Aller au contenu
Alpha
  • Modèles
  • Classements
  • Ori
Contacter l’équipe commerciale

Pied de page

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Produit

  • Chat
  • Classements
  • Évaluations comparatives
  • Applications
  • Découvrir
  • Modèles
  • Ori
  • Collections
  • Fournisseurs
  • Outils
  • Tarifs
  • Business
  • Enterprise
  • Laboratoire

Entreprise

  • À propos
  • Blog
  • Clients
  • Carrières
    Recrutement
  • Confidentialité
  • Conditions d’utilisation
  • Centre de confiance
  • Assistance
  • Compatible avec OR
  • Données
  • Marque

Développeur

  • Documentation
  • Référence de l’API
  • Plateforme pour développeurs
  • Statut
  • Plan du site pour l’IA

Connecter

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon de openai

OpenAI: GPT-5

openai/gpt-5

Comparer

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

Modalités
Prix en entrée / sortie
1,25 $US / 10 $USpar 1M
Contexte
400K
Publié
7 août 2025
Date limite des connaissances
sept. 2024
Comparer
FournisseursTarificationPerformancesDisponibilitéÉvaluations comparativesApplicationsActivitéDocumentationFAQExplorer

Fournisseurs

Différentes entreprises hébergent le même modèle. OpenRouter achemine votre requête vers l’une d’elles selon le mode de routage choisi — Balanced (prix + vitesse), Nitro (le plus rapide) ou Floor (le moins cher).

Tarification

Le prix moyen que les clients paient réellement pour ce modèle, à côté des prix affichés par les fournisseurs. Grâce à la mise en cache et aux remises, le prix réellement payé est souvent bien inférieur au prix affiché.

Performances

Le débit est la vitesse à laquelle le modèle écrit (jetons par seconde — plus il est élevé, mieux c’est). La latence est le temps total d’aller-retour (plus il est faible, mieux c’est). Le TTFT est le délai avant le premier jeton — le temps avant de voir quelque chose apparaître (plus il est faible, mieux c’est).

Disponibilité

La disponibilité correspond au pourcentage des 3 derniers jours pendant lequel au moins un fournisseur répondait aux requêtes. La disponibilité du service correspond au pourcentage de temps pendant lequel l’inférence a été assurée avec succès. OpenRouter surveille en continu les fournisseurs et utilise le meilleur fournisseur suivant lorsque l’un d’eux renvoie une erreur.

Évaluations comparatives

Scores aux évaluations standardisées et réponses de ce modèle aux prompts communs des tests de référence. Des pourcentages plus élevés sont meilleurs — et chaque rang indique la position de ce modèle parmi les modèles évalués sur cette source.

