Qu’est-ce que GPT-5.6 Sol ?

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.

Où se trouve la documentation de GPT-5.6 Sol ?

La documentation de GPT-5.6 Sol sur OpenRouter comprend le guide de recettes GPT-5.6 Migration Guide et l’article de blog GPT 5.6 Discounts & Jevons Paradox. Le guide de démarrage rapide présente les clés API et votre première requête, et la référence API répertorie tous les paramètres.

Combien coûte GPT-5.6 Sol ?

GPT-5.6 Sol coûte 4,00 $US/M de jetons d’entrée et 20,00 $US/M de jetons de sortie, avec des tarifs distincts pour Cache Read à 0,40 $US/M tokens et Cache Write à 5,00 $US/M tokens.

Quelle est la longueur de contexte de GPT-5.6 Sol ?

GPT-5.6 Sol dispose d’une fenêtre de contexte de 1 050 000 jetons. Il prend en charge jusqu’à 128 000 jetons de complétion.

GPT-5.6 Sol prend-il en charge les appels d’outils et les sorties structurées ?

Oui. GPT-5.6 Sol 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.

Puis-je désactiver la mise en cache des prompts pour GPT-5.6 Sol ?

Oui. OpenAI met automatiquement en cache les prompts de 1024 jetons ou plus, et GPT-5.6 Sol facture une écriture en cache pour chaque prompt mis en cache, que le préfixe mis en cache soit relu ou non. Pour désactiver la mise en cache pour une requête, définissez prompt_cache_options.mode sur "explicit" à la racine de la requête et ne marquez aucun bloc de contenu avec prompt_cache_breakpoint. Le mode explicite désactive les points de rupture gérés par OpenAI, de sorte qu’une requête sans point de rupture défini par vos soins ne possède aucun préfixe pouvant être mis en cache et est facturée au tarif d’entrée normal. Consultez le guide de mise en cache des prompts.

Quelles entrées et sorties GPT-5.6 Sol prend-il en charge ?

GPT-5.6 Sol accepte fichiers tels que des PDF, images et texte en entrée et renvoie texte.

Quels fournisseurs proposent GPT-5.6 Sol ?

GPT-5.6 Sol est proposé par 3 fournisseurs sur OpenRouter : OpenAI, Amazon Bedrock 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.

Quand GPT-5.6 Sol a-t-il été publié ?

GPT-5.6 Sol est sorti le 9 juillet 2026. Ses connaissances s’arrêtent au 16 février 2026.

