feat: Add new OVHcloud models

core/llm/llms/OVHcloud.ts

@@ -16,10 +16,16 @@ export class OVHcloud extends OpenAI {
     "llama3.1-70b": "Meta-Llama-3_1-70B-Instruct",
     "llama3.3-70b": "Meta-Llama-3_3-70B-Instruct",
     "qwen2.5-coder-32b": "Qwen2.5-Coder-32B-Instruct",
+    "qwen3-32b": "Qwen3-32B",
+    "qwen3-coder-30b-a3b": "Qwen3-Coder-30B-A3B-Instruct",
+    "qwen2.5-vl-72b": "Qwen2.5-VL-72B-Instruct",
     "codestral-mamba-latest": "mamba-codestral-7B-v0.1",
     "mistral-7b": "Mistral-7B-Instruct-v0.3",
     "mistral-8x7b": "Mixtral-8x7B-Instruct-v0.1",
     "mistral-nemo": "Mistral-Nemo-Instruct-2407",
+    "mistral-small-3.2-24b": "Mistral-Small-3.2-24B-Instruct-2506",
+    "gpt-oss-20b": "gpt-oss-20b",
+    "gpt-oss-120b": "gpt-oss-120b",
     "DeepSeek-R1-Distill-Llama-70B": "DeepSeek-R1-Distill-Llama-70B",
   };
 

core/llm/toolSupport.ts

@@ -356,6 +356,29 @@ export const PROVIDER_TOOL_SUPPORT: Record<string, (model: string) => boolean> =
         }
       }
 
+      return false;
+    },
+    ovhcloud: (model) => {
+      const lower = model.toLowerCase();
+
+      // Models that support tools according to OVHcloud AI Endpoints catalog
+      const toolSupportingModels = [
+        "llama-3.1-8b-instruct",
+        "qwen3-32b",
+        "qwen3-coder-30b-a3b-instruct",
+        "meta-llama-3_3-70b-instruct",
+        "deepseek-r1-distill-llama-70b",
+        "mistral-small-3.2-24b-instruct-2506",
+        "gpt-oss-120b",
+        "mistral-nemo-instruct-2407",
+        "gpt-oss-20b",
+        "qwen2.5-coder-32b-instruct",
+      ];
+
+      if (toolSupportingModels.some((m) => lower === m)) {
+        return true;
+      }
+
       return false;
     },
   };

docs/customize/model-providers/more/ovhcloud.mdx

@@ -15,7 +15,50 @@ OVHcloud AI Endpoints is a serverless inference API that provides access to a cu
 ## Chat model
 
 We recommend configuring **Qwen2.5-Coder-32B-Instruct** as your chat model.
-Check our [catalog](https://endpoints.ai.cloud.ovh.net/catalog) to see all of our models hsoted on AI Endpoints.
+Check our [catalog](https://endpoints.ai.cloud.ovh.net/catalog) to see all of our models hosted on AI Endpoints.
+
+### Available Models
+
+OVHcloud AI Endpoints provides access to the following models:
+
+**Llama Models:**
+- `llama3.1-8b` - Llama 3.1 8B Instruct (supports function calling)
+- `llama3.1-70b` - Llama 3.1 70B Instruct
+- `llama3.3-70b` - Llama 3.3 70B Instruct (supports function calling)
+
+**Qwen Models:**
+- `qwen2.5-coder-32b` - Qwen 2.5 Coder 32B Instruct (supports function calling)
+- `qwen3-32b` - Qwen 3 32B (supports function calling)
+- `qwen3-coder-30b-a3b` - Qwen 3 Coder 30B A3B Instruct (supports function calling)
+- `qwen2.5-vl-72b` - Qwen 2.5 VL 72B Instruct (vision-language model)
+
+**Mistral Models:**
+- `mistral-7b` - Mistral 7B Instruct v0.3
+- `mistral-8x7b` - Mixtral 8x7B Instruct v0.1
+- `mistral-nemo` - Mistral Nemo Instruct 2407 (supports function calling)
+- `mistral-small-3.2-24b` - Mistral Small 3.2 24B Instruct (supports function calling)
+
+**OpenAI Models:**
+- `gpt-oss-20b` - GPT-OSS 20B (supports function calling)
+- `gpt-oss-120b` - GPT-OSS 120B (supports function calling)
+
+**DeepSeek Models:**
+- `DeepSeek-R1-Distill-Llama-70B` - DeepSeek R1 Distill Llama 70B (supports function calling)
+
+**Other Models:**
+- `codestral-mamba-latest` - Codestral Mamba 7B v0.1
+
+### Function Calling Support
+
+Many OVHcloud models support function calling (tool use), which enables the model to interact with external tools and APIs. Models with function calling support include:
+
+- Llama 3.1 8B, Llama 3.3 70B
+- All Qwen 3 models and Qwen 2.5 Coder
+- GPT-OSS 20B and 120B
+- DeepSeek R1 Distill Llama 70B
+- Mistral Small 3.2 24B, Mistral Nemo
+
+Function calling is automatically enabled for supported models when using Continue.
 
