A beginner tutorial on signing up for MorLLM's free tier to get GLM 5.2, DeepSeek V4, and Qwen 3.6 API keys, then manually wiring MorLLM in as a custom provider inside a coding agent like OpenCode since it isn't a built-in provider.
Code With Yousaf8 minTranscript found
Quick learning frame
Read this before watching.
Creative automation accelerates production while keeping human taste in brief, source selection, generation, editing, and critique.
New playlist item from Code With Yousaf; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to onboard onto a free AI model API hub and manually configure it as a custom provider in a coding agent when it isn't pre-listed.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Brief
02Source material
03Generation
04Selection
05Edit
06Taste review
07Reusable recipe
Deep lesson
Turn this video into working knowledge.
1,088 cleaned transcript words reviewed across 320 timed caption segments.
Thesis
FREE AI APIs! GLM 5.2 + DeepSeek V4 + Qwen 3.6 🤯 teaches a practical creative automation move: A beginner tutorial on signing up for MorLLM's free tier to get GLM 5.2, DeepSeek V4, and Qwen 3.6 API keys, then manually wiring MorLLM in as a custom provider inside a coding agent like OpenCode since it isn't a built-in provider.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:37
Free Signup Flow
“limit, so there are other methods that you can re-access these API keys. So, let's get uh started. Search in your browser for Mor LLM. After searching that, you can see this first website, Mor LLM. Open that...”
He finds MorLLM, a hub offering free API access to open Chinese models (GLM 5.2, DeepSeek V4, Qwen 3.6) that compete with Google's and Anthropic's paid models; signup is Google-account based and walks through an onboarding flow introducing the model lineup, and critically you select 'continue without a plan' to land on the free-tier dashboard rather than picking a paid plan. Sign up for a free-tier API hub the same way (Google account, skip the paid plan step) and note exactly which screen offers the free/no-plan path before you commit to a paid tier by accident.
3:50
Model Menu & Limits
“you with your programming and general question today? So, let's now get the API key. Down, you can see use this model via API. So, this is the model name. Let's open, for example, open open code or...”
The dashboard's open source models section lists GLM 5.2, MiniMax M3, MiniMax M2.7, DeepSeek V4 flash, and Qwen 3.6, each testable directly in a built-in chat window before touching any code; when you hit the free-tier rate limit, the workaround shown is creating a fresh account to reset access, while adding a billing method is what unlocks full rate limits. Test at least two of the listed free models directly in the hub's own chat UI first, so you know which model actually answers your kind of question before wiring it into a coding agent.
6:27
Custom Provider Wiring
“Let's check the response of GLM 5.2. Yeah, hello. How can I help you today? We can select this MiniMax M3 also. What is OpenCode? So, let's check the response of MiniMax M3 also. Yeah, OpenCode is an...”
Because MorLLM isn't a built-in popular provider inside OpenCode, he adds it as a custom provider by hand: provider name, base URL (copied from the model's 'use via API' page, ending in /v1), API key, model ID (copied exact model name), and a display name, then repeats the model-ID step to add a second model, MiniMax M3, to the same provider; both then show up selectable in OpenCode's model picker and respond correctly when tested. Practice adding one model as a custom provider in your coding agent by hand (name, base URL, key, model ID) so you're not stuck only using pre-listed 'popular' providers.
01
Brief
Start with this video's job: A beginner tutorial on signing up for MorLLM's free tier to get GLM 5.2, DeepSeek V4, and Qwen 3.6 API keys, then manually wiring MorLLM in as a custom provider inside a coding agent like OpenCode since it isn't a built-in provider. Treat "Brief" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:37, where the video says: “limit, so there are other methods that you can re-access these API keys. So, let's get uh started. Search in your browser for Mor LLM. After searching that, you can see this first website, Mor LLM. Open that...”
02
Source material
Use "Source material" to locate the part of the creative automation mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 3:50, where the video says: “you with your programming and general question today? So, let's now get the API key. Down, you can see use this model via API. So, this is the model name. Let's open, for example, open open code or...”
03
Generation
Turn "Generation" into the reusable artifact for this lesson: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints. This is where watching becomes something you can inspect and reuse.