GPT-5.6 Sol - Tarifs de l’API et évaluations comparatives

Name: OpenAI: GPT-5.6 Sol
Author: OpenAI

Résumé des scores aux tests de performance pour OpenAI: GPT-5.6 Sol (Artificial Analysis et Vals AI)
Source	Test de performance	Score
Artificial Analysis	GPT-5.6 Sol (High) Coding Index	77,2
Artificial Analysis	GPT-5.6 Sol (High) Agentic Index	44,2
Artificial Analysis	GPT-5.6 Sol (High) GPQA Diamond	92.8%
Artificial Analysis	GPT-5.6 Sol (High) HLE	46.0%
Artificial Analysis	GPT-5.6 Sol (High) IFBench	69.2%
Artificial Analysis	GPT-5.6 Sol (High) τ²-Bench Telecom	83.3%
Artificial Analysis	GPT-5.6 Sol (High) AA-LCR	81.7%
Artificial Analysis	GPT-5.6 Sol (High) τ-Bench Banking	36.7%
Artificial Analysis	GPT-5.6 Sol (High) GDPval-AA	50.6%
Artificial Analysis	GPT-5.6 Sol (High) CritPt	25.7%
Artificial Analysis	GPT-5.6 Sol (High) SciCode	57.8%
Artificial Analysis	GPT-5.6 Sol (High) Terminal-Bench Hard	62.1%
Artificial Analysis	GPT-5.6 Sol (High) Terminal-Bench 4.0	20.7%
Artificial Analysis	GPT-5.6 Sol (High) Terminal-Bench 2.1	87.3%
Artificial Analysis	GPT-5.6 Sol (Low) Coding Index	69,7
Artificial Analysis	GPT-5.6 Sol (Low) Agentic Index	31,6
Artificial Analysis	GPT-5.6 Sol (Low) GPQA Diamond	89.8%
Artificial Analysis	GPT-5.6 Sol (Low) HLE	39.4%
Artificial Analysis	GPT-5.6 Sol (Low) IFBench	66.5%
Artificial Analysis	GPT-5.6 Sol (Low) τ²-Bench Telecom	76.0%
Artificial Analysis	GPT-5.6 Sol (Low) AA-LCR	78.0%
Artificial Analysis	GPT-5.6 Sol (Low) τ-Bench Banking	29.1%
Artificial Analysis	GPT-5.6 Sol (Low) GDPval-AA	40.7%
Artificial Analysis	GPT-5.6 Sol (Low) CritPt	14.9%
Artificial Analysis	GPT-5.6 Sol (Low) SciCode	56.4%
Artificial Analysis	GPT-5.6 Sol (Low) Terminal-Bench Hard	60.6%
Artificial Analysis	GPT-5.6 Sol (Low) Terminal-Bench 4.0	1.0%
Artificial Analysis	GPT-5.6 Sol (Low) Terminal-Bench 2.1	76.8%
Artificial Analysis	GPT-5.6 Sol (Max) Coding Index	77,4
Artificial Analysis	GPT-5.6 Sol (Max) Agentic Index	50,2
Artificial Analysis	GPT-5.6 Sol (Max) GPQA Diamond	94.1%
Artificial Analysis	GPT-5.6 Sol (Max) HLE	49.5%
Artificial Analysis	GPT-5.6 Sol (Max) IFBench	72.7%
Artificial Analysis	GPT-5.6 Sol (Max) τ²-Bench Telecom	85.1%
Artificial Analysis	GPT-5.6 Sol (Max) AA-LCR	84.0%
Artificial Analysis	GPT-5.6 Sol (Max) τ-Bench Banking	44.3%
Artificial Analysis	GPT-5.6 Sol (Max) GDPval-AA	55.9%
Artificial Analysis	GPT-5.6 Sol (Max) CritPt	32.3%
Artificial Analysis	GPT-5.6 Sol (Max) SciCode	57.1%
Artificial Analysis	GPT-5.6 Sol (Max) Terminal-Bench Hard	65.9%
Artificial Analysis	GPT-5.6 Sol (Max) Terminal-Bench 4.0	39.9%
Artificial Analysis	GPT-5.6 Sol (Max) Terminal-Bench 2.1	88.0%
Artificial Analysis	GPT-5.6 Sol (Medium) Coding Index	76,3
Artificial Analysis	GPT-5.6 Sol (Medium) Agentic Index	39,7
Artificial Analysis	GPT-5.6 Sol (Medium) GPQA Diamond	92.6%
Artificial Analysis	GPT-5.6 Sol (Medium) HLE	42.2%
Artificial Analysis	GPT-5.6 Sol (Medium) IFBench	69.6%
Artificial Analysis	GPT-5.6 Sol (Medium) τ²-Bench Telecom	81.0%
Artificial Analysis	GPT-5.6 Sol (Medium) AA-LCR	80.3%
Artificial Analysis	GPT-5.6 Sol (Medium) τ-Bench Banking	36.5%
Artificial Analysis	GPT-5.6 Sol (Medium) GDPval-AA	46.6%
Artificial Analysis	GPT-5.6 Sol (Medium) CritPt	22.9%
Artificial Analysis	GPT-5.6 Sol (Medium) SciCode	57.4%
