MiniMax M3 on VM0. Official MiniMax coding model at ×0.2
Official MiniMax M3 routing for coding agents, 1M context, and native multimodal understanding.
1M tokens · Text / Vision / Code · Prompt cache
MiniMax M3 is MiniMax's frontier coding and agentic model, exposed on VM0 through the official MiniMax Anthropic-compatible endpoint. It is the right MiniMax choice when an agent needs stronger coding, tool use, long-context reasoning, and native vision understanding than the retained M2 series.
VM0 prices M3 from MiniMax's standard non-promotional pay-as-you-go tier for the base context band: $0.60 / $2.40 per 1M tokens, with prompt cache reads at $0.12 / 1M and no separate cache-write billing in the M3 table. MiniMax M2.1 remains available for lower-cost compatibility, while M3 is the default MiniMax BYOK model.
¿Qué es MiniMax M3?
June 1, 2026 · Official MiniMax M3 text model alongside the retained M2 series.
MiniMax M3 is the new official MiniMax text model for coding and agentic workloads. MiniMax describes it as combining frontier coding capability, a 1M-token context window, and native multimodal understanding.
On VM0, M3 is added to the existing MiniMax API-key provider instead of creating a new integration. It uses the same api.minimax.io/anthropic routing surface and the same MINIMAX_API_KEY secret as M2.
The existing M2 entries stay available, while M3 is the MiniMax provider default for new selections.
Qué destaca de MiniMax M3
Características principales de arquitectura y capacidades.
M3 uses MiniMax Sparse Attention for ultra-long context. The official API supports up to 1M tokens with a 512K guaranteed minimum, automatic prompt cache support, and native multimodal understanding.
Especificaciones rápidas
Benchmarks de MiniMax M3
MiniMax positions M3 around coding, agentic tasks, and long-horizon execution. Treat these as vendor-reported signals and validate against your own VM0 agent regression set.
Precios de MiniMax M3
Precio de lista del proveedor, por 1M de tokens.
Cómo se comporta MiniMax M3 en la práctica
Comportamiento observado en ejecuciones de agentes en producción.
Coding agents
The best MiniMax option for coding assistants, long tool chains, and multi-step repository work.
Long context
A 1M context window lets agents keep large documents, code, logs, and previous work in scope without switching model families.
Multimodal
Native vision understanding makes M3 a better fit than M2 when screenshots, diagrams, or visual artifacts are part of the workflow.
Mejores tareas para MiniMax M3
The coding agent that must stay on MiniMax
Repository edits, debugging, and agentic coding flows where your deployment already uses MiniMax keys but needs a stronger coding model than M2.1.
The long-context review run
Large pull requests, logs, notebooks, or design documents that should stay in one model context while the agent reasons and edits.
The multimodal investigation
Workflows that mix text with screenshots or diagrams. M3 is marked image-input capable on VM0, while the M2 entries stay text/code only.
Cuándo evitar MiniMax M3
Skip M3 when you need the absolute lowest MiniMax cost and text-only M2.1 is already good enough, or when you need OpenRouter/Vercel routing because this VM0 entry intentionally uses only the official MiniMax path.
MiniMax M3 vs otros modelos
MiniMax M3 vs Kimi K2.6
Both target coding and agentic work at low cost. Kimi has broader existing gateway support on VM0, while M3 uses the official MiniMax route and gives MiniMax users the newer model.
MiniMax M3 vs Claude Sonnet 4.6
Sonnet 4.6 remains the baseline for reliability on complex English tool-use. M3 is much cheaper and attractive for MiniMax-native coding agents, but should be validated on critical workflows.
Conclusión: ¿deberías usar MiniMax M3?
Use MiniMax M3 when you want the official MiniMax coding model with long context and vision support. Keep M2.1 when cost and compatibility matter more.
Preguntas frecuentes
Is MiniMax M2.1 still available?
Yes. VM0 keeps MiniMax M2.1 in the direct MiniMax provider. M3 is now the default MiniMax BYOK model.
Does VM0 route MiniMax M3 through OpenRouter or Vercel?
No. This entry intentionally uses only the official MiniMax Anthropic-compatible endpoint.
Which M3 pricing tier does VM0 show?
The VM0 model page and usage seed use MiniMax's non-promotional standard base tier. MiniMax also documents a higher standard tier for input above 512K tokens.
Alternativas
Usar MiniMax M3 en VM0
Dos formas de acceder a MiniMax M3 en VM0
VM0 admite MiniMax M3 como modelo Built-in facturado en créditos VM0, y mediante bring-your-own con una MiniMax API key. La ruta Built-in usa enrutamiento gestionado de VM0 y el multiplicador de créditos explicado abajo; la ruta bring-your-own te factura directamente con el proveedor upstream y omite la conversión de créditos VM0.
Recomendación de VM0
VM0 posiciona MiniMax M3 como una opción de ahorro en lugar de un modelo principal de agente. Úsalo para optimizar el coste unitario en trabajo no principal, como clasificación masiva, prefiltros, respuestas cortas con requisitos de latencia o agentes heredados fijos, manteniendo Claude Opus 4.7, Claude Opus 4.6 o Claude Sonnet 4.6 en los pasos que deciden la ejecución.
Créditos y el multiplicador ×0.2
Cada modelo Built-in en VM0 se valora como un múltiplo de Claude Sonnet 4.6, que establece la base de ×1 crédito. MiniMax M3 factura a ×0.2 créditos. El multiplicador es lo que aparece en tu factura de VM0; el precio de lista del proveedor en la tabla de arriba es lo que cobra el proveedor upstream antes de que VM0 lo convierta en créditos.
MiniMax M3 factura a ×0.2, lo que significa que un paso aquí cuesta solo 0.2× los créditos de un paso equivalente en Sonnet 4.6 (la base ×1). Esto lo sitúa muy por debajo de la base de créditos y lo convierte en la elección natural para trabajo en segundo plano de alto volumen donde el coste por paso importa más que la máxima calidad de razonamiento.
Disponible en VM0 desde June 1, 2026.