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 x-ai

SpaceXAI: Grok 4.3

x-ai/grok-4.3

Comparer

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.

It supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.

Modalités
Prix en entrée / sortie
1,25 $US / 2,50 $USpar 1M
Contexte
1,0M
Publié
30 avr. 2026
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 SpaceXAI: Grok 4.3 (Artificial Analysis, Design Arena et Vals AI)
SourceTest de performanceScore
Artificial AnalysisGrok 4.3 (High) Coding Index42,2
Artificial AnalysisGrok 4.3 (High) Agentic Index15,5
Artificial AnalysisGrok 4.3 (High) GPQA Diamond90.1%
Artificial AnalysisGrok 4.3 (High) HLE37.2%
Artificial AnalysisGrok 4.3 (High) IFBench81.3%
Artificial AnalysisGrok 4.3 (High) τ²-Bench Telecom97.7%
Artificial AnalysisGrok 4.3 (High) AA-LCR73.0%
Artificial AnalysisGrok 4.3 (High) τ-Bench Banking12.4%
Artificial AnalysisGrok 4.3 (High) GDPval-AA22.3%
Artificial AnalysisGrok 4.3 (High) CritPt8.0%
Artificial AnalysisGrok 4.3 (High) SciCode48.3%
Artificial AnalysisGrok 4.3 (High) Terminal-Bench Hard37.9%
Artificial AnalysisGrok 4.3 (High) Terminal-Bench 4.00.0%
Artificial AnalysisGrok 4.3 (High) Terminal-Bench 2.139.7%
Artificial AnalysisGrok 4.3 (Low) GPQA Diamond84.3%
Artificial AnalysisGrok 4.3 (Low) HLE18.4%
Artificial AnalysisGrok 4.3 (Low) IFBench81.0%
Artificial AnalysisGrok 4.3 (Low) τ²-Bench Telecom88.9%
Artificial AnalysisGrok 4.3 (Low) AA-LCR74.0%
Artificial AnalysisGrok 4.3 (Low) CritPt0.6%
Artificial AnalysisGrok 4.3 (Low) Terminal-Bench Hard26.5%
Artificial AnalysisGrok 4.3 (Medium) GPQA Diamond89.0%
Artificial AnalysisGrok 4.3 (Medium) HLE30.0%
Artificial AnalysisGrok 4.3 (Medium) IFBench83.3%
Artificial AnalysisGrok 4.3 (Medium) τ²-Bench Telecom91.2%
Artificial AnalysisGrok 4.3 (Medium) AA-LCR75.0%
Artificial AnalysisGrok 4.3 (Medium) CritPt4.9%
Artificial AnalysisGrok 4.3 (Medium) Terminal-Bench Hard30.3%
Artificial AnalysisGrok 4.3 (Non-reasoning) Coding Index35,2
Artificial AnalysisGrok 4.3 (Non-reasoning) Agentic Index14,0
Artificial AnalysisGrok 4.3 (Non-reasoning) GPQA Diamond65.8%
Artificial AnalysisGrok 4.3 (Non-reasoning) HLE6.8%
Artificial AnalysisGrok 4.3 (Non-reasoning) IFBench47.6%
Artificial AnalysisGrok 4.3 (Non-reasoning) τ²-Bench Telecom65.8%
Artificial AnalysisGrok 4.3 (Non-reasoning) AA-LCR32.3%
Artificial AnalysisGrok 4.3 (Non-reasoning) τ-Bench Banking8.0%
Artificial AnalysisGrok 4.3 (Non-reasoning) GDPval-AA22.4%
Artificial AnalysisGrok 4.3 (Non-reasoning) CritPt0.0%
Artificial AnalysisGrok 4.3 (Non-reasoning) SciCode39.4%
Artificial AnalysisGrok 4.3 (Non-reasoning) Terminal-Bench Hard18.9%
Artificial AnalysisGrok 4.3 (Non-reasoning) Terminal-Bench 4.00.0%
Artificial AnalysisGrok 4.3 (Non-reasoning) Terminal-Bench 2.134.1%
Design ArenaGrok 4.3 Agents Arena Agenticgamedev Elo957
Design ArenaGrok 4.3 Agents Arena Agentichtmlslides Elo1066
Design ArenaGrok 4.3 Agents Arena Agenticslides Elo1072
Design ArenaGrok 4.3 Agents Arena Agenticslides(Html) Elo1066
Design ArenaGrok 4.3 Agents Arena Agenticslides(Python-Pptx) Elo1068
Design ArenaGrok 4.3 Agents Arena Androidnative Elo960
Design ArenaGrok 4.3 Agents Arena Blender3d Elo807
Design ArenaGrok 4.3 Agents Arena Full Stack Elo1006
Design ArenaGrok 4.3 Agents Arena Godotgamedev Elo914
Design ArenaGrok 4.3 Agents Arena Htmlslides Elo905
Design ArenaGrok 4.3 Agents Arena Mobile Apps Elo1058
Design ArenaGrok 4.3 Agents Arena Pdf Elo924
Design ArenaGrok 4.3 Agents Arena Pptxslides Elo1071
Design ArenaGrok 4.3 Agents Arena Python-Pptxslides Elo1072
Design ArenaGrok 4.3 Agents Arena Python-Pptxslides Elo972
Design ArenaGrok 4.3 Agents Arena Spreadsheet Elo940
Design ArenaGrok 4.3 Agents Arena Webapps Elo1111
Design ArenaGrok 4.3 Models Arena 3D Elo1121
Design ArenaGrok 4.3 Models Arena Asciiart Elo1123
Design ArenaGrok 4.3 Models Arena Code Categories Elo1185
Design ArenaGrok 4.3 Models Arena Data Visualization Elo1180
Design ArenaGrok 4.3 Models Arena Game Development Elo1170
Design ArenaGrok 4.3 Models Arena SVG Elo1078
Design ArenaGrok 4.3 Models Arena UI Component Elo1188
Design ArenaGrok 4.3 Models Arena Website Elo1194
Vals AIGrok 4.3 CaseLaw v279.3%
Vals AIGrok 4.3 Code Migration6.8%
Vals AIGrok 4.3 CorpFin v268.5%
Vals AIGrok 4.3 EMB18.4%
Vals AIGrok 4.3 Finance Agent (v2)37.7%
Vals AIGrok 4.3 GPQA Diamond91.4%
Vals AIGrok 4.3 Harvey's Legal Agent Benchmark v10.4%
Vals AIGrok 4.3 IOI v115.3%
Vals AIGrok 4.3 LiveCodeBench84.5%
Vals AIGrok 4.3 LegalBench84.5%
Vals AIGrok 4.3 Legal Research Bench15.4%
Vals AIGrok 4.3 MedCode38.1%
Vals AIGrok 4.3 MedScribe74.4%
Vals AIGrok 4.3 MMLU Pro85.8%
Vals AIGrok 4.3 MMMU Pro83.1%
Vals AIGrok 4.3 MortgageTax48.3%
Vals AIGrok 4.3 ProgramBench0.0%
Vals AIGrok 4.3 ProofBench v111.0%
Vals AIGrok 4.3 Public Benefits Bench v1.151.7%
Vals AIGrok 4.3 SAGE v119.7%
Vals AIGrok 4.3 SkillsBench40.6%
Vals AIGrok 4.3 SWE-bench71.4%
Vals AIGrok 4.3 Tax Agent Bench6.2%
Vals AIGrok 4.3 TaxEval v270.8%
Vals AIGrok 4.3 Terminal-Bench 2.141.9%
Vals AIGrok 4.3 Vals Index24.3%
Vals AIGrok 4.3 Vals Multimodal Index43.3%
Vals AIGrok 4.3 Vibe Code Bench v1.119.4%

