From 7558264fbc3cb74e7569d19c827c11bb90edc26b Mon Sep 17 00:00:00 2001 From: Quentin Maire Date: Mon, 6 Oct 2025 11:48:29 +0200 Subject: [PATCH 1/4] EN update virtual model doc to highlight its dynamicity --- .../guide.en-gb.md | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) 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..1153b8a56ae 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 @@ -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. From 5707eb59f6fabf942e063ee82bf391e31faf9542 Mon Sep 17 00:00:00 2001 From: Quentin Maire Date: Mon, 6 Oct 2025 11:53:50 +0200 Subject: [PATCH 2/4] FR update virtual model doc to highlight its dynamicity --- .../guide.fr-fr.md | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) 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..831c728b208 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 @@ -42,6 +42,11 @@ Follow the instructions in the [AI Endpoints - Getting Started](/pages/public_cl ## Model DSL +> [!warning] +> +> La fonctionnalité de modèle virtuel permettant de changer dynamiquement de modèle, les caractéristiques du modèle (telles que le prix ou la taille du contexte) peuvent évoluer lorsqu'un modèle plus récent sera sélectionné pour traiter votre requête. Pour garantir le maintien de certaines caractéristiques, vous pouvez les verrouiller en utilisant les conditions de requête indiquées ci-dessous +> + 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 | **Exemple:** Qwen3-32B | The most recently released model optimized for code chat tasks | +| meta-llama@latest | **Exemple:** Llama-3.1-8B-Instruct | The latest Meta-released LLaMA model | +| mistral@latest?context_size > 100000 | **Exemple:** 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 | **Exemple:** 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. From 5ef2c5af01dc6434a3227330b9cdebc7d6021ada Mon Sep 17 00:00:00 2001 From: Yoann Cosse Date: Mon, 6 Oct 2025 14:24:41 +0200 Subject: [PATCH 3/4] Proofreading --- .../guide.en-gb.md | 2 +- .../guide.fr-fr.md | 15 +++++++-------- 2 files changed, 8 insertions(+), 9 deletions(-) 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 1153b8a56ae..04a92cbc2d0 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: 2025-10-06 --- > [!primary] 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 831c728b208..1f653c5cf98 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: 2025-10-06 --- > [!primary] @@ -44,7 +44,7 @@ Follow the instructions in the [AI Endpoints - Getting Started](/pages/public_cl > [!warning] > -> La fonctionnalité de modèle virtuel permettant de changer dynamiquement de modèle, les caractéristiques du modèle (telles que le prix ou la taille du contexte) peuvent évoluer lorsqu'un modèle plus récent sera sélectionné pour traiter votre requête. Pour garantir le maintien de certaines caractéristiques, vous pouvez les verrouiller en utilisant les conditions de requête indiquées ci-dessous +> 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. @@ -59,10 +59,10 @@ Below are some example queries and the models they currently resolve to. Please | Model Query | Current Target Model | Usage | |-----------|-----------|-----------| -| code_chat@latest | **Exemple:** Qwen3-32B | The most recently released model optimized for code chat tasks | -| meta-llama@latest | **Exemple:** Llama-3.1-8B-Instruct | The latest Meta-released LLaMA model | -| mistral@latest?context_size > 100000 | **Exemple:** 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 | **Exemple:** 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. @@ -146,5 +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 From 3dc321603354c9c2010f9a0151447124970cdf91 Mon Sep 17 00:00:00 2001 From: Yoann Cosse Date: Mon, 6 Oct 2025 14:26:05 +0200 Subject: [PATCH 4/4] Date update --- .../endpoints_guide_07_virtual_models/guide.en-gb.md | 2 +- .../endpoints_guide_07_virtual_models/guide.fr-fr.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) 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 04a92cbc2d0..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: 2025-10-06 +updated: 2025-10-12 --- > [!primary] 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 1f653c5cf98..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: 2025-10-06 +updated: 2025-10-12 --- > [!primary]