Résumé des scores aux tests de performance pour OpenAI: GPT-5 (Artificial Analysis, Design Arena et Vals AI)
SourceTest de performanceScore
Artificial AnalysisGPT-5 (High) Coding Index37,8
Artificial AnalysisGPT-5 (High) GPQA Diamond85.4%
Artificial AnalysisGPT-5 (High) HLE28.5%
Artificial AnalysisGPT-5 (High) IFBench73.1%
Artificial AnalysisGPT-5 (High) τ²-Bench Telecom84.8%
Artificial AnalysisGPT-5 (High) AA-LCR78.2%
Artificial AnalysisGPT-5 (High) τ-Bench Banking22.1%
Artificial AnalysisGPT-5 (High) GDPval-AA21.3%
Artificial AnalysisGPT-5 (High) CritPt5.7%
Artificial AnalysisGPT-5 (High) LiveCodeBench84.6%
Artificial AnalysisGPT-5 (High) Terminal-Bench Hard32.6%
Artificial AnalysisGPT-5 (High) Terminal-Bench 2.135.2%
Artificial AnalysisGPT-5 (High) MMLU-Pro87.1%
Artificial AnalysisGPT-5 (High) AIME 202594.3%
Artificial AnalysisGPT-5 (High) AIME95.7%
Artificial AnalysisGPT-5 (High) MATH-50099.4%
Artificial AnalysisGPT-5 (Low) GPQA Diamond80.8%
Artificial AnalysisGPT-5 (Low) HLE19.6%
Artificial AnalysisGPT-5 (Low) IFBench66.6%
Artificial AnalysisGPT-5 (Low) τ²-Bench Telecom84.2%
Artificial AnalysisGPT-5 (Low) CritPt1.1%
Artificial AnalysisGPT-5 (Low) LiveCodeBench76.3%
Artificial AnalysisGPT-5 (Low) Terminal-Bench Hard26.5%
Artificial AnalysisGPT-5 (Low) MMLU-Pro86.0%
Artificial AnalysisGPT-5 (Low) AIME 202583.0%
Artificial AnalysisGPT-5 (Low) AIME83.0%
Artificial AnalysisGPT-5 (Low) MATH-50098.7%
Artificial AnalysisGPT-5 (Medium) GPQA Diamond84.2%
Artificial AnalysisGPT-5 (Medium) HLE25.4%
Artificial AnalysisGPT-5 (Medium) IFBench70.6%
Artificial AnalysisGPT-5 (Medium) τ²-Bench Telecom86.5%
Artificial AnalysisGPT-5 (Medium) AA-LCR76.0%
Artificial AnalysisGPT-5 (Medium) CritPt0.0%
Artificial AnalysisGPT-5 (Medium) LiveCodeBench70.3%
Artificial AnalysisGPT-5 (Medium) Terminal-Bench Hard37.9%
Artificial AnalysisGPT-5 (Medium) MMLU-Pro86.7%
Artificial AnalysisGPT-5 (Medium) AIME 202591.7%
Artificial AnalysisGPT-5 (Medium) AIME91.7%
Artificial AnalysisGPT-5 (Medium) MATH-50099.1%
Artificial AnalysisGPT-5 (Minimal) GPQA Diamond67.3%
Artificial AnalysisGPT-5 (Minimal) HLE6.0%
Artificial AnalysisGPT-5 (Minimal) IFBench45.6%
Artificial AnalysisGPT-5 (Minimal) τ²-Bench Telecom67.0%
Artificial AnalysisGPT-5 (Minimal) CritPt0.0%
Artificial AnalysisGPT-5 (Minimal) LiveCodeBench55.8%
Artificial AnalysisGPT-5 (Minimal) Terminal-Bench Hard18.2%
Artificial AnalysisGPT-5 (Minimal) MMLU-Pro80.6%
Artificial AnalysisGPT-5 (Minimal) AIME 202531.7%
Artificial AnalysisGPT-5 (Minimal) AIME36.7%
Artificial AnalysisGPT-5 (Minimal) MATH-50086.1%
Design ArenaGPT-5 (Minimal) Models Arena 3D Elo1053
Design ArenaGPT-5 (Minimal) Models Arena Asciiart Elo1138
Design ArenaGPT-5 (Minimal) Models Arena Code Categories Elo1163
Design ArenaGPT-5 (Minimal) Models Arena Data Visualization Elo1176
Design ArenaGPT-5 (Minimal) Models Arena Game Development Elo1153
Design ArenaGPT-5 (Minimal) Models Arena SVG Elo1124
Design ArenaGPT-5 (Minimal) Models Arena UI Component Elo1139
Design ArenaGPT-5 (Minimal) Models Arena Website Elo1183
Vals AIGPT 5 AIME93.4%
Vals AIGPT 5 CaseLaw v266.5%
Vals AIGPT 5 CorpFin v261.1%
Vals AIGPT 5 Finance Agent v1.152.2%
Vals AIGPT 5 GPQA Diamond85.6%
Vals AIGPT 5 IOI v120.0%
Vals AIGPT 5 LiveCodeBench85.9%
Vals AIGPT 5 LegalBench86.0%
Vals AIGPT 5 MATH 50096.0%
Vals AIGPT 5 MedCode49.6%
Vals AIGPT 5 MedQA96.3%
Vals AIGPT 5 MedScribe83.7%
Vals AIGPT 5 MGSM92.8%
Vals AIGPT 5 MMLU Pro86.5%
Vals AIGPT 5 MMMU Pro81.5%
Vals AIGPT 5 MortgageTax65.5%
Vals AIGPT 5 ProofBench v118.0%
Vals AIGPT 5 SAGE v143.7%
Vals AIGPT 5 SWE-bench69.0%
Vals AIGPT 5 TaxEval v273.4%
Vals AIGPT 5 Terminal-Bench 2.037.1%
Vals AIGPT 5 Vals Index49.0%
Vals AIGPT 5 Vals Multimodal Index49.9%
Vals AIGPT 5 Vibe Code Bench v1.120.1%

