diff --git a/packages/web/src/content/docs/go.mdx b/packages/web/src/content/docs/go.mdx
index 796e67c89..7b02f9091 100644
--- a/packages/web/src/content/docs/go.mdx
+++ b/packages/web/src/content/docs/go.mdx
@@ -75,17 +75,27 @@ The list of models may change as we test and add new ones.
 
 OpenCode Go includes the following limits:
 
-- **5 hour limit** — $4 of usage
-- **Weekly limit** — $10 of usage
-- **Monthly limit** — $20 of usage
+- **5 hour limit** — $12 of usage
+- **Weekly limit** — $30 of usage
+- **Monthly limit** — $60 of usage
 
-In terms of tokens, $20 of usage is roughly equivalent to:
+Limits are defined in dollar value. This means your actual request count depends on the model you use. Cheaper models like MiniMax M2.5 allow for more requests, while higher-cost models like GLM-5 allow for fewer.
 
-- 69 million GLM-5 tokens
-- 121 million Kimi K2.5 tokens
-- 328 million MiniMax M2.5 tokens
+The table below provides an estimated request count based on typical Go usage patterns:
 
-You can view your current usage in the **<a href={console}>console</a>**.
+| Usage limit   | Dollar | MiniMax M2.5 | Kimi K2.5 | GLM-5 |
+| ------------- | ------ | ------------ | --------- | ----- |
+| 5 hour limit  | $12    | 30,000       | 1,850     | 1,150 |
+| Weekly limit  | $30    | 75,000       | 4,630     | 2,880 |
+| Monthly limit | $60    | 150,000      | 9,250     | 5,750 |
+
+Estimates are based on observed average request patterns:
+
+- MiniMax M2.5 — 300 input, 55,000 cached, 125 output tokens per request
+- Kimi K2.5 — 870 input, 55,000 cached, 200 output tokens per request
+- GLM-5 — 700 input, 52,000 cached, 150 output tokens per request
+
+You can track your current usage in the **<a href={console}>console</a>**.
 
 :::tip
 If you reach the usage limit, you can continue using the free models.