Modelos
Explora 6 modelos LLM canónicos de todos los proveedores
Algunas descripciones forman parte del piloto de traducción automática y aún no han sido revisadas.
DeepSeek's fourth-generation model with improved mixture-of-experts architecture, enhanced reasoning and coding capabilities, and stronger multilingual performance. Competitive with frontier proprietary models.
Meta's efficient MoE model with 17B active parameters (109B total, 16 experts). Supports up to 10M token context — the longest of any production model. Strong performance on reasoning and multilingual tasks.
Meta's quality-focused MoE model with 17B active parameters (400B total, 128 experts). Targets quality-critical tasks with benchmark scores competitive with GPT-4o and Gemini 2.5 Pro.
Alibaba's Qwen3 32B dense language model with strong reasoning and multilingual capabilities, supporting function calling and code generation across diverse tasks.
Modelo de DeepSeek centrado en el razonamiento y entrenado mediante aprendizaje por refuerzo para tareas complejas de varios pasos. Destaca en problemas de matemáticas, ciencia y programación que requieren razonamiento en cadena.
Meta's flagship open-weight model with 70 billion parameters. Strong multilingual capabilities with competitive performance on reasoning and coding benchmarks. Available for self-hosting and through various inference providers.