Artificial Analysis	GPT-5.6 Sol (Medium) Terminal-Bench Hard	62.9%
Artificial Analysis	GPT-5.6 Sol (Medium) Terminal-Bench 4.0	14.6%
Artificial Analysis	GPT-5.6 Sol (Medium) Terminal-Bench 2.1	86.1%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) Coding Index	65,1
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) Agentic Index	28,1
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) GPQA Diamond	79.0%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) HLE	16.7%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) AA-LCR	62.3%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) τ-Bench Banking	19.6%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) GDPval-AA	37.5%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) CritPt	5.1%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) SciCode	47.7%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) Terminal-Bench 2.1	74.2%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Coding Index	78,3
Artificial Analysis	GPT-5.6 Sol (Xhigh) Agentic Index	47,4
Artificial Analysis	GPT-5.6 Sol (Xhigh) GPQA Diamond	93.1%
Artificial Analysis	GPT-5.6 Sol (Xhigh) HLE	47.3%
Artificial Analysis	GPT-5.6 Sol (Xhigh) IFBench	71.0%
Artificial Analysis	GPT-5.6 Sol (Xhigh) τ²-Bench Telecom	84.8%
Artificial Analysis	GPT-5.6 Sol (Xhigh) AA-LCR	82.3%
Artificial Analysis	GPT-5.6 Sol (Xhigh) τ-Bench Banking	38.1%
Artificial Analysis	GPT-5.6 Sol (Xhigh) GDPval-AA	53.9%
Artificial Analysis	GPT-5.6 Sol (Xhigh) CritPt	28.6%
Artificial Analysis	GPT-5.6 Sol (Xhigh) SciCode	57.1%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Terminal-Bench Hard	61.4%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Terminal-Bench 4.0	24.7%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Terminal-Bench 2.1	89.5%
Vals AI	GPT-5.6 Sol BioMysteryBench	71.1%
Vals AI	GPT-5.6 Sol Code Migration	52.9%
Vals AI	GPT-5.6 Sol CorpFin v2	64.4%
Vals AI	GPT-5.6 Sol CyberBench v1.1	76.3%
Vals AI	GPT-5.6 Sol EMB	72.3%
Vals AI	GPT-5.6 Sol Finance Agent (v2)	53.8%
Vals AI	GPT-5.6 Sol GPQA Diamond	95.2%
Vals AI	GPT-5.6 Sol Harvey's Legal Agent Benchmark v1	2.5%
Vals AI	GPT-5.6 Sol IOI	91.2%
Vals AI	GPT-5.6 Sol LiveCodeBench	82.6%
Vals AI	GPT-5.6 Sol LegalBench	87.0%
Vals AI	GPT-5.6 Sol Legal Research Bench	48.1%
Vals AI	GPT-5.6 Sol MedCode	44.0%
Vals AI	GPT-5.6 Sol MedScribe	85.2%
Vals AI	GPT-5.6 Sol MMLU Pro	89.1%
Vals AI	GPT-5.6 Sol MMMU Pro	88.8%
Vals AI	GPT-5.6 Sol MortgageTax	67.3%
Vals AI	GPT-5.6 Sol MysteryMechanism	33.3%
Vals AI	GPT-5.6 Sol ProgramBench	1.5%
Vals AI	GPT-5.6 Sol ProofBench v1.1	83.0%
Vals AI	GPT-5.6 Sol Public Benefits Bench v1.1	66.5%
Vals AI	GPT-5.6 Sol Vals RSI Index	23.9%
Vals AI	GPT-5.6 Sol SAGE v1	52.6%
Vals AI	GPT-5.6 Sol Vals Science Index	41.5%
Vals AI	GPT-5.6 Sol SkillsBench	54.1%
Vals AI	GPT-5.6 Sol SRE Bench	30.5%
Vals AI	GPT-5.6 Sol SWE-bench	96.2%
Vals AI	GPT-5.6 Sol Tax Agent Bench	31.1%
Vals AI	GPT-5.6 Sol TaxEval v2	74.8%
Vals AI	GPT-5.6 Sol Terminal-Bench 4.0	37.9%
Vals AI	GPT-5.6 Sol Terminal-Bench-Science	20.0%
Vals AI	GPT-5.6 Sol Vals Index	58.0%
Vals AI	GPT-5.6 Sol Vals Multimodal Index	72.6%
Vals AI	GPT-5.6 Sol Vibe Code Bench 1-100	20.0%
Vals AI	GPT-5.6 Sol Vibe Code Bench v1.1	80.5%
Vals AI	GPT-5.6 Sol Vals Web Search Index	43.6%


