MiniMax M2.5

minimax/minimax-m2.5

MiniMax-M2.5 is a MiniMax M2-series language model released in February 2026 for real-world productivity, trained with reinforcement learning across hundreds of thousands of complex real-world environments. MiniMax highlights coding across more than ten languages and the full development lifecycle, planning projects like a software architect before writing code, plus agentic search, tool use and office work. MiniMax now lists it as a legacy model behind M2.7 and M3.

Input price
$0.30USD / 1M tokens
Output price
$1.20USD / 1M tokens
Cache read
$0.03USD / 1M tokens
Context window
204.8K
Max output
131.1K

Specifications

CapabilitiesChatReasoningStructured outputFunction calling
Input
Text
Output
Text
Available

Questions

FAQ

How do I call MiniMax M2.5 through SandBase?

Create a SandBase API key, then send requests with the model ID "minimax/minimax-m2.5" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does MiniMax M2.5 cost?

$0.30 per 1M input tokens and $1.20 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of MiniMax M2.5?

204.8K tokens of context, with up to 131.1K output tokens per response.

Which features does MiniMax M2.5 support?

MiniMax M2.5 supports reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate MiniMax account?

No. One SandBase API key and balance gives you access to MiniMax M2.5 and the other models in the catalog; you do not need to sign up with MiniMax separately.