{"id":2206,"date":"2026-04-08T08:24:57","date_gmt":"2026-04-08T06:24:57","guid":{"rendered":"https:\/\/askem.eu\/?p=2206"},"modified":"2026-04-08T08:28:07","modified_gmt":"2026-04-08T06:28:07","slug":"litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud","status":"publish","type":"post","link":"https:\/\/askem.eu\/en\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/","title":{"rendered":"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud"},"content":{"rendered":"

LiteLLM : un proxy unifi\u00e9 pour router ses requ\u00eates LLM entre Ollama, vLLM et le cloud<\/h2>\n\n\n\n

Quand on auto-h\u00e9berge plusieurs backends LLM : Ollama pour le prototypage : vLLM pour la production GPU, un acc\u00e8s Claude ou GPT pour les cas complexes, la multiplication des endpoints et formats d’API devient vite un cauchemar d’int\u00e9gration. LiteLLM<\/a><\/strong> r\u00e9sout ce probl\u00e8me en exposant une API unique compatible OpenAI qui route intelligemment les requ\u00eates vers plus de 100 fournisseurs. C’est la couche d’abstraction qui manque entre applications et mod\u00e8les.<\/p>\n\n\n\n

Pourquoi un proxy LLM ?<\/h3>\n\n\n\n

Dans une stack IA auto-h\u00e9berg\u00e9e typique, chaque backend a son propre format d’appel, sa propre gestion des tokens, ses propres limites de d\u00e9bit. Vos applications (Open WebUI, n8n, agents MCP, scripts Python) doivent conna\u00eetre chaque endpoint. Ajouter un nouveau mod\u00e8le signifie modifier chaque client. LiteLLM inverse cette logique : vos applications parlent \u00e0 un seul endpoint, et le proxy se charge du reste : traduction de format, load balancing, fallback automatique, et suivi de consommation.<\/p>\n\n\n\n

Architecture et fonctionnement<\/h3>\n\n\n\n

LiteLLM se d\u00e9ploie comme un serveur proxy l\u00e9ger (Python\/Docker) qui intercepte les appels au format OpenAI \/v1\/chat\/completions<\/code> et les traduit vers le backend cible. La configuration se fait via un fichier YAML d\u00e9claratif :<\/p>\n\n\n\n

