MiniMax API: models and pricing

FastMetal serves 4 MiniMax models through one OpenAI-compatible API key, billed per token from a prepaid balance. Change the base URL and key, and existing code calls them as is. The list also shows MiniMax models we do not serve yet.

Sort by:

10 models

MiniMax M3.1 Flash

minimax-m3.1-flash
Policy unknown

MiniMax M3.1 Flash is a fast model from MiniMax, released on October 19, 2026, for agentic work, coding, computer use and cybersecurity.

Provider:minimax logoMiniMax
Pricing:$0.1583 in · $0.633 out / 1M tokens
Context:1.0M tokens

MiniMax M3

minimax-m3

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Provider:minimax logoMiniMax
Pricing:$0.2954 in · $1.17 out / 1M tokens
Context:1.0M tokens
Text Overall
#106

MiniMax M2.7

minimax-m2.7
Policy unknown

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.

Provider:minimax logoMiniMax
Pricing:$0.3165 in · $1.27 out / 1M tokens
Context:205K tokens
Text Overall
#143

MiniMax M2.5

minimax/minimax-m2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office wor…

Provider:minimax logoMiniMax
Pricing:Not on FastMetal yet
Context:197K tokens
Text Overall
#181

MiniMax M2.5 (free)

minimax/minimax-m2.5:free

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office wor…

Provider:minimax logoMiniMax
Pricing:Not on FastMetal yet
Context:197K tokens

MiniMax M2-her

minimax/minimax-m2-her

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations.

Provider:minimax logoMiniMax
Pricing:Not on FastMetal yet
Context:66K tokens

MiniMax M2.1

minimax/minimax-m2.1

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.

Provider:minimax logoMiniMax
Pricing:Not on FastMetal yet
Context:197K tokens

MiniMax M2

minimax/minimax-m2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,…

Provider:minimax logoMiniMax
Pricing:Not on FastMetal yet
Context:197K tokens
Text Overall
#232

MiniMax M1

minimax/minimax-m1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing…

Provider:minimax logoMiniMax
Pricing:Not on FastMetal yet
Context:1.0M tokens
Text Overall
#208

MiniMax H3-Image

minimax-h3-image

MiniMax H3-Image - image generation

Provider:minimax logoMiniMax
Pricing:$0.0264 per image
Context:- tokens