Released 75 days after MiniMax M2.7 · All MiniMax releases
MiniMax M3 is an open-weight Mixture-of-Experts model with roughly 428 billion total parameters and about 23 billion activated per token, built for frontier coding and agentic work and released under the minimax-community license. It is natively multimodal, trained across text, image, and video from the start, and can read screenshots and operate a desktop computer for end-to-end automation. The model is powered by MiniMax Sparse Attention, a sparse-attention design that supports context windows up to one million tokens while cutting the compute spent per token, giving large speedups over M2 at long context. MiniMax reports 59.0% on SWE-Bench Pro, 66.0% on Terminal-Bench 2.1, and 74.2% on MCP Atlas, alongside results on agentic suites such as BrowseComp, BFCL, and GAIA. M3 is suited to long-horizon tool use, multi-step coding loops, and computer-use automation where both reasoning depth and long-context throughput matter.
MiniMax M3 runs on 6 different routes through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
MiniMax M3 runs on 4 independently monitored routes through the qynio gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 2 further routes for this model are not on the board yet and are not counted above. See uptime for every provider qynio monitors.
Each route hosting MiniMax M3 has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; wallets; deposit available.
Zero data retention is not on by default — abuse monitoring. No training on customer data. GLOBAL; wallets; deposit available.
Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; wallets; deposit available.
Zero data retention is not on by default — abuse monitoring. No training on customer data. EU; deposit available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; wallets; deposit available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; deposit available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call MiniMax M3 through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "fireworks/minimax-m3",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
