O que é GPT-5.6 Terra?

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.

Onde está a documentação de GPT-5.6 Terra?

A documentação de GPT-5.6 Terra no OpenRouter inclui o guia de exemplos GPT-5.6 Migration Guide e a publicação GPT 5.6 Discounts & Jevons Paradox no blog. O guia de início rápido aborda chaves de API e sua primeira requisição, e a referência da API lista todos os parâmetros.

Quanto custa GPT-5.6 Terra?

GPT-5.6 Terra custa US$ 2,00/M de tokens de entrada e US$ 12,00/M de tokens de saída, com taxas separadas para Cache Read por US$ 0,20/M tokens, Cache Write por US$ 2,50/M tokens e Web Search por US$ 10,00/1K calls.

Qual é o tamanho do contexto de GPT-5.6 Terra?

GPT-5.6 Terra tem uma janela de contexto de 1.050.000 tokens. Ele aceita até 128.000 tokens de conclusão.

GPT-5.6 Terra oferece suporte a chamadas de ferramentas e saídas estruturadas?

Sim. GPT-5.6 Terra aceita tools e tool_choice para chamadas de função. Também oferece suporte a saídas estruturadas por meio de um esquema JSON em response_format.

Posso desativar o cache de prompts para GPT-5.6 Terra?

Sim. A OpenAI armazena automaticamente em cache prompts de 1024 tokens ou mais, e GPT-5.6 Terra cobra uma gravação em cache para cada prompt armazenado em cache, independentemente de o prefixo em cache ser lido novamente. Para desativar o cache em uma requisição, defina prompt_cache_options.mode como "explicit" na raiz da requisição e não marque nenhum bloco de conteúdo com prompt_cache_breakpoint. O modo explícito desativa os pontos de interrupção gerenciados pela OpenAI, portanto uma requisição sem pontos de interrupção próprios não tem prefixo que possa ser armazenado em cache e é cobrada pela tarifa normal de entrada. Consulte o guia de armazenamento de prompts em cache.

Quais entradas e saídas GPT-5.6 Terra suporta?

GPT-5.6 Terra aceita arquivos como PDFs, imagens e texto como entrada e retorna texto.

Quais provedores disponibilizam GPT-5.6 Terra?

GPT-5.6 Terra é disponibilizado por 3 provedores no OpenRouter: OpenAI, Azure e Amazon Bedrock. As solicitações são roteadas para o melhor provedor disponível, com alternância automática para os demais em caso de falha, e você pode fixar ou excluir provedores com o roteamento de provedores.

Quando GPT-5.6 Terra foi lançado?

GPT-5.6 Terra foi lançado em 9 de julho de 2026. Seu conhecimento vai até 16 de fevereiro de 2026.

