1
00:00:00,000 --> 00:00:04,080
In this tutorial, we'll install OpenAI's Codex app on Windows.

2
00:00:04,860 --> 00:00:11,200
Then, using CC Switch and AI HubMix, we'll make it run on almost any AI model, not just OpenAI's.

3
00:00:12,720 --> 00:00:15,640
Start in your browser. Search for Codex Download.

4
00:00:15,640 --> 00:00:31,600
Open the official Codex page on openai.com.

5
00:00:41,980 --> 00:00:43,700
Click Download for Windows.

6
00:00:45,640 --> 00:00:56,760
The installer itself is tiny, so it's done in seconds.

7
00:00:56,760 --> 00:01:02,460
When it finishes, show it in File Explorer.

8
00:01:02,460 --> 00:01:10,840
Right-click the installer and run it as administrator.

9
00:01:10,840 --> 00:01:17,920
A setup window opens, and the real download begins.

10
00:01:17,920 --> 00:01:36,520
This package is about 700 megabytes.

11
00:01:36,520 --> 00:01:40,040
Fair warning, this part can be slow, usually 5-6 minutes.

12
00:01:40,820 --> 00:01:41,700
So let's skip the wait.

13
00:01:49,780 --> 00:01:52,480
And we're back, 96% and counting.

14
00:02:01,720 --> 00:02:04,880
The moment it hits 100, everything happens on its own.

15
00:02:06,520 --> 00:02:25,260
The installer closes, and Codex launches itself.

16
00:02:25,260 --> 00:02:26,900
It lands on a sign-in screen.

17
00:02:26,900 --> 00:02:28,240
And here's the key part.

18
00:02:28,240 --> 00:02:29,240
Don't click anything.

19
00:02:29,240 --> 00:02:31,060
We're never going to log in.

20
00:02:31,060 --> 00:02:34,280
That's what CC Switch is for.

21
00:02:34,280 --> 00:02:35,280
Codex is installed.

22
00:02:35,280 --> 00:02:37,240
Now for the fun part, CC Switch.

23
00:02:38,020 --> 00:02:42,320
CC Switch is a free, open-source app that can point codecs at third-party providers.

24
00:02:43,120 --> 00:02:44,980
We'll use it to connect to AI HubMix,

25
00:02:45,340 --> 00:02:49,900
one gateway that carries basically every AI model behind a single API key.

26
00:02:50,680 --> 00:02:55,480
Today's example model, DeepSeq V4 Flash, the 0731 release.

27
00:02:57,080 --> 00:02:59,920
Head to the CC Switch site and hit Download Free.

28
00:02:59,920 --> 00:03:06,200
It takes us to the downloads page.

29
00:03:08,280 --> 00:03:09,700
Pick your operating system.

30
00:03:10,100 --> 00:03:13,180
We're on Windows 10, so we take the X64 installer.

31
00:03:16,760 --> 00:03:18,980
Chrome flags the file as unverified.

32
00:03:19,380 --> 00:03:21,200
That's just safe browsing being off.

33
00:03:21,640 --> 00:03:21,960
Keep it.

34
00:03:27,400 --> 00:03:28,540
12 megabytes.

35
00:03:28,820 --> 00:03:29,380
Done instantly.

36
00:03:29,380 --> 00:03:36,380
Open it to install.

37
00:03:36,380 --> 00:03:40,380
Setup takes a few seconds, then CC switch is ready.

38
00:03:40,380 --> 00:03:42,380
Open it up.

39
00:03:42,380 --> 00:03:45,380
At the top, switch to the OpenAI section.

40
00:03:45,380 --> 00:03:47,380
That's the one codex reads.

41
00:03:47,380 --> 00:03:51,380
Then hit the plus to add a provider.

42
00:03:51,380 --> 00:03:54,380
From the presets, choose AI HubMix.

43
00:03:54,380 --> 00:03:57,380
Icon and endpoint fill in automatically.