Applications

Applications publiques qui envoient le plus de trafic à ce modèle. Un bon indicateur des charges de travail réelles en production — et un aperçu des cas d’usage auxquels ce modèle convient le mieux.

Activité

Volume de jetons et trafic des requêtes vers ce modèle au fil du temps.

API

Code prêt à l’emploi pour appeler ce modèle. L’API d’OpenRouter est compatible avec OpenAI — la plupart des SDK fonctionnent en remplaçant simplement l’URL de base. Seul le slug du modèle ci-dessous change d’un modèle à l’autre.

Disponible via le routage au sein de la région UE

OpenAI: GPT-5 est disponible via le routage intrarégional dans l’UE. Les requêtes envoyées à eu.openrouter.ai sont déchiffrées dans l’UE et acheminées uniquement vers des points de terminaison partagés de fournisseurs en Europe (UE/EEE, Royaume-Uni et Suisse).

Fournisseurs en Europe
Azure
Tarifs en Europe
  • Azure : 1,375 $US/M tokens en entrée, 11 $US/M tokens en sortie
URL de base
https://eu.openrouter.ai/api/v1
Offre
Nécessite Business ou Enterprise. En libre-service avec Business : sans contrat ni minimum mensuel. OpenRouter Business pour le routage au sein de l’UE

Blocage en cas d’échec : si aucun point de terminaison de fournisseur partagé en Europe n’est disponible, la requête renvoie une erreur au lieu de quitter la région. Les requêtes traitées avec votre propre clé BYOK sont acheminées vers la région de votre déploiement, que vous contrôlez. Documentation sur le routage intrarégional

Documentation

Guides, recueils de recettes, articles de blog et outils pour développer avec OpenAI: GPT-5 sur OpenRouter.

  • GPT-5 is now live Article de blog

Explorer d’autres modèles

Modèles d’IA avec vision : LLM multimodaux pour la compréhension d’imagesCollectionClassements des modèles d’IAClassement
Latence / débit
1,250 $US10,00 $US0,1250 $US5,83s53 tps
100,00 %
1,250 $US10,00 $US0,1250 $US4,21s80 tps
100,00 %
Non utilisé pour le routage Standard :Pourquoi ces points de terminaison ne sont pas utilisés
1,375 $US11,00 $US0,1375 $US9,95s37 tps
98,44 %
Débit
80jetons/s

P50, meilleur résultat tous fournisseurs confondus

Latence
4,21s

P50, meilleur fournisseur

Évaluations comparatives AutoExacto
TAU-BenchOpenAI70,7 %
Disponibilité (3 j)Le modèle était joignable. Requête acheminée vers un fournisseur.
100,00 %
Disponibilité (3 j)Le modèle a renvoyé un résultat d’inférence, quel que soit le fournisseur. Les erreurs et les réponses vides sont comptabilisées à son détriment.
99,90 %

Disponibilité au cours des 3 derniers jours

72 dernières heures
Disponibilité 99,90 %
Il y a 3 joursIl y a 2 joursHierMaintenant

Disponibilité au cours des dernières 24 heures

OpenRouter Availability
99,96 %
Without Routing
99,45 %

Lorsqu’une erreur survient chez un fournisseur en amont, nous pouvons rétablir le service en routant la requête vers un autre fournisseur opérationnel, si les filtres de votre requête le permettent. Vous pouvez accéder par programmation aux données de disponibilité de chaque fournisseur via l’ API des points de terminaison. Découvrez nos options d’ équilibrage de charge et de routage des fournisseurs.