GPT-5.6 Terra - Preços da API e avaliações de desempenho

Name: OpenAI: GPT-5.6 Terra
Author: OpenAI

Resumo das pontuações de avaliações comparativas para OpenAI: GPT-5.6 Terra (Artificial Analysis e Vals AI)
Fonte	Avaliação comparativa	Pontuação
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Coding Index	52,3
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Agentic Index	23,5
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) GPQA Diamond	74.6%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) HLE	11.4%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-LCR	58.7%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) τ-Bench Banking	15.7%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) GDPval-AA	30.2%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) CritPt	2.0%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) SciCode	45.1%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Terminal-Bench 4.0	0.5%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Terminal-Bench 2.1	56.2%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-Omniscience Accuracy	32.6%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-Omniscience Non-Hallucination Rate	4.4%
Artificial Analysis	GPT-5.6 Terra (High) Coding Index	67,1
Artificial Analysis	GPT-5.6 Terra (High) Agentic Index	36,7
Artificial Analysis	GPT-5.6 Terra (High) GPQA Diamond	89.6%
Artificial Analysis	GPT-5.6 Terra (High) HLE	38.5%
Artificial Analysis	GPT-5.6 Terra (High) IFBench	64.4%
Artificial Analysis	GPT-5.6 Terra (High) τ²-Bench Telecom	78.4%
Artificial Analysis	GPT-5.6 Terra (High) AA-LCR	77.7%
Artificial Analysis	GPT-5.6 Terra (High) τ-Bench Banking	28.7%
Artificial Analysis	GPT-5.6 Terra (High) GDPval-AA	44.4%
Artificial Analysis	GPT-5.6 Terra (High) CritPt	22.9%
Artificial Analysis	GPT-5.6 Terra (High) SciCode	52.4%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench Hard	57.6%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench 4.0	1.5%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench 2.1	75.7%
Artificial Analysis	GPT-5.6 Terra (High) AA-Omniscience Accuracy	41.2%
Artificial Analysis	GPT-5.6 Terra (High) AA-Omniscience Non-Hallucination Rate	9.0%
Artificial Analysis	GPT-5.6 Terra (Max) Coding Index	76,7
Artificial Analysis	GPT-5.6 Terra (Max) Agentic Index	43,2
Artificial Analysis	GPT-5.6 Terra (Max) GPQA Diamond	92.5%
Artificial Analysis	GPT-5.6 Terra (Max) HLE	42.9%
Artificial Analysis	GPT-5.6 Terra (Max) IFBench	71.2%
Artificial Analysis	GPT-5.6 Terra (Max) τ²-Bench Telecom	86.3%
Artificial Analysis	GPT-5.6 Terra (Max) AA-LCR	83.0%
Artificial Analysis	GPT-5.6 Terra (Max) τ-Bench Banking	40.2%
Artificial Analysis	GPT-5.6 Terra (Max) GDPval-AA	48.1%
Artificial Analysis	GPT-5.6 Terra (Max) CritPt	30.0%
Artificial Analysis	GPT-5.6 Terra (Max) SciCode	55.0%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench Hard	57.6%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench 4.0	35.4%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench 2.1	88.0%
Artificial Analysis	GPT-5.6 Terra (Max) AA-Omniscience Accuracy	42.3%
Artificial Analysis	GPT-5.6 Terra (Max) AA-Omniscience Non-Hallucination Rate	10.6%
Artificial Analysis	GPT-5.6 Terra (Medium) Coding Index	64,7
Artificial Analysis	GPT-5.6 Terra (Medium) Agentic Index	30,4
Artificial Analysis	GPT-5.6 Terra (Medium) GPQA Diamond	87.2%
Artificial Analysis	GPT-5.6 Terra (Medium) HLE	33.3%
Artificial Analysis	GPT-5.6 Terra (Medium) IFBench	62.2%
Artificial Analysis	GPT-5.6 Terra (Medium) τ²-Bench Telecom	72.8%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-LCR	74.0%
Artificial Analysis	GPT-5.6 Terra (Medium) τ-Bench Banking	25.6%
Artificial Analysis	GPT-5.6 Terra (Medium) GDPval-AA	38.7%