model_list:\n  - model_name: \"mistral-local\"\n    litellm_params:\n      model: \"ollama\/mistral:7b\"\n      api_base: \"http:\/\/ollama:11434\"\n\n  - model_name: \"llama-prod\"\n    litellm_params:\n      model: \"hosted_vllm\/meta-llama\/Llama-3.1-70B\"\n      api_base: \"http:\/\/vllm:8000\/v1\"\n\n  - model_name: \"claude-fallback\"\n    litellm_params:\n      model: \"claude-sonnet-4-20250514\"\n      api_key: \"os.environ\/ANTHROPIC_API_KEY\"\n\nrouter_settings:\n  routing_strategy: \"least-busy\"\n  num_retries: 3\n  fallbacks:\n    - llama-prod: [\"mistral-local\", \"claude-fallback\"]<\/code><\/pre>\n\n\n\n
Avec cette configuration, une requ\u00eate vers llama-prod<\/code> est envoy\u00e9e \u00e0 vLLM. Si vLLM est indisponible, LiteLLM bascule automatiquement sur Ollama, puis sur Claude en dernier recours, le tout transparent pour l’application appelante.<\/p>\n\n\n\n
D\u00e9ploiement Docker dans une stack existante<\/h3>\n\n\n\n
# docker-compose.yml (extrait)\nservices:\n  litellm:\n    image: ghcr.io\/berriai\/litellm:main-latest\n    ports:\n      - \"4000:4000\"\n    volumes:\n      - .\/litellm-config.yaml:\/app\/config.yaml\n    environment:\n      - LITELLM_MASTER_KEY=sk-votre-cle-admin\n      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}\n      - DATABASE_URL=postgresql:\/\/user:pass@db:5432\/litellm\n    command: [\"--config\", \"\/app\/config.yaml\", \"--port\", \"4000\"]\n    depends_on:\n      - db\n\n  db:\n    image: postgres:16-alpine\n    environment:\n      POSTGRES_DB: litellm\n      POSTGRES_USER: user\n      POSTGRES_PASSWORD: pass\n    volumes:\n      - litellm-db:\/var\/lib\/postgresql\/data<\/code><\/pre>\n\n\n\n
LiteLLM utilise PostgreSQL pour persister la configuration des cl\u00e9s virtuelles, les logs de requ\u00eates et les budgets. L’interface d’administration web (port 4000) permet de g\u00e9rer les mod\u00e8les, cr\u00e9er des cl\u00e9s API par utilisateur ou par \u00e9quipe, et visualiser les m\u00e9triques de consommation en temps r\u00e9el.<\/p>\n\n\n\n
Fonctionnalit\u00e9s cl\u00e9s pour une infrastructure auto-h\u00e9berg\u00e9e<\/h3>\n\n\n\n
Cl\u00e9s virtuelles et budgets<\/strong> \u2014 Cr\u00e9ez des cl\u00e9s API par projet ou par utilisateur avec des limites de d\u00e9pense mensuelles. Id\u00e9al pour partager l’acc\u00e8s \u00e0 des mod\u00e8les cloud sans exposer vos cl\u00e9s API r\u00e9elles. Chaque cl\u00e9 peut \u00eatre restreinte \u00e0 certains mod\u00e8les.<\/p>\n\n\n\n
Load balancing et fallbacks<\/strong> \u2014 R\u00e9partissez la charge entre plusieurs instances d’un m\u00eame mod\u00e8le (round-robin, least-busy, latency-based). D\u00e9finissez des cha\u00eenes de fallback pour garantir la disponibilit\u00e9 : si votre GPU locale est satur\u00e9e, la requ\u00eate bascule vers le cloud.<\/p>\n\n\n\n
Guardrails et mod\u00e9ration<\/strong> \u2014 Int\u00e9grez des filtres de contenu (Presidio pour la d\u00e9tection PII, LlamaGuard, r\u00e8gles personnalis\u00e9es) directement dans le proxy. Les requ\u00eates sont analys\u00e9es avant d’atteindre le mod\u00e8le, ce qui centralise la politique de s\u00e9curit\u00e9 ind\u00e9pendamment des applications clientes.<\/p>\n\n\n\n
Observabilit\u00e9 native<\/strong> \u2014 LiteLLM expose des m\u00e9triques Prometheus (latence, tokens, co\u00fbts, erreurs) et supporte l’envoi de logs vers Langfuse, OpenTelemetry ou un simple callback. Combin\u00e9 avec Grafana (d\u00e9j\u00e0 en place si vous suivez le guide observabilit\u00e9), vous obtenez un tableau de bord complet de votre consommation LLM.<\/p>\n\n\n\n
Int\u00e9gration dans la stack askem<\/h3>\n\n\n\n
Voici comment LiteLLM s’ins\u00e8re dans une architecture type d\u00e9j\u00e0 en place :<\/p>\n\n\n\n
Applications (Open WebUI, n8n, agents MCP, scripts)\n        \u2502\n        \u25bc\n   \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n   \u2502  LiteLLM    \u2502  \u2190 API unique OpenAI-compatible (:4000)\n   \u2502  Proxy      \u2502  \u2190 Cl\u00e9s virtuelles, budgets, guardrails\n   \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u252c\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n          \u2502\n    \u250c\u2500\u2500\u2500\u2500\u2500\u253c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n    \u25bc     \u25bc          \u25bc\n Ollama  vLLM    Claude API\n (:11434) (:8000)  (cloud)\n    \u2502     \u2502\n    \u25bc     \u25bc\n  CPU    GPU<\/code><\/pre>\n\n\n\n
Open WebUI n’a plus besoin de conna\u00eetre Ollama directement \u2014 il pointe vers http:\/\/litellm:4000\/v1<\/code> et voit tous les mod\u00e8les disponibles. n8n utilise le m\u00eame endpoint. Vos agents MCP aussi. Un seul point de configuration, un seul jeu de m\u00e9triques, une seule politique de s\u00e9curit\u00e9.<\/p>\n\n\n\n
Cas d’usage concret : routage par complexit\u00e9<\/h3>\n\n\n\n
Un pattern puissant rendu possible par LiteLLM est le routage conditionnel. En configurant plusieurs mod\u00e8les sous le m\u00eame alias avec des priorit\u00e9s diff\u00e9rentes, vous pouvez diriger les requ\u00eates simples vers un petit mod\u00e8le local rapide (Mistral 7B sur Ollama) et r\u00e9server le mod\u00e8le lourd (Llama 70B sur vLLM ou Claude en cloud) aux requ\u00eates n\u00e9cessitant un raisonnement complexe. C\u00f4t\u00e9 application, un simple header x-litellm-model<\/code> ou un tag dans le prompt suffit \u00e0 orienter le routage.<\/p>\n\n\n\n
