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-5.4 Nano

openai/gpt-5.4-nano

Comparer

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.

The model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.

Modalités
Prix en entrée / sortie
0,20 $US / 1,25 $USpar 1M
Contexte
400K
Publié
17 mars 2026
Date limite des connaissances
août 2025
Comparer
FournisseursTarificationPerformancesDisponibilitéÉvaluations comparativesApplicationsActivitéFAQExplorer

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-5.4 Nano (Artificial Analysis et Vals AI)
SourceTest de performanceScore
Artificial AnalysisGPT-5.4 nano (Medium) GPQA Diamond76.1%
Artificial AnalysisGPT-5.4 nano (Medium) HLE15.9%
Artificial AnalysisGPT-5.4 nano (Medium) IFBench64.4%
Artificial AnalysisGPT-5.4 nano (Medium) τ²-Bench Telecom52.6%
Artificial AnalysisGPT-5.4 nano (Medium) AA-LCR67.3%
Artificial AnalysisGPT-5.4 nano (Medium) CritPt5.1%
Artificial AnalysisGPT-5.4 nano (Medium) Terminal-Bench Hard33.3%
Artificial AnalysisGPT-5.4 nano (Non-reasoning) GPQA Diamond55.8%
Artificial AnalysisGPT-5.4 nano (Non-reasoning) HLE4.1%
Artificial AnalysisGPT-5.4 nano (Non-reasoning) IFBench32.7%
Artificial AnalysisGPT-5.4 nano (Non-reasoning) τ²-Bench Telecom34.8%
Artificial AnalysisGPT-5.4 nano (Non-reasoning) AA-LCR29.7%
Artificial AnalysisGPT-5.4 nano (Non-reasoning) CritPt0.0%
Artificial AnalysisGPT-5.4 nano (Non-reasoning) Terminal-Bench Hard24.2%
Artificial AnalysisGPT-5.4 nano (Xhigh) Coding Index56,1
Artificial AnalysisGPT-5.4 nano (Xhigh) Agentic Index16,0
Artificial AnalysisGPT-5.4 nano (Xhigh) GPQA Diamond81.7%
Artificial AnalysisGPT-5.4 nano (Xhigh) HLE28.3%
Artificial AnalysisGPT-5.4 nano (Xhigh) IFBench75.9%
Artificial AnalysisGPT-5.4 nano (Xhigh) τ²-Bench Telecom76.0%
Artificial AnalysisGPT-5.4 nano (Xhigh) AA-LCR76.7%
Artificial AnalysisGPT-5.4 nano (Xhigh) τ-Bench Banking27.4%
Artificial AnalysisGPT-5.4 nano (Xhigh) GDPval-AA22.7%
Artificial AnalysisGPT-5.4 nano (Xhigh) CritPt9.3%
Artificial AnalysisGPT-5.4 nano (Xhigh) SciCode47.2%
Artificial AnalysisGPT-5.4 nano (Xhigh) Terminal-Bench Hard42.4%
Artificial AnalysisGPT-5.4 nano (Xhigh) Terminal-Bench 4.00.5%
Artificial AnalysisGPT-5.4 nano (Xhigh) Terminal-Bench 2.160.7%
Vals AIGPT 5.4 Nano AIME88.8%
Vals AIGPT 5.4 Nano CaseLaw v251.9%
Vals AIGPT 5.4 Nano Code Migration14.5%
Vals AIGPT 5.4 Nano CorpFin v261.2%
Vals AIGPT 5.4 Nano EMB44.8%
Vals AIGPT 5.4 Nano Finance Agent (v2)38.2%
Vals AIGPT 5.4 Nano GPQA Diamond77.5%
Vals AIGPT 5.4 Nano Harvey's Legal Agent Benchmark v10.0%
Vals AIGPT 5.4 Nano IOI v115.3%
Vals AIGPT 5.4 Nano LiveCodeBench84.0%
Vals AIGPT 5.4 Nano LegalBench77.9%
Vals AIGPT 5.4 Nano Legal Research Bench6.3%
Vals AIGPT 5.4 Nano MedCode41.0%
Vals AIGPT 5.4 Nano MedScribe77.1%
Vals AIGPT 5.4 Nano MMLU Pro77.2%
Vals AIGPT 5.4 Nano MMMU Pro73.6%
Vals AIGPT 5.4 Nano MortgageTax59.1%
Vals AIGPT 5.4 Nano ProofBench v15.0%
Vals AIGPT 5.4 Nano SAGE v138.1%
Vals AIGPT 5.4 Nano SWE-bench69.8%
Vals AIGPT 5.4 Nano Tax Agent Bench5.0%
Vals AIGPT 5.4 Nano TaxEval v267.4%
Vals AIGPT 5.4 Nano Terminal-Bench 2.141.6%
Vals AIGPT 5.4 Nano Vals Index33.0%
Vals AIGPT 5.4 Nano Vals Multimodal Index47.6%
Vals AIGPT 5.4 Nano Vibe Code Bench v1.126.1%

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.

Actuellement indisponible via le routage dans la région UE. Documentation sur le routage intrarégional

Explorer d’autres modèles

Modèles d’IA avec vision : LLM multimodaux pour la compréhension d’imagesCollectionClassements des modèles d’IAClassement
Latence / débit
0,20 $US1,250 $US0,020 $US1,89s53 tps
100,00 %
0,20 $US1,250 $US0,020 $US0,95s87 tps
99,15 %
Non utilisé pour le routage Standard :Pourquoi ces points de terminaison ne sont pas utilisés
Flex
0,10 $US0,625 $US0,010 $US1,30s103 tps
97,22 %
0,22 $US1,375 $US0,022 $US----
100,00 %
Débit
103jetons/s

P50, meilleur résultat tous fournisseurs confondus

Latence
0,95s

P50, meilleur fournisseur

Évaluations comparatives AutoExacto
GPQA DiamondTAU-BenchOpenAI77,3 %67,3 %
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.
99,17 %

Disponibilité au cours des 3 derniers jours

72 dernières heures
Disponibilité 99,17 %
Il y a 3 joursIl y a 2 joursHierMaintenant

Disponibilité au cours des dernières 24 heures

OpenRouter Availability
97,94 %
Without Routing
90,84 %

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://agent-unit-reason-graph.com/
unit-reason-graph
nouveau
39,2Bjetons
2.
Favicon de https://github.com/podpitch/webapp
Webapp
nouveau
5,27Bjetons
3.
Favicon de https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
2,95Bjetons
4.
Favicon de https://yoursite.com/
YourAppName
nouveau
2,01Bjetons
5.
Favicon de https://openai.com/codex
Codex
A coding agent that helps you build and ship with AI
1,67Bjetons

Questions fréquentes

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.

GPT-5.4 Nano coûte 0,20 $US/M de jetons d’entrée et 1,25 $US/M de jetons de sortie, avec des tarifs distincts pour Cache Read à 0,02 $US/M tokens.

GPT-5.4 Nano dispose d’une fenêtre de contexte de 400 000 jetons. Il prend en charge jusqu’à 128 000 jetons de complétion.

Oui. GPT-5.4 Nano 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-5.4 Nano accepte fichiers tels que des PDF, images et texte en entrée et renvoie texte.

GPT-5.4 Nano est proposé par 2 fournisseurs sur OpenRouter : OpenAI et Azure. 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-5.4 Nano est sorti le 17 mars 2026. Ses connaissances s’arrêtent au 31 août 2025.

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