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.

Versions de xAI: Grok

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
1,25 $US2,50 $US0,20 $US1,01s95 tps
96,90 %
1,25 $US2,50 $US0,20 $US1,20s82 tps
97,68 %
Non utilisé pour le routage Standard :Pourquoi ces points de terminaison ne sont pas utilisés
Priority
2,50 $US5,00 $US0,40 $US0,43s53 tps
100,00 %
Priority
2,50 $US5,00 $US0,40 $US----
--
Débit
95jetons/s

P50, meilleur résultat tous fournisseurs confondus

Latence
0,43s

P50, meilleur fournisseur

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.
99,01 %

Disponibilité au cours des 3 derniers jours

72 dernières heures
Disponibilité 99,01 %
Il y a 3 joursIl y a 2 joursHierMaintenant

Disponibilité au cours des dernières 24 heures

OpenRouter Availability
98,28 %

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://hey.fans/
HeyFans
nouveau
7,41Bjetons
2.
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.
3,51Bjetons
3.
Favicon de https://aidetector.com/
AiDetector
nouveau
2,62Bjetons
4.
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.
2,1Bjetons
5.
Favicon de https://www.isekai.world/
ISEKAI ZERO
AI adventures. Travel with your favorite characters
1,83Bjetons

Questions fréquentes

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.

Grok 4.3 coûte 1,25 $US/M de jetons d’entrée et 2,50 $US/M de jetons de sortie, avec des tarifs distincts pour Cache Read à 0,20 $US/M tokens et Web Search à 5,00 $US/1K calls.

Grok 4.3 dispose d’une fenêtre de contexte de 1 000 000 jetons.

Oui. Grok 4.3 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.

Grok 4.3 accepte texte, images et fichiers tels que des PDF en entrée et renvoie texte.

