Question 1

What is MiniMax M2?

Accepted Answer

MiniMax M2 is a model from MiniMax, released on Oct 27, 2025. MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. $0.255 per million input tokens, $1.02 per million output tokens. 204,800 token context window, maximum output of 131,072 tokens. Higher uptime with 3 providers. Includes independent benchmarks from Artificial Analysis.

Question 2

How much does MiniMax M2 cost?

Accepted Answer

On the Respan gateway, input starts at $0.27 per 1M tokens on Novita, and output starts at $1.08 per 1M tokens on Novita, after gateway discounts. Averaged across 5 providers, it costs $0.29 per 1M input tokens and $1.18 per 1M output tokens.

Question 3

Which providers serve MiniMax M2 on Respan?

Accepted Answer

5 providers serve MiniMax M2: Novita, MiniMax, OpenRouter, Tera, and Google Vertex AI. Tera and Google Vertex AI require your own provider API key (BYOK).

Question 4

What is MiniMax M2's context window?

Accepted Answer

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

Question 5

How do I use MiniMax M2 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". 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?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was MiniMax at 47 tokens per second, and the lowest response latency was 1.4 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does MiniMax M2 rank on the Respan Index?

Accepted Answer

MiniMax M2 scores 15.9 out of 100 on the Respan Index v1.1, ranking #119 of 138 models. By category: Coding 5.3, Agents 14.0, Reasoning 10.8, Knowledge & language 12.6 (estimated), and Human preference 47.1. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does MiniMax M2 score on benchmarks?

Accepted Answer

MiniMax M2 has 17 published benchmark scores, including SWE-bench Verified 69.4%, τ²-Bench 77.2%, and HLE (w/ tools) 31.8%. 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`	205K	$0.27/M	$1.08/M
MiniMax`minimax/MiniMax-M2`	200K	$0.30/M	$1.20/M
OpenRouter`openrouter/minimax/minimax-m2`	205K	$0.30/M	$1.20/M
TeraBYOK only`tera/MiniMaxAI/MiniMax-M2`	197K	$0.30/M	$1.20/M
Google Vertex AIBYOK only`vertex_ai/minimaxai/minimax-m2-maas`	205K	$0.30/M	$1.20/M

MiniMax M2

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Indexv1.1

Coding5

Apps

MiniMax M2 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Agents7

Reasoning2

Arena2

Other1