DeepSeekDSH
Independent community guideNot affiliated with DeepSeek.Download versions and guide references

MiniMax H3 vs M-Series in DSH: Which Works?

Beginner guide to MiniMax H3 vs M3 in DSH: why H3 is for video while M3 handles coding, how to avoid region 401 errors, and 4-step DSH setup instructions.

Maintained by DeepSeekDSH (independent site)Documentation review
On this page
MiniMax H3 guide illustration showing separate coding and video workflows

After seeing impressive MiniMax H3 video demos online, many beginners open DeepSeek Harness (DSH) and try typing MiniMax-H3 straight into the coding model list—only to hit immediate errors.

One plain distinction saves you hours of guesswork:

  • MiniMax H3 is the "video director": As described in the official MiniMax H3 announcement, H3 generates video, audio, and creative media assets—it is not a text/coding model in MiniMax's chat API.
  • MiniMax M3 (and the M-series) is the "software developer": When you want MiniMax to read project folders, edit code, and run tools inside DSH, pick an M-series model such as MiniMax-M3.

Side-by-side table: which MiniMax model and URL match your account?

Beginners hit two classic traps with MiniMax: pasting video model H3 into a coding slot, or mixing up China-region and International account URLs (which causes instant 401 authentication errors). Match your account below:

Your Goal & Account RegionWhich Model to UseExact Base URLHow to Connect in DSH
International account (platform.minimax.io) for codingMiniMax-M3 (M-series)https://api.minimax.io/anthropic (or /v1)Built-in MiniMax international card (anthropic-messages)
China account (platform.minimaxi.com) for codingMiniMax-M3 (M-series)https://api.minimaxi.com/anthropicBuilt-in MiniMax China (minimax-cn) card
Generating a product promo videoMiniMax H3MiniMax video studio / dedicated media APIDo not enter in DSH chat models—save the .mp4 first, then let DSH add it to your site

(Endpoints and model lists come from MiniMax's Anthropic SDK text guide, OpenAI SDK text guide, and the official DSH provider docs.)

Beginner Tutorial 1: Connect MiniMax M3 for coding in DSH (4 steps)

Follow these four steps to get MiniMax coding models running cleanly inside DSH:

Step 1: Check your API key's region and plan rules

Sign in to your MiniMax developer console (official setup prerequisites) and copy your API key while keeping three rules in mind:

  1. Match .io vs .com: Keys created on international platform.minimax.io only work on .io endpoints, and China platform.minimaxi.com keys only work on .com endpoints.
  2. Subscription keys vs pay-as-you-go keys are separate: As noted in MiniMax's Token Plan overview, subscription keys (M Plan / Token Plan) cannot be swapped with standard pay-as-you-go keys, and special media models like H3 sit outside standard text Token Plans.
  3. Preview model restrictions: Some preview IDs such as MiniMax-M3.1-Flash-Preview are restricted to M Plan and MiniMax Code subscribers, so standard pay-as-you-go accounts should start with MiniMax-M3.

Step 2: Select the matching built-in MiniMax card in DSH

Open DSH on your computer and click Settings -> Models -> Add provider:

  • Pick MiniMax (international) or MiniMax China (minimax-cn) to match where you created your key, paste the key, and click Save (full walkthrough in our DSH MiniMax provider guide).
  • Protocol tip: DSH's built-in MiniMax cards automatically use anthropic-messages. If you ever build a manual entry under Add a custom provider (custom provider guide), pair /anthropic with anthropic-messages or pair /v1 with openai-completions—never mix the two!

Step 3: Click "New session" and pick MiniMax-M3

Always click New session after changing providers or models—existing chat tabs stay pinned to whichever route sent their first message.

Step 4: Run a safe test in an empty folder

Select an empty dsh-test folder via Choose workspace and send "Reply with connected and list the files in this folder" to verify both chat and workspace tools work.

Beginner Tutorial 2: Combine H3 video assets with DSH web coding in 3 easy steps

Building a landing page that needs a custom product video? Skip complicated automation plugins on day one and use this clean 3-step handoff:

  1. Draft shot prompts in DSH: Ask your coding model in DSH to read your product copy and write three clear camera/scene prompts.
  2. Generate and inspect the video in MiniMax H3: Paste the prompt into MiniMax's H3 video interface, check that product details and audio look right, and download the finished .mp4 into your project's public/ folder (for example, public/product-demo.mp4).
  3. Ask DSH to wire the video into your webpage: Back in DSH, tell the coding agent: "I saved the approved video at public/product-demo.mp4—embed it in the hero section with muted loop playback and mobile fallback styling."

(Only if you later need to generate dozens of videos automatically every week should you explore wiring a dedicated video tool server through DSH's MCP client.)