44
00:03:59,380 --> 00:04:09,560
Next we need an API key, so over to the AI HubMix website.

45
00:04:09,560 --> 00:04:16,660
Search for iHubMix and open AIHubMix.com.

46
00:04:16,660 --> 00:04:25,240
One gateway, infinite models, every major LLM behind one unified API.

47
00:04:25,240 --> 00:04:29,360
Click Console.

48
00:04:29,360 --> 00:04:41,340
It asks us to sign in Google account, one click.

49
00:04:41,340 --> 00:04:55,140
Once we're in, open API keys in the sidebar and add a new key.

50
00:04:55,140 --> 00:05:04,860
Name it DeepSeq V4 Flash 0731 so we know what it's for.

51
00:05:04,860 --> 00:05:08,820
Notice the options here, quota and an expiry time.

52
00:05:08,820 --> 00:05:13,620
We'll give this key an expiration date, one day.

53
00:05:13,620 --> 00:05:15,700
If it ever leaks, it's already dead.

54
00:05:15,700 --> 00:05:17,900
Cheap insurance.

55
00:05:17,900 --> 00:05:23,480
Submit, and there's our key.

56
00:05:23,480 --> 00:05:29,800
it before closing, it's only shown once. Back in CC Switch, paste the key into the AI HubMix provider.

57
00:05:31,080 --> 00:05:35,960
Bonus feature, endpoint speed testing. Both endpoints answer fast, either one will do.

58
00:05:39,000 --> 00:05:45,640
Now the default model. Click the download icon and CC Switch pulls the full AI HubMix model list,

59
00:05:45,640 --> 00:05:47,640
everything they carry.

60
00:05:49,640 --> 00:05:55,640
Filter for DeepSeq and select DeepSeq V4 Flash 0731.

61
00:05:57,640 --> 00:05:59,640
Keep the upstream format on responses.

62
00:05:59,640 --> 00:06:01,640
That's what Codex speaks natively.

63
00:06:02,640 --> 00:06:04,640
Add it saved.

64
00:06:05,640 --> 00:06:06,640
The new provider appears at the bottom.

65
00:06:06,640 --> 00:06:08,640
Click it to enable it.

66
00:06:08,640 --> 00:06:10,640
Now it's the active config for Codex.

67
00:06:10,640 --> 00:06:16,640
Time to restart codecs properly.

68
00:06:16,640 --> 00:06:25,640
Close the window, then quit it from the system tray, bottom right corner.

69
00:06:25,640 --> 00:06:34,640
And launch it again.

70
00:06:34,640 --> 00:06:47,000
While it starts, remember last time, it demanded a chat GPT sign in.

71
00:06:47,000 --> 00:06:49,280
This time, straight to the welcome screen.

72
00:06:49,280 --> 00:06:50,500
No login at all.

73
00:06:50,500 --> 00:06:56,320
CC switch already wired codecs to AI HubMix.

74
00:06:56,320 --> 00:07:04,220
Pick any field, it doesn't matter, and continue.

75
00:07:04,220 --> 00:07:05,640
It offers a demo task.

76
00:07:05,640 --> 00:07:07,640
Skip it.

77
00:07:07,640 --> 00:07:10,220
Confirm.

78
00:07:10,220 --> 00:07:14,980
Go to Chat GPT.

79
00:07:14,980 --> 00:07:15,980
One last pop-up.

80
00:07:15,980 --> 00:07:18,520
Pitching GPT 5.6.

81
00:07:18,520 --> 00:07:20,140
Take Continue with Current Model.

82
00:07:20,140 --> 00:07:22,020
So we stay on our custom setup.

83
00:07:22,020 --> 00:07:23,400
Here's the main screen.

84
00:07:23,400 --> 00:07:24,860
Bottom right of the input box.

85
00:07:24,860 --> 00:07:26,620
The model says Custom.

86
00:07:26,620 --> 00:07:30,460
That's our DeepSeq V4 Flash, riding through AI HubMix.