Artificial Analysis	GPT-5.6 Terra (Medium) CritPt	17.4%
Artificial Analysis	GPT-5.6 Terra (Medium) SciCode	50.5%
Artificial Analysis	GPT-5.6 Terra (Medium) Terminal-Bench 4.0	1.0%
Artificial Analysis	GPT-5.6 Terra (Medium) Terminal-Bench 2.1	72.3%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-Omniscience Accuracy	40.5%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-Omniscience Non-Hallucination Rate	8.7%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Coding Index	70,6
Artificial Analysis	GPT-5.6 Terra (Xhigh) Agentic Index	41,4
Artificial Analysis	GPT-5.6 Terra (Xhigh) GPQA Diamond	90.8%
Artificial Analysis	GPT-5.6 Terra (Xhigh) HLE	41.9%
Artificial Analysis	GPT-5.6 Terra (Xhigh) IFBench	66.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) τ²-Bench Telecom	80.4%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-LCR	79.0%
Artificial Analysis	GPT-5.6 Terra (Xhigh) τ-Bench Banking	29.7%
Artificial Analysis	GPT-5.6 Terra (Xhigh) GDPval-AA	47.8%
Artificial Analysis	GPT-5.6 Terra (Xhigh) CritPt	27.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) SciCode	52.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench Hard	62.9%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench 4.0	10.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench 2.1	80.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-Omniscience Accuracy	41.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-Omniscience Non-Hallucination Rate	9.9%
Artificial Analysis	GPT-5.6 Terra (Low) Coding Index	58,1
Artificial Analysis	GPT-5.6 Terra (Low) Agentic Index	25,9
Artificial Analysis	GPT-5.6 Terra (Low) GPQA Diamond	84.3%
Artificial Analysis	GPT-5.6 Terra (Low) HLE	29.2%
Artificial Analysis	GPT-5.6 Terra (Low) IFBench	59.7%
Artificial Analysis	GPT-5.6 Terra (Low) τ²-Bench Telecom	60.5%
Artificial Analysis	GPT-5.6 Terra (Low) AA-LCR	71.3%
Artificial Analysis	GPT-5.6 Terra (Low) τ-Bench Banking	18.8%
Artificial Analysis	GPT-5.6 Terra (Low) GDPval-AA	30.9%
Artificial Analysis	GPT-5.6 Terra (Low) CritPt	9.4%
Artificial Analysis	GPT-5.6 Terra (Low) SciCode	49.9%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench Hard	43.9%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench 4.0	1.5%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench 2.1	62.5%
Artificial Analysis	GPT-5.6 Terra (Low) AA-Omniscience Accuracy	39.8%
Artificial Analysis	GPT-5.6 Terra (Low) AA-Omniscience Non-Hallucination Rate	8.7%
Vals AI	GPT-5.6 Terra Code Migration	47.8%
Vals AI	GPT-5.6 Terra CorpFin v2	65.3%
Vals AI	GPT-5.6 Terra CyberBench v1.1	72.1%
Vals AI	GPT-5.6 Terra EMB	66.2%
Vals AI	GPT-5.6 Terra Finance Agent (v2)	54.4%
Vals AI	GPT-5.6 Terra GPQA Diamond	90.9%
Vals AI	GPT-5.6 Terra Harvey's Legal Agent Benchmark v1	0.8%
Vals AI	GPT-5.6 Terra IOI	87.6%
Vals AI	GPT-5.6 Terra LiveCodeBench	85.9%
Vals AI	GPT-5.6 Terra LegalBench	85.1%
Vals AI	GPT-5.6 Terra Legal Research Bench	41.3%
Vals AI	GPT-5.6 Terra MedCode	43.4%
Vals AI	GPT-5.6 Terra MedScribe	82.9%
Vals AI	GPT-5.6 Terra MMLU Pro	86.7%
Vals AI	GPT-5.6 Terra MMMU Pro	86.5%
Vals AI	GPT-5.6 Terra MortgageTax	67.3%
Vals AI	GPT-5.6 Terra ProgramBench	0.5%
Vals AI	GPT-5.6 Terra ProofBench v1.1	74.0%
Vals AI	GPT-5.6 Terra Public Benefits Bench v1.1	62.4%
Vals AI	GPT-5.6 Terra SAGE	87.0%
Vals AI	GPT-5.6 Terra SkillsBench	58.9%
Vals AI	GPT-5.6 Terra SRE Bench	9.5%
Vals AI	GPT-5.6 Terra SWE-bench	95.4%
Vals AI	GPT-5.6 Terra Tax Agent Bench	30.0%
Vals AI	GPT-5.6 Terra TaxEval v2	76.2%
Vals AI	GPT-5.6 Terra Terminal-Bench 4.0	22.7%
Vals AI	GPT-5.6 Terra Terminal-Bench-Science	10.0%
Vals AI	GPT-5.6 Terra Vals Index	53.1%
Vals AI	GPT-5.6 Terra Vals Multimodal Index	65.1%
Vals AI	GPT-5.6 Terra Vibe Code Bench 1-100	14.8%
Vals AI	GPT-5.6 Terra Vibe Code Bench v1.1	74.6%


