diff --git a/CHANGELOG.md b/CHANGELOG.md
index e47a51f..3b7d019 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,11 @@
 # Changelog
 
+## Unreleased
+
+### Changed
+
+- **`maxTokens` now matches the CLI registry instead of a uniform 16384 (#195).** Every Opus entry and `claude-sonnet-5` go to **64000**, `claude-sonnet-4-6` and `claude-haiku-4-5` to **32000** — the `max_output_tokens.default` each model actually declares in the compiled CLI 2.1.220 registry. OCP never enforced this value; it is propagated to OpenClaw, where it **caps the outbound request**: `maxTokens = Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens)`. OpenClaw's reasoning budgets are medium 8192 / high 16384, and when `maxTokens <= thinkingBudget` it clamps thinking to `maxTokens - 1024` — so a model declared at 16384 running at **high** reasoning spent ~15360 on thinking and left **~1024 tokens for the actual answer**. `ocp-connect`'s independent family table moves to the family floor (opus 64000, sonnet 32000, haiku 32000) since prefixes cannot distinguish versions. Expect longer answers and correspondingly higher per-request quota burn on long generations.
+
 ## v3.25.0 — 2026-07-27
 
 Minor release. Headline: **Claude Opus 5** joins the model list and the `opus` alias now resolves to it. Alongside it, two `server.mjs` correctness fixes found by review rather than by users — a monotonic in-flight-counter leak, and cache keys that were hashing the alias string instead of the model it resolves to. The three TUI/prompt fixes that landed after v3.24.0 are included here too.
diff --git a/models.json b/models.json
index f3c13d6..0db0b7a 100644
--- a/models.json
+++ b/models.json
@@ -8,7 +8,7 @@
       "openclawName": "Claude Opus 5 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 16384
+      "maxTokens": 64000
     },
     {
       "id": "claude-opus-4-8",
@@ -16,7 +16,7 @@
       "openclawName": "Claude Opus 4.8 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 16384
+      "maxTokens": 64000
     },
     {
       "id": "claude-opus-4-7",
@@ -24,7 +24,7 @@
       "openclawName": "Claude Opus 4.7 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 16384
+      "maxTokens": 64000
     },
     {
       "id": "claude-opus-4-6",
@@ -32,7 +32,7 @@
       "openclawName": "Claude Opus 4.6 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 16384
+      "maxTokens": 64000
     },
     {
       "id": "claude-sonnet-5",
@@ -40,7 +40,7 @@
       "openclawName": "Claude Sonnet 5 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 16384
+      "maxTokens": 64000
     },
     {
       "id": "claude-sonnet-4-6",
@@ -48,7 +48,7 @@
       "openclawName": "Claude Sonnet 4.6 (via CLI)",
       "reasoning": true,
       "contextWindow": 200000,
-      "maxTokens": 16384
+      "maxTokens": 32000
     },
     {
       "id": "claude-haiku-4-5-20251001",
@@ -56,7 +56,7 @@
       "openclawName": "Claude Haiku 4.5 (via CLI)",
       "reasoning": false,
       "contextWindow": 200000,
-      "maxTokens": 8192
+      "maxTokens": 32000
     }
   ],
   "aliases": {
diff --git a/ocp-connect b/ocp-connect
index 0722806..2495491 100755
--- a/ocp-connect
+++ b/ocp-connect
@@ -129,10 +129,17 @@ provider = {
 # re-trip it. Family prefixes classify any versioned ID correctly with no per-model
 # edit. (ADR 0003: models.json is the SPOT for model existence; /v1/models does not
 # expose reasoning/maxTokens, so family classification stays here.)
+# maxTokens values are the FAMILY FLOOR of the CLI registry max_output_tokens.default
+# (opus family 64000; sonnet 32000 because sonnet-4-6 is 32000 while sonnet-5 is 64000;
+# haiku 32000). Family prefixes cannot distinguish versions, so the floor is used
+# deliberately: under-advertising caps a client lower than the model allows, which is safe,
+# whereas over-advertising would promise capacity a member of the family does not have.
+# models.json is authoritative per ADR 0003; this table only exists because /v1/models does
+# not expose maxTokens.
 model_meta = {
-    "claude-opus": {"name": "Claude Opus (OCP)", "reasoning": True, "maxTokens": 16384},
-    "claude-sonnet": {"name": "Claude Sonnet (OCP)", "reasoning": True, "maxTokens": 16384},
-    "claude-haiku": {"name": "Claude Haiku (OCP)", "reasoning": False, "maxTokens": 8192},
+    "claude-opus": {"name": "Claude Opus (OCP)", "reasoning": True, "maxTokens": 64000},
+    "claude-sonnet": {"name": "Claude Sonnet (OCP)", "reasoning": True, "maxTokens": 32000},
+    "claude-haiku": {"name": "Claude Haiku (OCP)", "reasoning": False, "maxTokens": 32000},
 }
 
 def get_model_meta(mid):
diff --git a/test-features.mjs b/test-features.mjs
index 57c00f8..a932eef 100644
--- a/test-features.mjs
+++ b/test-features.mjs
@@ -4299,6 +4299,24 @@ test("models.json: every aliases value resolves to a real models[].id (referenti
   }
 });
 
+// maxTokens must leave room for a visible answer once a client's thinking budget is taken out
+// (#195). OCP never enforces maxTokens itself — it is propagated to OpenClaw (setup.mjs,
+// scripts/sync-openclaw.mjs) where it CAPS the outbound request:
+//     maxTokens = Math.min(baseMaxTokens + thinkingBudget, modelMaxTokens)
+// OpenClaw's reasoning budgets are medium 8192 / high 16384, and when maxTokens <= thinkingBudget
+// it clamps thinking to maxTokens - 1024. So a model declared at 16384 running at `high` spent
+// ~15360 on thinking and left ~1024 for the actual answer — which is what this repo shipped until
+// v3.25.0. Asserting the PRINCIPLE rather than pinning per-model numbers: a value test would need
+// editing every time a model is added, and would not say why.
+const _spotHighThinkingBudget = 16384; // OpenClaw's `high` reasoning budget
+test("models.json: every maxTokens exceeds the high thinking budget, leaving room for output (#195)", () => {
+  for (const m of _spotModels.models) {
+    assert.ok(m.maxTokens > _spotHighThinkingBudget,
+      `${m.id} declares maxTokens=${m.maxTokens} <= ${_spotHighThinkingBudget}: at OpenClaw's 'high' reasoning ` +
+      `level the thinking budget would consume all but ~1024 tokens of the response`);
+  }
+});
+
 test("models.json: every legacyAliases value resolves to a real models[].id (referential integrity)", () => {
   for (const [name, target] of Object.entries(_spotModels.legacyAliases || {})) {
     assert.ok(_spotModelIds.has(target), `legacyAliases.${name} -> '${target}' is a dangling alias (no matching models[].id)`);