04
Selection
Use "Selection" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Edit
Use "Edit" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Taste review
Use "Taste review" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
07
Reusable recipe
Connect "Reusable recipe" to FREE AI APIs! GLM 5.2 + DeepSeek V4 + Qwen 3.6 🤯 by naming the claim, the evidence, and the artifact it should produce.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints..
Example
Creative automation proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the creative automation pattern.
Example
Teach-back module
Transform the lesson into a definition, a Brief -> Source material -> Generation -> Selection -> Edit -> Taste review -> Reusable recipe diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
mistaking novelty for quality
no source/brief discipline
shipping generated media without taste review
Letting the lesson drift into generic content advice.
Letting the lesson drift into tool hype.
Letting the lesson drift into creative output without selection criteria.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: A beginner tutorial on signing up for MorLLM's free tier to get GLM 5.2, DeepSeek V4, and Qwen 3.6 API keys, then manually wiring MorLLM in as a custom provider inside a coding agent like OpenCode since it isn't a built-in provider.
02
Explain the practical stakes without hype: New playlist item from Code With Yousaf; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Brief -> Source material -> Generation -> Selection -> Edit -> Taste review -> Reusable recipe sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: FREE AI APIs! GLM 5.2 + DeepSeek V4 + Qwen 3.6 🤯
- URL: https://www.youtube.com/watch?v=D7mLq35inVE
- Topic: Creative Automation
- My current learning frame: Sign up for the free MorLLM tier, wire GLM 5.2 in as a custom provider inside OpenCode or Kilo Code, and run a real coding prompt through it to confirm the free-tier connection actually works end to end.
- Why this matters: New playlist item from Code With Yousaf; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:37 / Evidence 1: "limit, so there are other methods that you can re-access these API keys. So, let's get uh started. Search in your browser for Mor LLM. After searching that, you can see this first website, Mor LLM. Open that..."
- 2:08 / Evidence 2: "Where do you want to use Morp? Let's press this API. Welcome to Morp. Make your first API. So, here you we can move to the Yeah, this is what we can access for the first time. Okay,..."
- 3:50 / Evidence 3: "you with your programming and general question today? So, let's now get the API key. Down, you can see use this model via API. So, this is the model name. Let's open, for example, open open code or..."
- 6:27 / Evidence 4: "Let's check the response of GLM 5.2. Yeah, hello. How can I help you today? We can select this MiniMax M3 also. What is OpenCode? So, let's check the response of MiniMax M3 also. Yeah, OpenCode is an..."
Video-aware target:
- Prompt lane: Creative automation
- Mechanism to extract: Extract the creative production loop, especially where the human keeps taste, selection, and final judgment.
- Artifact to produce: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
- Artifact must include: brief; source inputs; generation recipe; selection criteria; edit/review checkpoint
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Extract the creative production loop, especially where the human keeps taste, selection, and final judgment. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Brief -> Source material -> Generation -> Selection -> Edit -> Taste review -> Reusable recipe
- answers to these source questions: What asset is being produced? | What inputs and tools drive it? | Where does human taste intervene?
- 3 concrete examples that apply the video idea to real agentic work, such as Claude-generated video campaign; image-to-site workflow; voice or video editing loop
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: mistaking novelty for quality; no source/brief discipline; shipping generated media without taste review
- a checklist for the next real workflow, focused on: brief, inputs, generation, selection, critique
- one practical exercise with a clear done signal: Build one reusable creative recipe and define what would make the result rejectable.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "FREE AI APIs! GLM 5.2 + DeepSeek V4 + Qwen 3.6 🤯", not a generic Creative Automation essay.
- Anchor each creative step to transcript evidence about inputs, model/tool choices, iteration, editing, or critique.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic content advice; tool hype; creative output without selection criteria.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints..
A reusable artifact with a done signal and one verification step.03
Creative automation teach-back card
Explain the creative automation mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
What step does the video say to take during MorLLM signup to make sure you land on the free tier instead of a paid plan?
What does the video say happens when you hit the free-tier rate limit on MorLLM, and what's the described workaround?
Why did the creator have to use OpenCode's custom provider option instead of picking MorLLM from the provider list?
Source shelf
Use the video as a doorway, then verify with primary sources.
