Skip to content

MiniMax M3.1 Flash

MiniMax's multimodal agent and coding model joins the catalog, free on NVIDIA's developer tier.

Open MiniMax M3.1 Flash
Table comparing MiniMax M3.1 Flash with DeepSeek V4.1 Flash, Kimi K3, GLM-5.3, GPT-5.6 Sol and Opus 5 on CoWork, computer use, coding, cyber and general benchmarks

Update 2026-10-25: the launch-week free offer has ended (OpenRouter, Kilo, Cline and OpenCode Go retired their free ids on 2026-10-22). It is free again through NVIDIA's own free endpoint, which is rate limited and has no published price. Call minimax/minimax-m3.1-flash:free with your AnyRouter key to use it. Every other route is paid, so add your own MiniMax, OpenRouter or Vercel key for steady use.

MiniMax M3.1 Flash is built for agent work and coding. It has a 1M token context, takes text, image and video, and always reasons. List price is $0.15 input and $0.60 output per 1M tokens. With your own MiniMax key under Dashboard → BYOK, you pay MiniMax directly at that price.

AI SDK
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({ model: anyrouter("minimax/minimax-m3.1-flash:free"), prompt: "Find the bug in this function." })
Coding agent
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr claude --model "minimax/minimax-m3.1-flash:free"

Playbooks: AI SDK, coding agents, OpenAI SDK.

Chart of DeepSWE v1.1 score against cost per task for MiniMax M3.1 Flash at high, xhigh and max effort (68.1 to 73.7 percent) and other models
DeepSWE v1.1 score vs. cost per task. Source: MiniMax.
Chart of Automation-Bench score against cost per task for MiniMax M3.1 Flash at five effort levels (52.8 to 62.8 percent) and other models
Automation-Bench score vs. cost per task. Source: MiniMax.

Related posts

Looking for the full catalog? Browse all models.