1.
Favicon de https://smp.followthewhiterabbit.tech/
Supernova Worker
nouveau
1,07Bjetons
2.
Favicon de https://sparkfire.ai/
Sparkfire
nouveau
932Mjetons
3.
Favicon de https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
778Mjetons
4.
Favicon de https://build.chipp.ai/
Chipp
nouveau
644Mjetons
5.
Favicon de https://thevisa.com/
Lead Phase Builder
nouveau
622Mjetons

Questions fréquentes

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases.

La documentation de GPT-5 sur OpenRouter comprend l’article de blog GPT-5 is now live . Le guide de démarrage rapide présente les clés API et votre première requête, et la référence API répertorie tous les paramètres.

GPT-5 coûte 1,25 $US/M de jetons d’entrée et 10,00 $US/M de jetons de sortie, avec des tarifs distincts pour Cache Read à 0,125 $US/M tokens.

GPT-5 dispose d’une fenêtre de contexte de 400 000 jetons. Il prend en charge jusqu’à 128 000 jetons de complétion.

Oui. GPT-5 accepte tools et tool_choice pour l’appel de fonctions. Il prend également en charge les sorties structurées via un schéma JSON dans response_format.

GPT-5 accepte texte, images et fichiers tels que des PDF en entrée et renvoie texte.

GPT-5 est proposé par 2 fournisseurs sur OpenRouter : Azure et OpenAI. Les requêtes sont acheminées vers le meilleur fournisseur disponible, avec un basculement automatique vers les autres, et vous pouvez fixer ou exclure des fournisseurs avec le routage des fournisseurs.

GPT-5 est sorti le 7 août 2025. Ses connaissances s’arrêtent au 30 septembre 2024.

Autres modèles de OpenAI

GPT-6.1 Terra Pro

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M1 $US / 5 $US
GPT-6.1 Terra Pro (batch)

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M0,50 $US / 2,50 $US
GPT-6.1 Terra

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

TexteContexte de 1,1M1 $US / 5 $US
GPT-6.1 Terra (batch)

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

TexteContexte de 1,1M0,50 $US / 2,50 $US
GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.

Décisions0,10 $US / 0 $US
GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M2 $US / 10 $US
GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M1 $US / 5 $US
GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

TexteContexte de 1,1M2 $US / 10 $US
GPT-6.1 Sol (batch)

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

TexteContexte de 1,1M1 $US / 5 $US
GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M0,10 $US / 0,50 $US
GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M0,05 $US / 0,25 $US
GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

TexteContexte de 1,1M0,10 $US / 0,50 $US
GPT-6 Luna (batch)

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

TexteContexte de 1,1M0,05 $US / 0,25 $US
GPT-6 Sol Pro

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M2 $US / 10 $US
GPT-6 Sol Pro (batch)

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

TexteContexte de 1,1M1 $US / 5 $US
GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

TexteContexte de 1,1M2 $US / 10 $US
GPT-6 Sol (batch)

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

TexteContexte de 1,1M1 $US / 5 $US
GPT Astra Latest

This model always redirects to the latest model in the GPT Astra family.

TexteContexte de 1,1M
GPT Sol Latest

This model always redirects to the latest model in the GPT Sol family.

TexteContexte de 1,1M
GPT Terra Latest

This model always redirects to the latest model in the GPT Terra family.

TexteContexte de 1,1M