 <Tabs>
     <Tab title="YAML">
@@ -47,6 +90,43 @@ Check our [catalog](https://endpoints.ai.cloud.ovh.net/catalog) to see all of ou
     </Tab>
 </Tabs>
 
+### Example: Model with Function Calling
+
+Here's an example configuration for a model that supports function calling:
+
+<Tabs>
+    <Tab title="YAML">
+    ```yaml title="config.yaml"
+    name: My Config
+    version: 0.0.1
+    schema: v1
+
+    models:
+      - name: GPT-OSS-120B
+        provider: ovhcloud
+        model: gpt-oss-120b
+        apiKey: <YOUR_AIENDPOINTS_API_KEY>
+        capabilities:
+          - tool_use
+    ```
+    </Tab>
+    <Tab title="JSON">
+    ```json title="config.json"
+    {
+      "models": [
+        {
+          "title": "GPT-OSS-120B",
+          "provider": "ovhcloud",
+          "model": "gpt-oss-120b",
+          "apiKey": "<YOUR_AIENDPOINTS_API_KEY>",
+          "capabilities": ["tool_use"]
+        }
+      ]
+    }
+    ```
+    </Tab>
+</Tabs>
+
 ## Embeddings model
 
 We recommend configuring **bge-multilingual-gemma2** as your embeddings model.

extensions/vscode/config_schema.json

@@ -1414,10 +1414,16 @@
                       "llama3.1-70b",
                       "llama3.3-70b",
                       "qwen2.5-coder-32b",
+                      "qwen3-32b",
+                      "qwen3-coder-30b-a3b",
+                      "qwen2.5-vl-72b",
                       "codestral-mamba-latest",
                       "mistral-7b",
                       "mistral-8x7b",
                       "mistral-nemo",
+                      "mistral-small-3.2-24b",
+                      "gpt-oss-20b",
+                      "gpt-oss-120b",
                       "DeepSeek-R1-Distill-Llama-70B"
                     ]
                   },