	US$ 2,00	US$ 12,00	US$ 0,20	2,30s	79 tps	100,00%
	US$ 2,00	US$ 12,00	US$ 0,20	1,55s	62 tps	100,00%
Não utilizado no roteamento Standard:Por que estes endpoints não são usados
Flex	US$ 1,00	US$ 6,00	US$ 0,10	7,15s	101 tps	100,00%
	US$ 2,20	US$ 13,20	US$ 0,22	1,60s	89 tps	100,00%
	US$ 2,20	US$ 13,20	US$ 0,22	1,57s	80 tps	--
	US$ 2,20	US$ 13,20	US$ 0,22	0,89s	80 tps	100,00%
Fast	US$ 4,00	US$ 24,00	US$ 0,40	2,17s	109 tps	100,00%

Resumo das pontuações de avaliações comparativas para OpenAI: GPT-5.6 Terra (Artificial Analysis e Vals AI)
Fonte	Avaliação comparativa	Pontuação
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Coding Index	52,3
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Agentic Index	23,5
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) GPQA Diamond	74.6%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) HLE	11.4%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-LCR	58.7%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) τ-Bench Banking	15.7%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) GDPval-AA	30.2%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) CritPt	2.0%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) SciCode	45.1%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Terminal-Bench 4.0	0.5%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Terminal-Bench 2.1	56.2%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-Omniscience Accuracy	32.6%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-Omniscience Non-Hallucination Rate	4.4%
Artificial Analysis	GPT-5.6 Terra (High) Coding Index	67,1
Artificial Analysis	GPT-5.6 Terra (High) Agentic Index	36,7
Artificial Analysis	GPT-5.6 Terra (High) GPQA Diamond	89.6%
Artificial Analysis	GPT-5.6 Terra (High) HLE	38.5%
Artificial Analysis	GPT-5.6 Terra (High) IFBench	64.4%
Artificial Analysis	GPT-5.6 Terra (High) τ²-Bench Telecom	78.4%
Artificial Analysis	GPT-5.6 Terra (High) AA-LCR	77.7%
Artificial Analysis	GPT-5.6 Terra (High) τ-Bench Banking	28.7%
Artificial Analysis	GPT-5.6 Terra (High) GDPval-AA	44.4%
Artificial Analysis	GPT-5.6 Terra (High) CritPt	22.9%
Artificial Analysis	GPT-5.6 Terra (High) SciCode	52.4%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench Hard	57.6%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench 4.0	1.5%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench 2.1	75.7%
Artificial Analysis	GPT-5.6 Terra (High) AA-Omniscience Accuracy	41.2%
Artificial Analysis	GPT-5.6 Terra (High) AA-Omniscience Non-Hallucination Rate	9.0%
Artificial Analysis	GPT-5.6 Terra (Max) Coding Index	76,7
Artificial Analysis	GPT-5.6 Terra (Max) Agentic Index	43,2
Artificial Analysis	GPT-5.6 Terra (Max) GPQA Diamond	92.5%
Artificial Analysis	GPT-5.6 Terra (Max) HLE	42.9%
Artificial Analysis	GPT-5.6 Terra (Max) IFBench	71.2%
Artificial Analysis	GPT-5.6 Terra (Max) τ²-Bench Telecom	86.3%
Artificial Analysis	GPT-5.6 Terra (Max) AA-LCR	83.0%
Artificial Analysis	GPT-5.6 Terra (Max) τ-Bench Banking	40.2%
Artificial Analysis	GPT-5.6 Terra (Max) GDPval-AA	48.1%
Artificial Analysis	GPT-5.6 Terra (Max) CritPt	30.0%
Artificial Analysis	GPT-5.6 Terra (Max) SciCode	55.0%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench Hard	57.6%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench 4.0	35.4%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench 2.1	88.0%
Artificial Analysis	GPT-5.6 Terra (Max) AA-Omniscience Accuracy	42.3%
Artificial Analysis	GPT-5.6 Terra (Max) AA-Omniscience Non-Hallucination Rate	10.6%
Artificial Analysis	GPT-5.6 Terra (Medium) Coding Index	64,7
Artificial Analysis	GPT-5.6 Terra (Medium) Agentic Index	30,4
Artificial Analysis	GPT-5.6 Terra (Medium) GPQA Diamond	87.2%
Artificial Analysis	GPT-5.6 Terra (Medium) HLE	33.3%
Artificial Analysis	GPT-5.6 Terra (Medium) IFBench	62.2%
Artificial Analysis	GPT-5.6 Terra (Medium) τ²-Bench Telecom	72.8%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-LCR	74.0%
Artificial Analysis	GPT-5.6 Terra (Medium) τ-Bench Banking	25.6%
Artificial Analysis	GPT-5.6 Terra (Medium) GDPval-AA	38.7%
Artificial Analysis	GPT-5.6 Terra (Medium) CritPt	17.4%
Artificial Analysis	GPT-5.6 Terra (Medium) SciCode	50.5%
Artificial Analysis	GPT-5.6 Terra (Medium) Terminal-Bench 4.0	1.0%
Artificial Analysis	GPT-5.6 Terra (Medium) Terminal-Bench 2.1	72.3%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-Omniscience Accuracy	40.5%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-Omniscience Non-Hallucination Rate	8.7%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Coding Index	70,6
Artificial Analysis	GPT-5.6 Terra (Xhigh) Agentic Index	41,4
Artificial Analysis	GPT-5.6 Terra (Xhigh) GPQA Diamond	90.8%
Artificial Analysis	GPT-5.6 Terra (Xhigh) HLE	41.9%
Artificial Analysis	GPT-5.6 Terra (Xhigh) IFBench	66.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) τ²-Bench Telecom	80.4%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-LCR	79.0%
Artificial Analysis	GPT-5.6 Terra (Xhigh) τ-Bench Banking	29.7%
Artificial Analysis	GPT-5.6 Terra (Xhigh) GDPval-AA	47.8%
Artificial Analysis	GPT-5.6 Terra (Xhigh) CritPt	27.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) SciCode	52.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench Hard	62.9%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench 4.0	10.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench 2.1	80.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-Omniscience Accuracy	41.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-Omniscience Non-Hallucination Rate	9.9%
Artificial Analysis	GPT-5.6 Terra (Low) Coding Index	58,1
Artificial Analysis	GPT-5.6 Terra (Low) Agentic Index	25,9
Artificial Analysis	GPT-5.6 Terra (Low) GPQA Diamond	84.3%
Artificial Analysis	GPT-5.6 Terra (Low) HLE	29.2%
Artificial Analysis	GPT-5.6 Terra (Low) IFBench	59.7%
Artificial Analysis	GPT-5.6 Terra (Low) τ²-Bench Telecom	60.5%
Artificial Analysis	GPT-5.6 Terra (Low) AA-LCR	71.3%
Artificial Analysis	GPT-5.6 Terra (Low) τ-Bench Banking	18.8%
Artificial Analysis	GPT-5.6 Terra (Low) GDPval-AA	30.9%
Artificial Analysis	GPT-5.6 Terra (Low) CritPt	9.4%
Artificial Analysis	GPT-5.6 Terra (Low) SciCode	49.9%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench Hard	43.9%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench 4.0	1.5%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench 2.1	62.5%
Artificial Analysis	GPT-5.6 Terra (Low) AA-Omniscience Accuracy	39.8%
Artificial Analysis	GPT-5.6 Terra (Low) AA-Omniscience Non-Hallucination Rate	8.7%
Vals AI	GPT-5.6 Terra Code Migration	47.8%
Vals AI	GPT-5.6 Terra CorpFin v2	65.3%
Vals AI	GPT-5.6 Terra CyberBench v1.1	72.1%
Vals AI	GPT-5.6 Terra EMB	66.2%
Vals AI	GPT-5.6 Terra Finance Agent (v2)	54.4%
Vals AI	GPT-5.6 Terra GPQA Diamond	90.9%
Vals AI	GPT-5.6 Terra Harvey's Legal Agent Benchmark v1	0.8%
Vals AI	GPT-5.6 Terra IOI	87.6%
Vals AI	GPT-5.6 Terra LiveCodeBench	85.9%
Vals AI	GPT-5.6 Terra LegalBench	85.1%
Vals AI	GPT-5.6 Terra Legal Research Bench	41.3%
Vals AI	GPT-5.6 Terra MedCode	43.4%
Vals AI	GPT-5.6 Terra MedScribe	82.9%
Vals AI	GPT-5.6 Terra MMLU Pro	86.7%
Vals AI	GPT-5.6 Terra MMMU Pro	86.5%
Vals AI	GPT-5.6 Terra MortgageTax	67.3%
Vals AI	GPT-5.6 Terra ProgramBench	0.5%
Vals AI	GPT-5.6 Terra ProofBench v1.1	74.0%
Vals AI	GPT-5.6 Terra Public Benefits Bench v1.1	62.4%
Vals AI	GPT-5.6 Terra SAGE	87.0%
Vals AI	GPT-5.6 Terra SkillsBench	58.9%
Vals AI	GPT-5.6 Terra SRE Bench	9.5%
Vals AI	GPT-5.6 Terra SWE-bench	95.4%
Vals AI	GPT-5.6 Terra Tax Agent Bench	30.0%
Vals AI	GPT-5.6 Terra TaxEval v2	76.2%
Vals AI	GPT-5.6 Terra Terminal-Bench 4.0	22.7%
Vals AI	GPT-5.6 Terra Terminal-Bench-Science	10.0%
Vals AI	GPT-5.6 Terra Vals Index	53.1%
Vals AI	GPT-5.6 Terra Vals Multimodal Index	65.1%
Vals AI	GPT-5.6 Terra Vibe Code Bench 1-100	14.8%
Vals AI	GPT-5.6 Terra Vibe Code Bench v1.1	74.6%

