diff --git a/docs/providers/inferrs.md b/docs/providers/inferrs.md
index 069f9ece505..21fcac16f52 100644
--- a/docs/providers/inferrs.md
+++ b/docs/providers/inferrs.md
@@ -23,7 +23,7 @@ backend, not a dedicated OpenClaw provider plugin.
 Example:
 
 ```bash
-inferrs serve gg-hf-gg/gemma-4-E2B-it \
+inferrs serve google/gemma-4-E2B-it \
   --host 127.0.0.1 \
   --port 8080 \
   --device metal
@@ -46,9 +46,9 @@ This example uses Gemma 4 on a local `inferrs` server.
 {
   agents: {
     defaults: {
-      model: { primary: "inferrs/gg-hf-gg/gemma-4-E2B-it" },
+      model: { primary: "inferrs/google/gemma-4-E2B-it" },
       models: {
-        "inferrs/gg-hf-gg/gemma-4-E2B-it": {
+        "inferrs/google/gemma-4-E2B-it": {
           alias: "Gemma 4 (inferrs)",
         },
       },
@@ -63,7 +63,7 @@ This example uses Gemma 4 on a local `inferrs` server.
         api: "openai-completions",
         models: [
           {
-            id: "gg-hf-gg/gemma-4-E2B-it",
+            id: "google/gemma-4-E2B-it",
             name: "Gemma 4 E2B (inferrs)",
             reasoning: false,
             input: ["text"],
@@ -132,10 +132,10 @@ Once configured, test both layers:
 ```bash
 curl http://127.0.0.1:8080/v1/chat/completions \
   -H 'content-type: application/json' \
-  -d '{"model":"gg-hf-gg/gemma-4-E2B-it","messages":[{"role":"user","content":"What is 2 + 2?"}],"stream":false}'
+  -d '{"model":"google/gemma-4-E2B-it","messages":[{"role":"user","content":"What is 2 + 2?"}],"stream":false}'
 
 openclaw infer model run \
-  --model inferrs/gg-hf-gg/gemma-4-E2B-it \
+  --model inferrs/google/gemma-4-E2B-it \
   --prompt "What is 2 + 2? Reply with one short sentence." \
   --json
 ```
diff --git a/src/agents/openai-transport-stream.test.ts b/src/agents/openai-transport-stream.test.ts
index be673005ffc..b3496bbebdc 100644
--- a/src/agents/openai-transport-stream.test.ts
+++ b/src/agents/openai-transport-stream.test.ts
@@ -1082,7 +1082,7 @@ describe("openai transport stream", () => {
   it("flattens pure text content arrays for string-only completions backends when opted in", () => {
     const params = buildOpenAICompletionsParams(
       {
-        id: "gg-hf-gg/gemma-4-E2B-it",
+        id: "google/gemma-4-E2B-it",
         name: "Gemma 4 E2B",
         api: "openai-completions",
         provider: "inferrs",
diff --git a/src/agents/pi-embedded-runner-extraparams.test.ts b/src/agents/pi-embedded-runner-extraparams.test.ts
index 241a3510447..172b0514fb0 100644
--- a/src/agents/pi-embedded-runner-extraparams.test.ts
+++ b/src/agents/pi-embedded-runner-extraparams.test.ts
@@ -567,11 +567,11 @@ describe("applyExtraParamsToAgent", () => {
   it("flattens pure text OpenAI completions message arrays for string-only compat models", () => {
     const payload = runResponsesPayloadMutationCase({
       applyProvider: "inferrs",
-      applyModelId: "gg-hf-gg/gemma-4-E2B-it",
+      applyModelId: "google/gemma-4-E2B-it",
       model: {
         api: "openai-completions",
         provider: "inferrs",
-        id: "gg-hf-gg/gemma-4-E2B-it",
+        id: "google/gemma-4-E2B-it",
         name: "Gemma 4 E2B (inferrs)",
         baseUrl: "http://127.0.0.1:8080/v1",
         reasoning: false,