diff --git a/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.en-gb.md b/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.en-gb.md index 4eaf43c6b4a..9ad40817d30 100644 --- a/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.en-gb.md +++ b/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.en-gb.md @@ -1,7 +1,7 @@ --- title: AI Endpoints - Using Virtual Models excerpt: Learn how to use OVHcloud AI Endpoints Virtual Models -updated: 2025-08-18 +updated: 2025-10-12 --- > [!primary] @@ -42,6 +42,11 @@ Follow the instructions in the [AI Endpoints - Getting Started](/pages/public_cl ## Model DSL +> [!warning] +> +> As our virtual model feature allows dynamic model switching, the model’s characteristics (including pricing or context size) may change when a newer model is selected to handle your query. If you prefer certain features to remain fixed, you can lock them using the query conditions listed below. +> + When you request an LLM generation through our unified endpoint, you can provide in the OpenAI-compliant `model` field a model DSL query instead of a hardcoded model name. These queries are divided into three parts: tag, ranker, and condition: @@ -54,10 +59,10 @@ Below are some example queries and the models they currently resolve to. Please | Model Query | Current Target Model | Usage | |-----------|-----------|-----------| -| code_chat@latest | Qwen3-32B | The most recently released model optimized for code chat tasks | -| meta-llama@latest | Llama-3.1-8B-Instruct | The latest Meta-released LLaMA model | -| mistral@latest?context_size > 100000 | Mistral-Small-3.2-24B-Instruct-2506 | The latest Mistral model with a context window greater than 100k tokens | -| llama@biggest?input_cost<0.5 | Llama-3.1-8B-Instruct | The largest LLaMA model whose input token cost is under €0.50 per 1M tokens | +| code_chat@latest | **Example:** Qwen3-32B | The most recently released model optimized for code chat tasks | +| meta-llama@latest | **Example:** Llama-3.1-8B-Instruct | The latest Meta-released LLaMA model | +| mistral@latest?context_size > 100000 | **Example:** Mistral-Small-3.2-24B-Instruct-2506 | The latest Mistral model with a context window greater than 100k tokens | +| llama@biggest?input_cost<0.5 | **Example:** Llama-3.1-8B-Instruct | The largest LLaMA model whose input token cost is under €0.50 per 1M tokens | You can visit our [catalog](https://endpoints.ai.cloud.ovh.net/catalog) to learn more about the different model specifications. diff --git a/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.fr-fr.md b/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.fr-fr.md index 8c6490770fe..e6984e4c4f2 100644 --- a/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.fr-fr.md +++ b/pages/public_cloud/ai_machine_learning/endpoints_guide_07_virtual_models/guide.fr-fr.md @@ -1,7 +1,7 @@ --- title: AI Endpoints - Modèles virtuels excerpt: "Découvrez comment utiliser les modèles virtuels d'AI Endpoints" -updated: 2025-08-18 +updated: 2025-10-12 --- > [!primary] @@ -42,6 +42,11 @@ Follow the instructions in the [AI Endpoints - Getting Started](/pages/public_cl ## Model DSL +> [!warning] +> +> As our virtual model feature allows dynamic model switching, the model’s characteristics (including pricing or context size) may change when a newer model is selected to handle your query. If you prefer certain features to remain fixed, you can lock them using the query conditions listed below. +> + When you request an LLM generation through our unified endpoint, you can provide in the OpenAI-compliant `model` field a model DSL query instead of a hardcoded model name. These queries are divided into three parts: tag, ranker, and condition: @@ -54,10 +59,10 @@ Below are some example queries and the models they currently resolve to. Please | Model Query | Current Target Model | Usage | |-----------|-----------|-----------| -| code_chat@latest | Qwen3-32B | The most recently released model optimized for code chat tasks | -| meta-llama@latest | Llama-3.1-8B-Instruct | The latest Meta-released LLaMA model | -| mistral@latest?context_size > 100000 | Mistral-Small-3.2-24B-Instruct-2506 | The latest Mistral model with a context window greater than 100k tokens | -| llama@biggest?input_cost<0.5 | Llama-3.1-8B-Instruct | The largest LLaMA model whose input token cost is under €0.50 per 1M tokens | +| code_chat@latest | **Example:** Qwen3-32B | The most recently released model optimized for code chat tasks | +| meta-llama@latest | **Example:** Llama-3.1-8B-Instruct | The latest Meta-released LLaMA model | +| mistral@latest?context_size > 100000 | **Example:** Mistral-Small-3.2-24B-Instruct-2506 | The latest Mistral model with a context window greater than 100k tokens | +| llama@biggest?input_cost<0.5 | **Example:** Llama-3.1-8B-Instruct | The largest LLaMA model whose input token cost is under €0.50 per 1M tokens | You can visit our [catalog](https://endpoints.ai.cloud.ovh.net/catalog) to learn more about the different model specifications. @@ -141,5 +146,4 @@ If you need training or technical assistance to implement our solutions, contact Please send us your questions, feedback and suggestions to improve the service: -- On the OVHcloud [Discord server](https://discord.gg/ovhcloud). - +- On the OVHcloud [Discord server](https://discord.gg/ovhcloud). \ No newline at end of file