	4,00 $US	20,00 $US	0,40 $US	1,68s	67 tps	100,00 %
	4,00 $US	20,00 $US	0,40 $US	6,31s	50 tps	99,97 %
	4,00 $US	20,00 $US	0,40 $US	2,54s	85 tps	100,00 %
Non utilisé pour le routage Standard :Pourquoi ces points de terminaison ne sont pas utilisés
Flex	2,00 $US	10,00 $US	0,20 $US	8,35s	153 tps	100,00 %
	4,40 $US	22,00 $US	0,44 $US	0,82s	70 tps	100,00 %
	4,40 $US	22,00 $US	0,44 $US	0,15s	154 tps	100,00 %
	4,40 $US	22,00 $US	0,44 $US	0,83s	66 tps	100,00 %
Fast	8,00 $US	40,00 $US	0,80 $US	2,11s	94 tps	100,00 %

Résumé des scores aux tests de performance pour OpenAI: GPT-5.6 Sol (Artificial Analysis et Vals AI)
Source	Test de performance	Score
Artificial Analysis	GPT-5.6 Sol (High) Coding Index	77,2
Artificial Analysis	GPT-5.6 Sol (High) Agentic Index	44,2
Artificial Analysis	GPT-5.6 Sol (High) GPQA Diamond	92.8%
Artificial Analysis	GPT-5.6 Sol (High) HLE	46.0%
Artificial Analysis	GPT-5.6 Sol (High) IFBench	69.2%
Artificial Analysis	GPT-5.6 Sol (High) τ²-Bench Telecom	83.3%
Artificial Analysis	GPT-5.6 Sol (High) AA-LCR	81.7%
Artificial Analysis	GPT-5.6 Sol (High) τ-Bench Banking	36.7%
Artificial Analysis	GPT-5.6 Sol (High) GDPval-AA	50.6%
Artificial Analysis	GPT-5.6 Sol (High) CritPt	25.7%
Artificial Analysis	GPT-5.6 Sol (High) SciCode	57.8%
Artificial Analysis	GPT-5.6 Sol (High) Terminal-Bench Hard	62.1%
Artificial Analysis	GPT-5.6 Sol (High) Terminal-Bench 4.0	20.7%
Artificial Analysis	GPT-5.6 Sol (High) Terminal-Bench 2.1	87.3%
Artificial Analysis	GPT-5.6 Sol (Low) Coding Index	69,7
Artificial Analysis	GPT-5.6 Sol (Low) Agentic Index	31,6
Artificial Analysis	GPT-5.6 Sol (Low) GPQA Diamond	89.8%
Artificial Analysis	GPT-5.6 Sol (Low) HLE	39.4%
Artificial Analysis	GPT-5.6 Sol (Low) IFBench	66.5%
Artificial Analysis	GPT-5.6 Sol (Low) τ²-Bench Telecom	76.0%
Artificial Analysis	GPT-5.6 Sol (Low) AA-LCR	78.0%
Artificial Analysis	GPT-5.6 Sol (Low) τ-Bench Banking	29.1%
Artificial Analysis	GPT-5.6 Sol (Low) GDPval-AA	40.7%
Artificial Analysis	GPT-5.6 Sol (Low) CritPt	14.9%
Artificial Analysis	GPT-5.6 Sol (Low) SciCode	56.4%
Artificial Analysis	GPT-5.6 Sol (Low) Terminal-Bench Hard	60.6%
Artificial Analysis	GPT-5.6 Sol (Low) Terminal-Bench 4.0	1.0%
Artificial Analysis	GPT-5.6 Sol (Low) Terminal-Bench 2.1	76.8%
Artificial Analysis	GPT-5.6 Sol (Max) Coding Index	77,4
Artificial Analysis	GPT-5.6 Sol (Max) Agentic Index	50,2
Artificial Analysis	GPT-5.6 Sol (Max) GPQA Diamond	94.1%
Artificial Analysis	GPT-5.6 Sol (Max) HLE	49.5%
Artificial Analysis	GPT-5.6 Sol (Max) IFBench	72.7%
Artificial Analysis	GPT-5.6 Sol (Max) τ²-Bench Telecom	85.1%
Artificial Analysis	GPT-5.6 Sol (Max) AA-LCR	84.0%
Artificial Analysis	GPT-5.6 Sol (Max) τ-Bench Banking	44.3%
Artificial Analysis	GPT-5.6 Sol (Max) GDPval-AA	55.9%
Artificial Analysis	GPT-5.6 Sol (Max) CritPt	32.3%
Artificial Analysis	GPT-5.6 Sol (Max) SciCode	57.1%
Artificial Analysis	GPT-5.6 Sol (Max) Terminal-Bench Hard	65.9%
Artificial Analysis	GPT-5.6 Sol (Max) Terminal-Bench 4.0	39.9%
Artificial Analysis	GPT-5.6 Sol (Max) Terminal-Bench 2.1	88.0%
Artificial Analysis	GPT-5.6 Sol (Medium) Coding Index	76,3
Artificial Analysis	GPT-5.6 Sol (Medium) Agentic Index	39,7
Artificial Analysis	GPT-5.6 Sol (Medium) GPQA Diamond	92.6%
Artificial Analysis	GPT-5.6 Sol (Medium) HLE	42.2%
Artificial Analysis	GPT-5.6 Sol (Medium) IFBench	69.6%
Artificial Analysis	GPT-5.6 Sol (Medium) τ²-Bench Telecom	81.0%
Artificial Analysis	GPT-5.6 Sol (Medium) AA-LCR	80.3%
Artificial Analysis	GPT-5.6 Sol (Medium) τ-Bench Banking	36.5%
