docs(models): document reasoning_effort levels across the chat catalogue

src/content/docs-es/models.mdx

@@ -309,4 +309,36 @@ OpenAI y la misma `base URL`.
   ]}
 />
 
+## Controlar el razonamiento.
+
+Todos los modelos de chat de arriba razonan antes de responder, y el
+razonamiento llega separado de la respuesta, en `message.reasoning_content`.
+Cuánto puede pensar cada modelo se elige por petición con el parámetro
+`reasoning_effort`, y cada modelo lo aplica distinto: la tabla es el contrato.
+Un valor que un modelo no puede aplicar nunca es un error.
+
+| Modelo | valores de `reasoning_effort` | Qué hace |
+| --- | --- | --- |
+| `glm5.3` · `glm5.3-flash` | `low`, `medium`, `high`, `max` | Control total. Valores más altos dejan que el modelo razone más antes de responder; `max` es el más profundo. |
+| `qwen3.6` | `none`, `minimal`, `low`, `medium`, `high`, `max` | `none` y `minimal` se saltan por completo la fase de razonamiento. Los otros cuatro la acotan: low 2.048, medium 8.192, high 16.384, max 32.768 tokens. |
+| `gemma4` | `none`, `minimal`, `low`, `medium`, `high`, `max` | Igual que `qwen3.6`: apagado, o un presupuesto de razonamiento entre 2.048 y 32.768 tokens. |
+| `deepseek-v4-flash` | cualquier valor (sin efecto) | El modelo decide por petición cuánto razona; el parámetro nunca cambia eso. |
+| `qwen3.8-flash` · `mimo-v2.5` | aceptado, profundidad no ajustable | El parámetro se acepta y nunca se rechaza, pero estos modelos gestionan su propia profundidad de razonamiento. |
+
+Sin parámetro, cada modelo usa su propio valor por defecto (razonamiento
+activo en `qwen3.6` y `gemma4`, con presupuesto de 16.384 tokens). Más
+razonamiento cuesta latencia y cuenta dentro de `max_tokens`; nunca cuesta
+configuración adicional.
+
+```bash
+curl https://api.nan.builders/v1/chat/completions \
+  -H "Authorization: Bearer $NAN_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "glm5.3-flash",
+    "reasoning_effort": "low",
+    "messages": [{"role": "user", "content": "Write a one-line summary of the CAP theorem."}]
+  }'
+```
+
 <RateLimits />

src/content/docs/models.mdx

@@ -33,7 +33,7 @@ with the same `base URL`.
   ]}
   items={[
     'Tool calling (function calling)',
-    'Reasoning mode (reasoning trace)',
+    'Reasoning control (`reasoning_effort`: low · medium · high · max)',
     'Coding and long-horizon agentic tasks',
     '1M token context',
     'Streaming generation (SSE)',
@@ -58,7 +58,7 @@ with the same `base URL`.
   ]}
   items={[
     'Tool calling',
-    'Reasoning mode',
+    'Reasoning mode (adaptive — not level-adjustable)',
     'Vision (image input)',
     '1M token context',
     'Streaming generation (SSE)',
@@ -83,7 +83,7 @@ with the same `base URL`.
   ]}
   items={[
     'Tool calling (function calling)',
-    'Reasoning mode',
+    'Reasoning control (`reasoning_effort`: low · medium · high · max)',
     'Vision (image input)',
     '1M token context',
     'Streaming generation (SSE)',
@@ -158,7 +158,7 @@ with the same `base URL`.
   ]}
   items={[
     'Tool calling (XML format)',
-    'Reasoning mode',
+    'Reasoning control (`none` · low · medium · high · max)',
     'Multimodal (vision / images)',
     'Streaming generation (SSE)',
   ]}
@@ -182,7 +182,7 @@ with the same `base URL`.
   ]}
   items={[
     'Tool calling (XML format)',
-    'Reasoning mode',
+    'Reasoning control (`none` · low · medium · high · max)',
     'Multimodal (vision / images)',
     'Streaming generation (SSE)',
   ]}
@@ -308,4 +308,35 @@ with the same `base URL`.
   ]}
 />
 
+## Controlling reasoning.
+
+Every chat model above thinks before it answers, and the reasoning trace
+arrives separately from the answer, in `message.reasoning_content`. How much a
+model is allowed to think is a request parameter, `reasoning_effort`, and each
+model applies it differently — the table is the contract. A value a model
+cannot apply is never an error.
+
+| Model | `reasoning_effort` values | What it does |
+| --- | --- | --- |
+| `glm5.3` · `glm5.3-flash` | `low`, `medium`, `high`, `max` | Fully controllable. Higher values let the model reason longer before it answers; `max` is the deepest. |
+| `qwen3.6` | `none`, `minimal`, `low`, `medium`, `high`, `max` | `none` and `minimal` skip the reasoning phase entirely. The other four cap it: low 2,048, medium 8,192, high 16,384, max 32,768 tokens. |
+| `gemma4` | `none`, `minimal`, `low`, `medium`, `high`, `max` | Same as `qwen3.6`: off, or a reasoning budget between 2,048 and 32,768 tokens. |
+| `deepseek-v4-flash` | any value (no effect) | The model decides per request how much to reason; the parameter never changes that. |
+| `qwen3.8-flash` · `mimo-v2.5` | accepted, depth not adjustable | The parameter is accepted and never rejected, but these models manage their own reasoning depth. |
+
+With no parameter, every model uses its own default (reasoning on for
+`qwen3.6` and `gemma4`, with a 16,384-token budget). More reasoning costs
+latency and counts toward `max_tokens`; it never costs extra setup.
+
+```bash
+curl https://api.nan.builders/v1/chat/completions \
+  -H "Authorization: Bearer $NAN_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "glm5.3-flash",
+    "reasoning_effort": "low",
+    "messages": [{"role": "user", "content": "Write a one-line summary of the CAP theorem."}]
+  }'
+```
+
 <RateLimits />

src/data/openapi.json

@@ -221,13 +221,15 @@
                   "reasoning_effort": {
                     "type": "string",
                     "enum": [
+                      "none",
+                      "minimal",
                       "low",
                       "medium",
-                      "high"
+                      "high",
+                      "max"
                     ],
-                    "default": "medium",
-                    "description": "Reasoning depth (`deepseek-v4-flash` only). The trace comes back in `message.reasoning_content`. More effort helps on hard problems, at the cost of latency and tokens.",
-                    "example": "medium"
+                    "description": "Reasoning depth. Per model: `glm5.3` and `glm5.3-flash` accept `low`, `medium`, `high` and `max` — deeper means the model reasons longer before answering. `qwen3.6` and `gemma4` accept `none` or `minimal` (no reasoning phase at all) and `low`, `medium`, `high`, `max`, which cap the reasoning phase at 2,048 / 8,192 / 16,384 / 32,768 tokens. `deepseek-v4-flash` reasons adaptively per request: the parameter is accepted and has no effect. The remaining chat models accept the parameter and manage their own depth. The reasoning trace arrives in `message.reasoning_content`. A value a model cannot apply is never rejected. Details: [Models](https://nan.builders/docs/models).",
+                    "example": "high"
                   },
                   "chat_template_kwargs": {
                     "type": "object",