← All models

Best Model for OpenCode

OpenCode supports multiple providers, so you can match the model to the task. Claude Sonnet 4.6 is the quality default with strong LSP-assisted edits; for value, DeepSeek V4 Pro, GLM 5.2, Kimi K2.7 Code, and Qwen3.7 Max deliver near-frontier coding at open-weight prices.

Read the full OpenCode review → · updated 2026-06-22
#1Claude Sonnet 4.6Anthropic · $6.60/1M · 1M ctx

The quality default — pairs well with OpenCode's LSP intelligence for accurate edits.

Overall 91/100 · Value 46 · 78% community winFull breakdown →
#2DeepSeek V4 ProDeepSeek · $0.57/1M · 1.0M ctx

The value champion — near-frontier quality at a fraction of the cost, open weights included.

Overall 88/100 · Value 83 · 77% community winFull breakdown →
#3GLM 5.2Z.AI · $1.61/1M · 1.0M ctx

A capable open-weight flagship with a 1M context for harder sessions.

Overall 89/100 · Value 65 · 77% community winFull breakdown →
#4Kimi K2.7 CodeMoonshot AI · $1.35/1M · 262K ctx

Coding-tuned with great tool use — a strong cheap default for OpenCode.

Overall 88/100 · Value 67 · 77% community winFull breakdown →
#5Qwen3.7 MaxAlibaba (Qwen) · $2.00/1M · 1M ctx

Frontier-class quality with a 1M context at a friendlier price.

Overall 89/100 · Value 62 · 77% community winFull breakdown →
#6GPT-5.4OpenAI · $6.25/1M · 1.1M ctx

A well-priced GPT option for those who prefer the OpenAI family.

Overall 90/100 · Value 46 · 77% community winFull breakdown →

FAQ

What is the best model for OpenCode?
Claude Sonnet 4.6 for quality, or DeepSeek V4 Pro, GLM 5.2, and Kimi K2.7 Code for the best value. OpenCode's multi-provider support lets you run any of them and switch per session.
Does OpenCode support open-weight models?
Yes — OpenCode is multi-provider, so open-weight models like DeepSeek, GLM, Qwen, and Kimi all work, via hosted APIs or self-hosting.

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →