Comparação · 2026-06-29
GPT-5.1 Codex vs Claude Sonnet 4.5 (latest)
Comparação de preços, janela de contexto e recursos entre GPT-5.1 Codex (OpenAI) e Claude Sonnet 4.5 (latest) (Anthropic). Foco: coding.
| GPT-5.1 Codex | Claude Sonnet 4.5 (latest) | |
|---|---|---|
| Fornecedor | OpenAI | Anthropic |
| Preço de entrada / 1M tokens | $1.25 | $3.00 |
| Preço de saída / 1M tokens | $10.00 | $15.00 |
| Total por 1M (entrada + saída) | $11.25 | $18.00 |
| Janela de contexto | 400K | 200K |
| Tokens de saída máximos | 128K | 64K |
| Tool calling | ✓ Sim | ✓ Sim |
| Saída estruturada | ✓ Sim | Desconhecido |
| Raciocínio | ✓ Sim | ✓ Sim |
| Entrada de imagem | ✓ Sim | ✓ Sim |
| Pesos abertos | ✗ Não | ✗ Não |
| Disponibilidade de provedores | 19 provedores | 21 provedores |
| Data de lançamento | 2025-11-13 | 2025-09-29 |
| Data de conhecimento | 2024-09-30 | 2025-07-31 |
Resumo rápido
- GPT-5.1 Codex é cerca de 1.6× mais barato por 1M de tokens combinados (entrada + saída).
- GPT-5.1 Codex tem uma janela de contexto maior (400K vs. 200K).
- Apenas GPT-5.1 Codex oferece saída estruturada / modo JSON.
- Claude Sonnet 4.5 (latest) está disponível em mais provedores (21 vs. 19).
How to read this comparison
This page compares GPT-5.1 Codex and Claude Sonnet 4.5 (latest) on the dimensions that matter most for production LLM selection: per-token cost, context window, declared capabilities (tool calling, structured output, reasoning, vision), and provider availability.
Green highlights in the table indicate which model leads on a given row. "Leads" means lower price or higher context/capability — not necessarily "better for your use case". A model that costs 3× more may still be the right choice if it unlocks a capability you need.
What this comparison does NOT tell you
- Quality / accuracy — we have no benchmark data. Declared capabilities ≠ measured performance.
- Latency — time-to-first-token varies by provider, region and load. Test with your actual traffic.
- Prompt caching savings — if you reuse system prompts, the cheaper model on headline rate may not be cheapest in practice.
- Fine-tuning availability — not all models can be fine-tuned, even if they are open-weight.
Data is refreshed daily. If a model's capabilities or pricing change, this page updates automatically on the next build cycle.
Frequently asked questions
GPT-5.1 Codex é mais barato que Claude Sonnet 4.5 (latest)?
GPT-5.1 Codex custa $1.25/1M tokens de entrada + $10.00/1M de saída; Claude Sonnet 4.5 (latest) custa $3.00/1M + $15.00/1M. Mais barato por 1M combinados: GPT-5.1 Codex.
Qual modelo tem janela de contexto maior, GPT-5.1 Codex ou Claude Sonnet 4.5 (latest)?
GPT-5.1 Codex tem janela maior — 400,000 tokens vs. 200,000.
Onde posso executar GPT-5.1 Codex e Claude Sonnet 4.5 (latest)?
GPT-5.1 Codex está em 19 provedores; Claude Sonnet 4.5 (latest) em 21. Veja a lista completa na página de cada modelo.
Explore more
Última atualização:
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.