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

TextoContexto de 1,1MUS$ 1 / US$ 5

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

TextoContexto de 1,1MUS$ 0,50 / US$ 2,50

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.

TextoContexto de 1,1MUS$ 1 / US$ 5

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.

TextoContexto de 1,1MUS$ 0,50 / US$ 2,50

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.

DecisõesUS$ 0,10 / US$ 0

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

TextoContexto de 1,1MUS$ 2 / US$ 10

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

TextoContexto de 1,1MUS$ 1 / US$ 5

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.

TextoContexto de 1,1MUS$ 2 / US$ 10

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.

TextoContexto de 1,1MUS$ 1 / US$ 5

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

TextoContexto de 1,1MUS$ 0,10 / US$ 0,50

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

TextoContexto de 1,1MUS$ 0,05 / US$ 0,25

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.

TextoContexto de 1,1MUS$ 0,10 / US$ 0,50

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.

TextoContexto de 1,1MUS$ 0,05 / US$ 0,25

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

TextoContexto de 1,1MUS$ 2 / US$ 10

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

TextoContexto de 1,1MUS$ 1 / US$ 5

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.

TextoContexto de 1,1MUS$ 2 / US$ 10

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.

TextoContexto de 1,1MUS$ 1 / US$ 5

GPT Astra Latest

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

TextoContexto de 1,1M

GPT Sol Latest

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

TextoContexto de 1,1M

GPT Terra Latest

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

TextoContexto de 1,1M