Pour aller plus loin<\/h3>\n\n\n\n
LiteLLM est un projet open source actif<\/a> (licence MIT, plus de 18 000 \u00e9toiles sur GitHub). La documentation officielle couvre l’int\u00e9gration avec Keycloak pour le SSO admin, le d\u00e9ploiement sur Kubernetes via Helm, et la configuration avanc\u00e9e des guardrails. Pour une stack auto-h\u00e9berg\u00e9e qui grandit, c’est la brique de routage qui transforme un ensemble de mod\u00e8les disparates en une plateforme LLM unifi\u00e9e et gouvern\u00e9e.<\/p>","protected":false},"excerpt":{"rendered":"
LiteLLM : un proxy unifi\u00e9 pour router ses requ\u00eates LLM entre Ollama, vLLM et le cloud Quand on auto-h\u00e9berge plusieurs backends LLM : Ollama pour le prototypage : vLLM pour la production GPU, un acc\u00e8s Claude ou GPT pour les cas complexes, la multiplication des endpoints et formats d’API devient vite un cauchemar d’int\u00e9gration. LiteLLM r\u00e9sout ce probl\u00e8me […]<\/p>\n","protected":false},"author":1,"featured_media":2207,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","osh_disable_topbar_sticky":"default","osh_disable_header_sticky":"default","osh_sticky_header_style":"default","osh_sticky_header_effect":"","osh_custom_sticky_logo":0,"osh_custom_retina_sticky_logo":0,"osh_custom_sticky_logo_height":0,"osh_background_color":"","osh_links_color":"","osh_links_hover_color":"","osh_links_active_color":"","osh_links_bg_color":"","osh_links_hover_bg_color":"","osh_links_active_bg_color":"","osh_menu_social_links_color":"","osh_menu_social_hover_links_color":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[16],"tags":[],"class_list":["post-2206","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","entry","has-media"],"yoast_head":"\nLiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud - askem<\/title>\n<meta name=\"description\" content=\"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/askem.eu\/en\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud - askem\" \/>\n<meta property=\"og:description\" content=\"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/askem.eu\/en\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/\" \/>\n<meta property=\"og:site_name\" content=\"askem\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/fb.me\/askem.eu\" \/>\n<meta property=\"article:published_time\" content=\"2026-04-08T06:24:57+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-08T06:28:07+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/04\/sujet-askem-2026-04-07.png\" \/>\n\t<meta property=\"og:image:width\" content=\"900\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"askemadmin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"askemadmin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/\"},\"author\":{\"name\":\"askemadmin\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/person\\\/8bbee74ab9a977d56bf4826662e9d2e9\"},\"headline\":\"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud\",\"datePublished\":\"2026-04-08T06:24:57+00:00\",\"dateModified\":\"2026-04-08T06:28:07+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/\"},\"wordCount\":765,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/04\\/sujet-askem-2026-04-07.png\",\"articleSection\":[\"AI\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/\",\"url\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/\",\"name\":\"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud - askem\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/04\\/sujet-askem-2026-04-07.png\",\"datePublished\":\"2026-04-08T06:24:57+00:00\",\"dateModified\":\"2026-04-08T06:28:07+00:00\",\"description\":\"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#primaryimage\",\"url\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/04\\/sujet-askem-2026-04-07.png\",\"contentUrl\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/04\\/sujet-askem-2026-04-07.png\",\"width\":900,\"height\":600},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/04\\\/08\\\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\\\/\\\/askem.eu\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#website\",\"url\":\"https:\\\/\\\/askem.eu\\\/\",\"name\":\"askem\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/askem.eu\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#organization\",\"name\":\"Askem\",\"url\":\"https:\\\/\\\/askem.eu\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\/\\/mlpi0fxo3sth.i.optimole.com\\/cb:3obA.c61\\/w:760\\/h:480\\/q:mauto\\/f:best\\/https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2020\\/10\\/logoGalaxieAskem3.png\",\"contentUrl\":\"https:\\/\\/mlpi0fxo3sth.i.optimole.com\\/cb:3obA.c61\\/w:760\\/h:480\\/q:mauto\\/f:best\\/https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2020\\/10\\/logoGalaxieAskem3.png\",\"width\":760,\"height\":480,\"caption\":\"Askem\"},\"image\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/fb.me\\\/askem.eu\",\"https:\\\/\\\/linkedin.com\\\/company\\\/askem-eu\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/person\\\/8bbee74ab9a977d56bf4826662e9d2e9\",\"name\":\"askemadmin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g\",\"caption\":\"askemadmin\"},\"sameAs\":[\"https:\\\/\\\/askem.eu\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud - askem","description":"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/askem.eu\/en\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/","og_locale":"en_US","og_type":"article","og_title":"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud - askem","og_description":"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.","og_url":"https:\/\/askem.eu\/en\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/","og_site_name":"askem","article_publisher":"https:\/\/fb.me\/askem.eu","article_published_time":"2026-04-08T06:24:57+00:00","article_modified_time":"2026-04-08T06:28:07+00:00","og_image":[{"width":900,"height":600,"url":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/04\/sujet-askem-2026-04-07.png","type":"image\/png"}],"author":"askemadmin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"askemadmin","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#article","isPartOf":{"@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/"},"author":{"name":"askemadmin","@id":"https:\/\/askem.eu\/#\/schema\/person\/8bbee74ab9a977d56bf4826662e9d2e9"},"headline":"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud","datePublished":"2026-04-08T06:24:57+00:00","dateModified":"2026-04-08T06:28:07+00:00","mainEntityOfPage":{"@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/"},"wordCount":765,"commentCount":0,"publisher":{"@id":"https:\/\/askem.eu\/#organization"},"image":{"@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#primaryimage"},"thumbnailUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/04\/sujet-askem-2026-04-07.png","articleSection":["AI"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/","url":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/","name":"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud - askem","isPartOf":{"@id":"https:\/\/askem.eu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#primaryimage"},"image":{"@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#primaryimage"},"thumbnailUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/04\/sujet-askem-2026-04-07.png","datePublished":"2026-04-08T06:24:57+00:00","dateModified":"2026-04-08T06:28:07+00:00","description":"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.","breadcrumb":{"@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#primaryimage","url":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/04\/sujet-askem-2026-04-07.png","contentUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/04\/sujet-askem-2026-04-07.png","width":900,"height":600},{"@type":"BreadcrumbList","@id":"https:\/\/askem.eu\/2026\/04\/08\/litellm-un-proxy-unifie-pour-router-ses-requetes-llm-entre-ollama-vllm-et-le-cloud\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/askem.eu\/"},{"@type":"ListItem","position":2,"name":"LiteLLM : un proxy unifie pour router ses requetes LLM entre Ollama, vLLM et le cloud"}]},{"@type":"WebSite","@id":"https:\/\/askem.eu\/#website","url":"https:\/\/askem.eu\/","name":"askem","description":"","publisher":{"@id":"https:\/\/askem.eu\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/askem.eu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/askem.eu\/#organization","name":"Askem","url":"https:\/\/askem.eu\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/askem.eu\/#\/schema\/logo\/image\/","url":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:760\/h:480\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2020\/10\/logoGalaxieAskem3.png","contentUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:760\/h:480\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2020\/10\/logoGalaxieAskem3.png","width":760,"height":480,"caption":"Askem"},"image":{"@id":"https:\/\/askem.eu\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/fb.me\/askem.eu","https:\/\/linkedin.com\/company\/askem-eu"]},{"@type":"Person","@id":"https:\/\/askem.eu\/#\/schema\/person\/8bbee74ab9a977d56bf4826662e9d2e9","name":"askemadmin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g","caption":"askemadmin"},"sameAs":["https:\/\/askem.eu"]}]}},"_links":{"self":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts\/2206","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/comments?post=2206"}],"version-history":[{"count":2,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts\/2206\/revisions"}],"predecessor-version":[{"id":2211,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts\/2206\/revisions\/2211"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/media\/2207"}],"wp:attachment":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/media?parent=2206"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/categories?post=2206"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/tags?post=2206"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}