diff --git a/docs/models/supported_models.md b/docs/models/supported_models.md
index 96d5ec25c0064..1089de87b994e 100644
--- a/docs/models/supported_models.md
+++ b/docs/models/supported_models.md
@@ -666,7 +666,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
 | Architecture | Models | Inputs | Example HF Models | [LoRA](../features/lora.md) | [PP](../serving/parallelism_scaling.md) |
 |--------------|--------|--------|-------------------|----------------------|---------------------------|
 | `AriaForConditionalGeneration` | Aria | T + I<sup>+</sup> | `rhymes-ai/Aria` | | |
-| `AyaVisionForConditionalGeneration` | Aya Vision | T + I<sup>+</sup> | `CohereForAI/aya-vision-8b`, `CohereForAI/aya-vision-32b`, etc. | | ✅︎ |
+| `AyaVisionForConditionalGeneration` | Aya Vision | T + I<sup>+</sup> | `CohereLabs/aya-vision-8b`, `CohereLabs/aya-vision-32b`, etc. | | ✅︎ |
 | `BeeForConditionalGeneration` | Bee-8B | T + I<sup>E+</sup> | `Open-Bee/Bee-8B-RL`, `Open-Bee/Bee-8B-SFT` | | ✅︎ |
 | `Blip2ForConditionalGeneration` | BLIP-2 | T + I<sup>E</sup> | `Salesforce/blip2-opt-2.7b`, `Salesforce/blip2-opt-6.7b`, etc. | | ✅︎ |
 | `ChameleonForConditionalGeneration` | Chameleon | T + I | `facebook/chameleon-7b`, etc. | | ✅︎ |
diff --git a/examples/offline_inference/vision_language.py b/examples/offline_inference/vision_language.py
index 0888a9d60a3fa..22802dddf7893 100755
--- a/examples/offline_inference/vision_language.py
+++ b/examples/offline_inference/vision_language.py
@@ -72,7 +72,7 @@ def run_aria(questions: list[str], modality: str) -> ModelRequestData:
 # Aya Vision
 def run_aya_vision(questions: list[str], modality: str) -> ModelRequestData:
     assert modality == "image"
-    model_name = "CohereForAI/aya-vision-8b"
+    model_name = "CohereLabs/aya-vision-8b"
 
     engine_args = EngineArgs(
         model=model_name,
diff --git a/examples/offline_inference/vision_language_multi_image.py b/examples/offline_inference/vision_language_multi_image.py
index 560ca768d1a6c..28c466c03dfa5 100755
--- a/examples/offline_inference/vision_language_multi_image.py
+++ b/examples/offline_inference/vision_language_multi_image.py
@@ -76,7 +76,7 @@ def load_aria(question: str, image_urls: list[str]) -> ModelRequestData:
 
 
 def load_aya_vision(question: str, image_urls: list[str]) -> ModelRequestData:
-    model_name = "CohereForAI/aya-vision-8b"
+    model_name = "CohereLabs/aya-vision-8b"
 
     engine_args = EngineArgs(
         model=model_name,
diff --git a/tests/distributed/test_pipeline_parallel.py b/tests/distributed/test_pipeline_parallel.py
index 89f035d2cdd6f..cc6251514c3dc 100644
--- a/tests/distributed/test_pipeline_parallel.py
+++ b/tests/distributed/test_pipeline_parallel.py
@@ -109,7 +109,7 @@ TEXT_GENERATION_MODELS = {
     "baichuan-inc/Baichuan2-13B-Chat": PPTestSettings.fast(),
     "bigscience/bloomz-1b1": PPTestSettings.fast(),
     "zai-org/chatglm3-6b": PPTestSettings.fast(),
-    "CohereForAI/c4ai-command-r-v01": PPTestSettings.fast(load_format="dummy"),
+    "CohereLabs/c4ai-command-r-v01": PPTestSettings.fast(load_format="dummy"),
     "databricks/dbrx-instruct": PPTestSettings.fast(load_format="dummy"),
     "Deci/DeciLM-7B-instruct": PPTestSettings.fast(),
     "deepseek-ai/deepseek-llm-7b-chat": PPTestSettings.fast(),
diff --git a/tests/models/multimodal/generation/test_common.py b/tests/models/multimodal/generation/test_common.py
index f896126a49089..fd26b838ae209 100644
--- a/tests/models/multimodal/generation/test_common.py
+++ b/tests/models/multimodal/generation/test_common.py
@@ -278,7 +278,7 @@ VLM_TEST_SETTINGS = {
         marks=[large_gpu_mark(min_gb=64)],
     ),
     "aya_vision": VLMTestInfo(
-        models=["CohereForAI/aya-vision-8b"],
+        models=["CohereLabs/aya-vision-8b"],
         test_type=(VLMTestType.IMAGE),
         prompt_formatter=lambda img_prompt: f"<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{img_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>",  # noqa: E501
         single_image_prompts=IMAGE_ASSETS.prompts(
@@ -294,7 +294,7 @@ VLM_TEST_SETTINGS = {
         vllm_runner_kwargs={"mm_processor_kwargs": {"crop_to_patches": True}},
     ),
     "aya_vision-multi_image": VLMTestInfo(
-        models=["CohereForAI/aya-vision-8b"],
+        models=["CohereLabs/aya-vision-8b"],
         test_type=(VLMTestType.MULTI_IMAGE),
         prompt_formatter=lambda img_prompt: f"<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{img_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>",  # noqa: E501
         single_image_prompts=IMAGE_ASSETS.prompts(
diff --git a/tests/models/registry.py b/tests/models/registry.py
index 352abdd2da9a0..020cb749341a6 100644
--- a/tests/models/registry.py
+++ b/tests/models/registry.py
@@ -211,10 +211,10 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
         trust_remote_code=True,
     ),
     "CohereForCausalLM": _HfExamplesInfo(
-        "CohereForAI/c4ai-command-r-v01", trust_remote_code=True
+        "CohereLabs/c4ai-command-r-v01", trust_remote_code=True
     ),
     "Cohere2ForCausalLM": _HfExamplesInfo(
-        "CohereForAI/c4ai-command-r7b-12-2024",
+        "CohereLabs/c4ai-command-r7b-12-2024",
         trust_remote_code=True,
     ),
     "CwmForCausalLM": _HfExamplesInfo("facebook/cwm", min_transformers_version="4.58"),
@@ -581,7 +581,7 @@ _AUTOMATIC_CONVERTED_MODELS = {
 _MULTIMODAL_EXAMPLE_MODELS = {
     # [Decoder-only]
     "AriaForConditionalGeneration": _HfExamplesInfo("rhymes-ai/Aria"),
-    "AyaVisionForConditionalGeneration": _HfExamplesInfo("CohereForAI/aya-vision-8b"),
+    "AyaVisionForConditionalGeneration": _HfExamplesInfo("CohereLabs/aya-vision-8b"),
     "BeeForConditionalGeneration": _HfExamplesInfo(
         "Open-Bee/Bee-8B-RL",
         trust_remote_code=True,