilot or ChatGPT Plus/Pro
Multiple agents in parallel on the same project
Share sessions via link
LSP servers loaded automatically
No storage of code or context data
Go
10.00 $/ Month
Subscription with monthly usage limits for curated open coding models. Billed monthly, cancel any time.
Curated models tested for agentic coding, including Kimi K3, GLM-5.3, DeepSeek V4.1 Flash, Qwen3.8 Max, Claude Haiku 5.5 and GPT 6 Luna
Monthly usage limit per model as a dollar amount, plus 5-hour (20%) and weekly (50%) limits
Works with OpenCode and other coding agents such as Claude Code and Codex
Credit top-up available, optional fallback to the pay-as-you-go balance after reaching the limit
Cancel any time
Go Plus
40.00 $/ Month
Built for larger, demanding projects. Billed monthly, cancel any time.
Everything included in Go, plus:
Higher monthly usage limits per model
Fewer interruptions from limits
Same token pricing as Go
Zen
Pay as you go
Usage-based billing per request from a balance, no base fee. Starts with a USD 20 balance plus a USD 1.23 card processing fee, automatic top-up of USD 20 when the balance drops below USD 5.
Curated models tested for coding agents from OpenAI, Anthropic, Google, xAI, DeepSeek, Qwen, Kimi, GLM, MiniMax and Mistral
Prices per 1M tokens, e.g. GPT 5 Nano from USD 0.05 input and USD 0.40 output, DeepSeek V4.1 Flash USD 0.30 / 1.20, Claude Sonnet 5.5 USD 2 / 10, Claude Opus 5.5 USD 4 / 20
Sold at cost, markup only to cover processing fees
Monthly spend limits per workspace and member
Works with OpenCode and other coding agents
Cancel any time
Enterprise
Upon request
For organizations that want their code and data to stay within their own infrastructure. Per-seat pricing, price on request.
Per-seat pricing
No token charges with an own LLM gateway
Central config for the entire organization
SSO integration through the central config
Use of the internal AI gateway only, other providers can be disabled
No storage of code or context data
No licensing restrictions or ownership claims on generated code