Artificial Analysis	GPT-5.6 Sol (Medium) GDPval-AA	46.6%
Artificial Analysis	GPT-5.6 Sol (Medium) CritPt	22.9%
Artificial Analysis	GPT-5.6 Sol (Medium) SciCode	57.4%
Artificial Analysis	GPT-5.6 Sol (Medium) Terminal-Bench Hard	62.9%
Artificial Analysis	GPT-5.6 Sol (Medium) Terminal-Bench 4.0	14.6%
Artificial Analysis	GPT-5.6 Sol (Medium) Terminal-Bench 2.1	86.1%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) Coding Index	65,1
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) Agentic Index	28,1
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) GPQA Diamond	79.0%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) HLE	16.7%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) AA-LCR	62.3%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) τ-Bench Banking	19.6%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) GDPval-AA	37.5%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) CritPt	5.1%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) SciCode	47.7%
Artificial Analysis	GPT-5.6 Sol (Non-reasoning) Terminal-Bench 2.1	74.2%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Coding Index	78,3
Artificial Analysis	GPT-5.6 Sol (Xhigh) Agentic Index	47,4
Artificial Analysis	GPT-5.6 Sol (Xhigh) GPQA Diamond	93.1%
Artificial Analysis	GPT-5.6 Sol (Xhigh) HLE	47.3%
Artificial Analysis	GPT-5.6 Sol (Xhigh) IFBench	71.0%
Artificial Analysis	GPT-5.6 Sol (Xhigh) τ²-Bench Telecom	84.8%
Artificial Analysis	GPT-5.6 Sol (Xhigh) AA-LCR	82.3%
Artificial Analysis	GPT-5.6 Sol (Xhigh) τ-Bench Banking	38.1%
Artificial Analysis	GPT-5.6 Sol (Xhigh) GDPval-AA	53.9%
Artificial Analysis	GPT-5.6 Sol (Xhigh) CritPt	28.6%
Artificial Analysis	GPT-5.6 Sol (Xhigh) SciCode	57.1%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Terminal-Bench Hard	61.4%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Terminal-Bench 4.0	24.7%
Artificial Analysis	GPT-5.6 Sol (Xhigh) Terminal-Bench 2.1	89.5%
Vals AI	GPT-5.6 Sol BioMysteryBench	71.1%
Vals AI	GPT-5.6 Sol Code Migration	52.9%
Vals AI	GPT-5.6 Sol CorpFin v2	64.4%
Vals AI	GPT-5.6 Sol CyberBench v1.1	76.3%
Vals AI	GPT-5.6 Sol EMB	72.3%
Vals AI	GPT-5.6 Sol Finance Agent (v2)	53.8%
Vals AI	GPT-5.6 Sol GPQA Diamond	95.2%
Vals AI	GPT-5.6 Sol Harvey's Legal Agent Benchmark v1	2.5%
Vals AI	GPT-5.6 Sol IOI	91.2%
Vals AI	GPT-5.6 Sol LiveCodeBench	82.6%
Vals AI	GPT-5.6 Sol LegalBench	87.0%
Vals AI	GPT-5.6 Sol Legal Research Bench	48.1%
Vals AI	GPT-5.6 Sol MedCode	44.0%
Vals AI	GPT-5.6 Sol MedScribe	85.2%
Vals AI	GPT-5.6 Sol MMLU Pro	89.1%
Vals AI	GPT-5.6 Sol MMMU Pro	88.8%
Vals AI	GPT-5.6 Sol MortgageTax	67.3%
Vals AI	GPT-5.6 Sol MysteryMechanism	33.3%
Vals AI	GPT-5.6 Sol ProgramBench	1.5%
Vals AI	GPT-5.6 Sol ProofBench v1.1	83.0%
Vals AI	GPT-5.6 Sol Public Benefits Bench v1.1	66.5%
Vals AI	GPT-5.6 Sol Vals RSI Index	23.9%
Vals AI	GPT-5.6 Sol SAGE v1	52.6%
Vals AI	GPT-5.6 Sol Vals Science Index	41.5%
Vals AI	GPT-5.6 Sol SkillsBench	54.1%
Vals AI	GPT-5.6 Sol SRE Bench	30.5%
Vals AI	GPT-5.6 Sol SWE-bench	96.2%
Vals AI	GPT-5.6 Sol Tax Agent Bench	31.1%
Vals AI	GPT-5.6 Sol TaxEval v2	74.8%
Vals AI	GPT-5.6 Sol Terminal-Bench 4.0	37.9%
Vals AI	GPT-5.6 Sol Terminal-Bench-Science	20.0%
Vals AI	GPT-5.6 Sol Vals Index	58.0%
Vals AI	GPT-5.6 Sol Vals Multimodal Index	72.6%
Vals AI	GPT-5.6 Sol Vibe Code Bench 1-100	20.0%
Vals AI	GPT-5.6 Sol Vibe Code Bench v1.1	80.5%
Vals AI	GPT-5.6 Sol Vals Web Search Index	43.6%

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