gui/src/pages/AddNewModel/configs/models.ts

@@ -98,7 +98,24 @@ export const models: { [key: string]: ModelPackage } = {
       contextLength: 128_000,
     },
     icon: "openai.png",
-    providerOptions: ["vllm"],
+    dimensions: [
+      {
+        name: "Provider",
+        description: "The provider to use for this model",
+        options: {
+          vllm: {
+            model: "openai/gpt-oss-20b",
+            title: "gpt-oss-20b (vLLM)",
+          },
+          ovhcloud: {
+            model: "gpt-oss-20b",
+            title: "gpt-oss-20b (OVHcloud)",
+            contextLength: 131072,
+          },
+        },
+      },
+    ],
+    providerOptions: ["vllm", "ovhcloud"],
     isOpenSource: true,
   },
   gptOss120B: {
@@ -112,7 +129,24 @@ export const models: { [key: string]: ModelPackage } = {
       contextLength: 128_000,
     },
     icon: "openai.png",
-    providerOptions: ["vllm"],
+    dimensions: [
+      {
+        name: "Provider",
+        description: "The provider to use for this model",
+        options: {
+          vllm: {
+            model: "openai/gpt-oss-120b",
+            title: "gpt-oss-120b (vLLM)",
+          },
+          ovhcloud: {
+            model: "gpt-oss-120b",
+            title: "gpt-oss-120b (OVHcloud)",
+            contextLength: 131072,
+          },
+        },
+      },
+    ],
+    providerOptions: ["vllm", "ovhcloud"],
     isOpenSource: true,
   },
   llama318BChat: {
@@ -1896,6 +1930,49 @@ export const models: { [key: string]: ModelPackage } = {
     providerOptions: ["scaleway", "nebius", "ovhcloud", "ncompass"],
     isOpenSource: true,
   },
+  Qwen3Coder30BA3B: {
+    title: "Qwen 3 Coder 30B A3B",
+    description:
+      "Qwen3-Coder-30B-A3B-Instruct is Alibaba Cloud's advanced code-specialized LLM that excels in agentic coding tasks and supports extended context lengths for handling large code repositories.",
+    refUrl: "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct",
+    params: {
+      title: "Qwen 3 Coder 30B A3B",
+      model: "qwen3-coder-30b-a3b",
+      contextLength: 262144,
+    },
+    icon: "qwen.png",
+    providerOptions: ["ovhcloud"],
+    isOpenSource: true,
+  },
+  Qwen25VL72B: {
+    title: "Qwen 2.5 VL 72B",
+    description:
+      "Qwen2.5-VL is a powerful vision-language model, designed for advanced image understanding. It can generate detailed image captions, analyze documents, OCR, detect objects, and answer questions based on visuals.",
+    refUrl: "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct",
+    params: {
+      title: "Qwen 2.5 VL 72B",
+      model: "qwen2.5-vl-72b",
+      contextLength: 32768,
+    },
+    icon: "qwen.png",
+    providerOptions: ["ovhcloud"],
+    isOpenSource: true,
+  },
+  MistralSmall32: {
+    title: "Mistral Small 3.2 24B",
+    description:
+      "Building upon Mistral Small 3 (2501), Mistral Small 3.2 (2506) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.",
+    refUrl:
+      "https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506",
+    params: {
+      title: "Mistral Small 3.2 24B",
+      model: "mistral-small-3.2-24b",
+      contextLength: 131072,
+    },
+    icon: "mistral.png",
+    providerOptions: ["ovhcloud"],
+    isOpenSource: true,
+  },
   grokCodeFast1: {
     title: "Grok Code Fast 1",
     description:
@@ -2215,11 +2292,11 @@ export const models: { [key: string]: ModelPackage } = {
     description: "Qwen 3 32B model from Alibaba",
     params: {
       title: "Qwen 3 32B",
-      model: "Qwen3-32B",
-      contextLength: 8192,
+      model: "qwen3-32b",
+      contextLength: 32768,
     },
     icon: "qwen.png",
-    providerOptions: ["sambanova"],
+    providerOptions: ["sambanova", "ovhcloud"],
     isOpenSource: true,
   },
   gptOss120b: {

gui/src/pages/AddNewModel/configs/providers.ts

@@ -254,6 +254,12 @@ export const providers: Partial<Record<string, ProviderInfo>> = {
       models.mistralOs,
       models.mistralNemo,
       models.Qwen25Coder32b,
+      models.Qwen3Coder30BA3B,
+      models.Qwen25VL72B,
+      models.qwen332B,
+      models.MistralSmall32,
+      models.gptOss20B,
+      models.gptOss120B,
       models.deepseekR1DistillLlama70B,
     ],
     apiKeyUrl: "https://endpoints.ai.cloud.ovh.net/",