87
00:07:30,460 --> 00:07:31,820
Time for a real test.

88
00:07:31,820 --> 00:07:44,820
I'll ask for a short introduction of AI HubMix.

89
00:07:44,820 --> 00:07:47,373
Questions in, send it.

90
00:07:48,893 --> 00:07:53,173
The request flows through AI HubMix to DeepSeq and Codex gets to work.

91
00:07:53,173 --> 00:07:57,613
It's an agent, so instead of guessing, it actually runs a shell command to look around

92
00:07:57,613 --> 00:07:58,613
first.

93
00:08:02,373 --> 00:08:05,473
21 seconds of work.

94
00:08:07,753 --> 00:08:08,893
And here's the reply.

95
00:08:10,953 --> 00:08:11,993
It's an honest one.

96
00:08:12,373 --> 00:08:15,533
The model says it doesn't have reliable information about AI HubMix

97
00:08:15,533 --> 00:08:19,293
and asks for a URL or some context instead of making things up.

98
00:08:20,033 --> 00:08:20,633
Fine by us.

99
00:08:21,033 --> 00:08:22,413
Next, we'll hand it the URL.

100
00:08:24,333 --> 00:08:27,313
Picking up right where we left off, the model wanted a URL.

101
00:08:27,753 --> 00:08:28,353
Let's give it one.

102
00:08:28,353 --> 00:08:35,353
The answer, an AI model aggregator, and the URL is AIHubMix.com.

103
00:08:40,213 --> 00:08:41,873
Sent. Now watch it work.

104
00:08:45,373 --> 00:08:50,433
It announces the plan, fetch info from the site, and fires off Curl to download the homepage.

105
00:08:50,433 --> 00:08:57,833
The first attempt hits a Windows quirk.

106
00:08:57,833 --> 00:09:01,793
In PowerShell, curl is just an alias for InvokeWebRequest.

107
00:09:01,793 --> 00:09:09,933
The model catches that and switches to the real curl.exe.

108
00:09:09,933 --> 00:09:20,413
Still blocked, so it retries, this time pretending to be a browser with a Mozilla user agent.

109
00:09:20,413 --> 00:09:22,413
This is what makes agents fun to watch.

110
00:09:22,413 --> 00:09:26,413
It's debugging its own path to the answer.

111
00:09:30,413 --> 00:09:38,413
And remember, this is DeepSeq v4 Flash, a fast, inexpensive model doing genuine multi-step work.

112
00:09:44,413 --> 00:09:49,413
Once the page downloads, it strips the HTML down to readable text.

113
00:09:50,413 --> 00:09:59,473
1 minute, 31 seconds of work.

114
00:10:01,333 --> 00:10:02,553
And here's the payoff.

115
00:10:04,153 --> 00:10:06,853
A real introduction, sourced from the live site.

116
00:10:07,653 --> 00:10:13,513
One API, many models, and open AI-compatible endpoint, routing, developer tools, the works.

117
00:10:14,213 --> 00:10:14,753
Final stop.

118
00:10:15,133 --> 00:10:16,333
Let's see what all of this costs.

119
00:10:16,733 --> 00:10:18,293
Back to the AI HubMix console.

120
00:10:18,853 --> 00:10:20,333
In the sidebar, open logs.

121
00:10:20,413 --> 00:10:24,093
Here is every request itemized.

122
00:10:24,093 --> 00:10:32,593
Each row shows the model, our deep seek, v4, flash, 0731, tokens in and out, cash tokens,

123
00:10:32,593 --> 00:10:36,193
latency around a second and a half, and the exact spend.

124
00:10:36,193 --> 00:10:39,213
Most of these calls cost less than a tenth of a cent.

125
00:10:39,213 --> 00:10:43,913
And that's the full setup, codecs on windows, CC switch in the middle, and one AI Hub Mix

126
00:10:43,913 --> 00:10:46,733
key that unlocks any model you want to try.

127
00:10:46,733 --> 00:10:47,413
Thanks for watching.