Question 1

What is MiniMax M2.5?

Accepted Answer

MiniMax M2.5 is a model from MiniMax, released on Feb 12, 2026. 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 work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

Question 2

How much does MiniMax M2.5 cost?

Accepted Answer

On the Respan gateway, input starts at $0.27 per 1M tokens on Novita and OpenRouter, and output starts at $1.08 per 1M tokens on Novita and OpenRouter, after gateway discounts. Averaged across 6 providers, it costs $0.29 per 1M input tokens and $1.16 per 1M output tokens.

Question 3

Which providers serve MiniMax M2.5 on Respan?

Accepted Answer

6 providers serve MiniMax M2.5: Novita, OpenRouter, IO.net, Featherless, FriendliAI, and MiniMax.

Question 4

What is MiniMax M2.5's context window?

Accepted Answer

MiniMax M2.5 accepts up to 205K tokens of context on its largest provider route.

Question 5

How do I use MiniMax M2.5 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "minimax/MiniMax-M2.5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is MiniMax M2.5?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was FriendliAI at 143 tokens per second, and the lowest response latency was 0.8 seconds on FriendliAI. Speed varies with request size and provider.

Question 7

How does MiniMax M2.5 score on benchmarks?

Accepted Answer

MiniMax M2.5 has 3 published benchmark scores, including Vending-Bench 2 -23.16 and LMArena Elo 1391. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
NovitaSave 10%`novita/minimax/minimax-m2.5`	205K	$0.27/M	$1.08/M
OpenRouter`openrouter/minimax/minimax-m2.5`	205K	$0.27/M	$1.08/M
IO.net`ionet/MiniMaxAI/MiniMax-M2.5`	197K	$0.29/M	$1.18/M
Featherless`featherless_ai/MiniMaxAI/MiniMax-M2.5`	205K	$0.29/M	$1.20/M
FriendliAI`friendliai/MiniMaxAI/MiniMax-M2.5`	197K	$0.30/M	$1.20/M
MiniMax`minimax/MiniMax-M2.5`	200K	$0.30/M	$1.20/M

MiniMax M2.5

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Agents1

Arena2

Apps

MiniMax M2.5 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.