OpenCode Go

Limits

As the provider states them.

Per-model USD-value limits: 5-hour = 20% of monthly limit, weekly = 50%, monthly = 100%. Go monthly limits per model: $15 (GLM-5.3, Kimi K3, MiMo-V2.6-Pro, MiMo-V2.5-Pro, Qwen3.8 Max, DeepSeek V4 Pro, DeepSeek V4 Flash Vision Exp, Grok 4.7/4.6, GPT 6 Luna, GPT 5.6 Luna, Claude Haiku 5.5), $30 (Qwen3.8 Flash, DeepSeek V4 Flash, Hy4 preview, Space Bunny), $60 (GLM-5.3-Flash, GLM-5.2, Kimi K2.7 Code, Kimi K2.6, LongCat-2.0, MiMo-V2.6-Flash, MiMo-V2.5, MiniMax M3/M2.7, Muse Spark, Qwen3.7 Plus, DeepSeek V4.1 Flash, Hy3)

• 5-hour: 20% of the monthly limit, for percent of per-model monthly dollar limit
• Weekly: 50%, for percent of per-model monthly dollar limit
• Monthly: 100%, for percent of per-model monthly dollar limit

At the limit

With a Zen credit balance and 'Use balance' enabled in the console, requests continue by drawing from balance; otherwise blocked

Fair use

not stated

Models included

Stated as families: Curated open-source coding models plus a few closed models

• GLM-5.3-Flash
• GLM-5.3
• GLM-5.2
• Kimi K3
• Kimi K2.7 Code HighSpeed
• Kimi K2.6
• LongCat-2.0
• MiMo-V2.6-Flash
• MiMo-V2.6-Pro
• MiMo-V2.5
• MiMo-V2.5-Pro
• MiniMax-M3
• MiniMax-M2.7
• Muse Spark 1.3
• Muse Spark 1.2 Contributor
• Qwen3.8 Max
• Qwen3.8 Flash
• Qwen3.7 Plus
• DeepSeek V4.1 Flash
• DeepSeek V4 Pro
• DeepSeek V4 Flash
• DeepSeek V4 Flash Vision Exp
• Hy4 preview
• Hy3
• Grok 4.7
• Grok 4.6
• GPT-6 Luna
• Claude Haiku 5.5

Named by the plan but not matched to a model in our data: Space Bunny, GPT 5.6 Luna, Qwen3.8 Flash (alibaba/qwen3-8-flash matched by name, verify).

Source

“Each model has the following usage limits: 5-hour — 20% of the monthly limit; weekly — 50%; and monthly — 100%.” paraphrased from source

opencode.ai/docs/go/ Verified 2026-10-11

Page says 31/32+ models. Limits are dollar-value budgets per model, not request counts.

Similar plans