Common questions

What happens if I type MiniMax-H3 into DSH's custom model box anyway?

Requests fail with a 404 or unsupported-model error because MiniMax's chat/tool endpoints only serve M-series text models, not H3 video generation jobs.

If MiniMax-M3 understands images, why can't it generate videos too?

Reading an uploaded screenshot and rendering an .mp4 video file are completely different pipelines. M3 can inspect UI screenshots to help fix CSS, while H3 creates video clips.

Do I have to buy a monthly subscription to test MiniMax in DSH?

No. Standard pay-as-you-go API credits work fine for MiniMax-M3 so you only pay for the tokens you use.

Why did saving my key succeed, yet my first message failed with 401?

Saving a key only stores it locally on your computer. Getting 401 on your first message almost always means an international .io key was pasted into the China .com card (or vice versa).

Model and workflow guides

Models and costs

Gemini 4 Neon is here. When is it worth switching models?

Compare Gemini 4 Neon in two coding setups, work through a $0.45 API example, and find Neon in Gemini, Google AI Studio, and Antigravity.

Read →
Models and costs

GPT-6.2 Astra & Sol Guide: Specs, Pricing & Choice

Beginner guide to OpenAI's GPT-6.2 Astra and Sol: Claude vs DeepSeek price table, plain-English benchmarks, 272K cliff, and step-by-step DSH & Python setup.

Read →
Models and costs

GPT-6.1 Terra Guide: Uses, Pricing and Sol Comparison

Beginner guide to OpenAI's GPT-6.1 Terra: half-price visual, computer-use, and writing model compared with Sol and DeepSeek, plus DSH and Python setup steps.

Read →
Model setup and costs

Connect Local Qwen 3.8 27B to DSH

Beginner guide to connecting local Qwen 3.8 27B to DSH: GPU memory table, LM Studio / Ollama / llama.cpp port setup, exact 5-field config, and error fixes.

Read →
Model setup and costs

Codex Costs: API Billing vs Subscription Usage

Beginner guide to OpenAI Codex costs: ChatGPT Plus login vs API-key billing table, real per-prompt dollar math, and 3 steps to lock a monthly budget cap.

Read →
Model setup and costs

Connect Grok API to DSH: Setup & Tools

Step-by-step beginner guide to connecting xAI's Grok API (grok-4.7) to DSH: Grok vs Groq comparison, exact 5-field custom provider setup, and 401/404 fixes.

Read →
Model setup and costs

Choose a Gemini Model by Task and Cost

Beginner guide to Google Gemini model selection: compare 3.8 Flash, 4 Argon, and DeepSeek prices, watch 2027 rate changes, and set up DSH in 4 simple steps.

Read →
Model benchmarks and engineering

Gemini 4 Argon Coding Benchmarks & 1M Window

Beginner guide to Google's Gemini 4 Argon coding scores vs Claude and GPT, how its shared 1M window and 65K output cap work, plus 4-step DSH setup.

Read →
API costs and enterprise ROI

Gemini 4 Argon API Pricing, Cache & ROI Guide

Beginner guide to Gemini 4 Argon API pricing: Dec 2026 2x rate jump, how 95% auto-caching and thinking tokens bill, DeepSeek cost comparison, and calculator.

Read →
Model setup and costs

Claude Sonnet vs Opus: Which Should You Use?

Beginner guide to Claude Sonnet 5.5 vs Opus 5.5: side-by-side API prices, per-prompt cost math, clear rules on when to upgrade, and 4-step DSH setup.

Read →
Models and costs

Opus 5.5 vs Fable 5.2: Which Model Is Right for You?

Beginner guide to Claude Opus 5.5 vs Fable 5.2: side-by-side API prices, coding benchmarks, per-task cost math, 30-day retention rules, and 4-step DSH setup.

Read →
Content creation

How to draft a video script with Media Desk for DeepSeek Harness

Turn a phone note into a video script, cover, and storyboard with Media Desk for DeepSeek Harness. See how to install it, set up images, and export a draft.

Read →
Mobile and remote access

Use DeepSeek Harness on Your Phone: Beginner Guide

Zero-jargon beginner guide to using DeepSeek Harness on your phone: find your computer IP, connect over home Wi-Fi in 2 minutes, or use Tailscale on 4G/5G.

Read →
API credentials and troubleshooting

Kimi API Key Errors: Region, Model and Permissions

Beginner fix guide for Kimi / Moonshot API key errors: match .ai vs .cn URLs, avoid retired model names and K3 Max typos, decode 401/404/429, and set up DSH.

Read →
Image editing and tools

AI Image Editing: Prompts, Masks and Review

Beginner guide to AI image editing without ruining your subject: copy our 4-line prompt template, avoid PNG mask traps, inspect edges, and use DSH safely.

Read →