Fast agentic models built for practical coding throughput. MiniMax’s coding models on Kilo Code include MiniMax M2.1, MiniMax M2.5, MiniMax M2.7, and MiniMax M3. Use them across VS Code, JetBrains IDEs, Cursor, Windsurf, Trae, and the Kilo CLI — with pay-as-you-go pricing and no markup over the underlying provider rates.
Sorted by coding-index where published. Click any model for the full review with benchmarks, real-world Kilo usage, and provider-specific pricing.
MiniMax
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
MiniMax
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...
MiniMax
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
MiniMax
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,...
MiniMax builds high-throughput foundation models that often punch above their price for agentic development work. The M-series emphasizes practical coding loops: fast responses, broad instruction following, and enough reasoning depth for multi-file edits without frontier-model pricing.
Pay-as-you-go, no markup over the underlying provider rates. Cheapest first.
| Model | Input / 1M | Output / 1M | Context | Coding index |
|---|---|---|---|---|
| MiniMax: MiniMax M2.1 | $0.300 | $1.20 | 205K | — |
| MiniMax: MiniMax M2.5 | $0.300 | $1.20 | 205K | — |
| MiniMax: MiniMax M2.7 | $0.300 | $1.20 | 205K | — |
| MiniMax: MiniMax M3 | $0.300 | $1.20 | 1049K | — |
Two ways: hosted in Kilo with no setup, or through your own provider keys.
The fastest path: install Kilo Code, sign in, pick minimax from the model picker. No API keys, no markup. Works in VS Code, JetBrains, Cursor, Windsurf, Trae, and the Kilo CLI.
See live model leaderboard →Already have an account with MiniMax, OpenRouter, AWS Bedrock, Google Vertex, Together AI, or another compatible provider? Plug your key into Kilo Code and keep your existing billing relationship.
BYOK setup guide →See coding-model lineups from MiniMax’s closest competitors.
MiniMax’s flagship is among the strongest coding models on the Kilo Code leaderboard, ranked by Code, Plan, Ask, Debug, and Review usage.
VS Code, Cursor, Windsurf, Trae, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand, RubyMine, Android Studio), and the Kilo CLI / terminal.
Switch between MiniMax and 500+ other models with one click. Pay only for what you use, at the underlying provider rate.
The latest MiniMax M-series model with the highest coding index is usually the best choice for difficult coding. Earlier M2 variants remain useful for cheaper everyday agent loops.
MiniMax models work in every Kilo-supported IDE and the Kilo CLI.
MiniMax pricing is shown per model in Kilo Code and is billed with no markup over provider rates.
No. The MiniMax models listed in Kilo Code are hosted API models.
Newer M-series releases target stronger reasoning and coding reliability, while older or smaller variants emphasize speed and cost efficiency.
MiniMax models work in every Kilo-supported IDE and the Kilo CLI.
Install Kilo Code and get instant access to MiniMax: MiniMax M2.1 and 3 other MiniMax models, plus 500+ frontier and open-source options. Free to start, no credit card required.