Grok 4.7, Grok 4.6, Grok 4.5 et 3 de plus sont d’autres modèles de type texte de SpaceXAI.

Grok 4.3 est sorti le 30 avril 2026.

Autres modèles de SpaceXAI

Grok Imagine Video 1.5 Lite

Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from Grok Imagine Video 1.5. It supports text-to-video and image-to-video, trading some quality for speed and price. 1080p output is rendered at 720p and upscaled.

Vidéofrom 0,02 $US/second
Grok 4.7

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations.

The model was trained with a longer reinforcement learning run weighted toward problems that take many hours to complete, and natively understands the Grok Bot harness for conversational tasks. It ships with a new safeguard stack that pairs strong jailbreak resistance with low refusal rates for legitimate cybersecurity and biology work. SpaceXAI's reported benchmark results use the xhigh reasoning effort.

TexteContexte de 500K2 $US / 6 $US
Grok 4.6

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.

TexteContexte de 500K2 $US / 6 $US
Grok Imagine Image 2.0

Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and medium quality modes.

Imagefrom 0,04 $US/image
Grok STT 1.0

Grok STT is SpaceXAI's speech-to-text model, available via the REST /v1/stt endpoint. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.

Transcription0,000028 $US/second
Grok Imagine Video 1.5

Grok Imagine Video 1.5 is a video generation model from SpaceXAI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject and camera motion, pacing, atmosphere, and physical behavior while maintaining visual continuity, and can generate synchronized sound effects, ambience, and dialogue.

Vidéofrom 0,08 $US/second
Grok 4.5

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

TexteContexte de 500K2 $US / 6 $US
Grok Latest

This model always redirects to the latest Grok model from xAI.

TexteContexte de 500K
Grok Build 0.1

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. The model powers SpaceXAI’s Grok Build CLI and features a 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows. Currently in early access.

TexteContexte de 256K1 $US / 2 $US
Grok Imagine Video

Grok Imagine Video is SpaceXAI's fast, text-, image-, and reference-conditioned video generation model. It produces short videos (1–15 seconds, 24 fps) at 480p or 720p across seven aspect ratios - 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.

The model supports three generation modes: text-to-video from a prompt alone, image-to-video that animates a still input, and reference-to-video that grounds the output in up to seven reference images for consistent characters, styles, or settings.

Vidéofrom 0,05 $US/second
Grok Imagine Image Quality

Grok Imagine Image Quality is SpaceXAI's fast, high-fidelity image generation and editing model. It accepts text prompts and optional reference images, producing photorealistic outputs at 1K or 2K across a range of aspect ratios, including flexible adjustment of reference images.

The model emphasizes realistic detail — natural lighting and physics, accurate textures, and consistent rendering of named entities such as brands, public figures, and specific locations. It supports clean multilingual text rendering inside images, making it the top choice for posters, packaging, ads, menus, and social graphics. When given reference images, it preserves identity and structure for product placement, brand-aligned variations, and character continuity across scenes.

Image
Grok Voice TTS 1.0

Grok Voice TTS 1.0 is a text-to-speech model from SpaceXAI. It converts text into spoken audio across 20+ languages with automatic language detection, and offers five built-in voices (Eve, Ara, Rex, Sal, Leo) covering a range of tones. Inline speech tags allow control over pauses, emphasis, pitch, speed, and vocal style. Output is available in MP3, WAV, PCM, μ-law, and A-law formats at sample rates from 8 kHz to 48 kHz, with up to 15,000 characters per request.

Parole15 $US/M characters
Grok 4.3

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.

It supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.

TexteContexte de 1M1,25 $US / 2,50 $US
Grok 4.3 (batch)

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.

It supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.

TexteContexte de 1M1 $US / 2 $US
Grok 4.20 Multi-Agent

Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.

Reasoning effort behavior:

TexteContexte de 2M1,25 $US / 2,50 $US
Grok 4.20

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.

Reasoning can be enabled/disabled using the reasoning enabled parameter in the API. Learn more in our docs

TexteContexte de 2M1,25 $US / 2,50 $US
Grok 4.20 Multi-Agent Beta

Grok 4.20 Multi-Agent Beta is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.

Reasoning effort behavior:

TexteContexte de 2M
Grok 4.20 Beta

Grok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.

Reasoning can be enabled/disabled using the reasoning enabled parameter in the API. Learn more in our docs

TexteContexte de 2M
Grok 4.1 Fast

Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window.

Reasoning can be enabled/disabled using the reasoning enabled parameter in the API. Learn more in our docs

TexteContexte de 2M
Grok 4 Fast

Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's news post.

Reasoning can be enabled/disabled using the reasoning enabled parameter in the API. Learn more in our docs

TexteContexte de 2M