Repository navigation
[FEATURE]: Document Go Plus per-model usage multipliers and fix sub-4x tiers #52026
Description
Feature hasn't been suggested before.
- I have verified this feature I'm about to request hasn't been suggested before.
Describe the enhancement you want to request
Problem. Go Plus costs 4x Go ($40/mo vs $10/mo), with the same models and the same per-token prices. The only difference is the monthly dollar allowance per model — and that allowance is not scaled by a uniform 4x. It ranges from 2x to 8x, and this is not documented anywhere.
Per dollar, Go Plus is therefore worse than Go for 11 of the 28 paid models, neutral (exactly 4x) for 16, and better for only 1.
| Multiplier | Models | Examples (Go → Go Plus) |
|---|---|---|
| 2x (worse) | 5 | MiMo-V2.6-Flash $60→$120, DeepSeek V4.1 Flash $60→$120, Muse Spark 1.3/1.2 $60→$120 |
| 3x (worse) | 6 | GLM-5.2 $60→$180, Kimi K2.7 Code $60→$180, MiniMax M3 $60→$180 |
| 4x (neutral) | 16 | Kimi K3 $15→$60, Qwen3.8 Max $15→$60, DeepSeek V4 Pro $15→$60, Grok 4.7 $15→$60, GPT 6 Luna $15→$60 |
| 8x (better) | 1 | GLM-5.3 $15→$120 |
The estimated-request tables scale by the same multipliers (GLM-5.3: 220→1,760 req/5h; MiMo-V2.6-Flash: 30,100→60,200), so this is structural. And since "only one member per workspace can subscribe to OpenCode Go or Go Plus", a user on a 2x/3x model cannot work around it by stacking two $10 Go plans.
Requested change.
- Add a "Go Plus multiplier" (or "Go Plus monthly limit") column to the Go pricing tables, so the upgrade value is visible per model.
- Raise the 2x/3x models to at least 4x on Go Plus — or explicitly position Go Plus as a bigger bucket for a subset of models, rather than an across-the-board 4x upgrade.
Related: #43194 (optional Go quota multipliers), #24879 (Go Pro tier), #28846 (limit adjustment after price cuts), #15872 (Go pricing/limits docs clarity). Not a duplicate of #43194: that asks for optional multipliers on Go; this is about the existing Go Plus tier's per-model multipliers being inconsistent.
Activity
[-][FEATURE]: Document and rebalance Go Plus per-model usage multipliers (currently 2x-8x, not a uniform 4x)[/-][+][FEATURE]: Document Go Plus per-model usage multipliers and fix sub-4x tiers[/+]github-actions commentedon Sep 29, 2026
Thanks for updating the issue with the requested details!
carlosmintfan commentedon Oct 1, 2026
I think you can still create multiple workspaces to stack multiple $10 plans btw
neriousy commentedon Oct 21, 2026
Thanks for the feedback. Go and Go Plus both have one allowance shared across all models. How fast each model uses it up is set per model, so the difference between Go and Go Plus isn't a flat 4x for every model. That's intentional, and it depends on what we can get for each model. The current per-model numbers for both plans are at https://opencode.ai/docs/go#usage-limits.
OpenCode Go and the free models have usage limits. They're set by plan, and for free models they also change with available capacity, so they're not something we can raise case by case. Your current usage and reset times are in the console, and how the limits work is described at https://opencode.ai/docs/go. If you think your usage was counted wrongly on your account, email help@anoma.ly with your workspace ID.
isoux35 commentedon Oct 23, 2026
Why haven’t the Go docs been corrected after the team confirmed that all models share one allowance? They still imply separate per-model limits, which affects purchasing decisions. When will this be fixed?