YouTube2Text

Get 7.4 Billion Free Tokens for Claude Code (Full Setup) — Transcript

by Verma Tech icon · 1,971 words · 267 segments · language en · Watch on YouTube

Full transcript

  1. 0:00So guys, today we're going to see how
  2. 0:02to get 7.4 billion AI tokens per month
  3. 0:05for free. In this, we will connect a
  4. 0:08total of 34 free providers. 635 free
  5. 0:11model endpoints and 474 model families.
  6. 0:16This will also include chat, embedding,
  7. 0:18and video models. So in this video, we
  8. 0:20will look at how we can configure this.
  9. 0:22We will use smart fallback routing for
  10. 0:25all models, meaning we will switch
  11. 0:27models automatically. We will handle
  12. 0:30rate limiting automatically, and most
  13. 0:32importantly, we can connect it to any
  14. 0:34coding agent like Claude Code. So in
  15. 0:37this video, we will integrate it with
  16. 0:38Claude Code and see how it works. So
  17. 0:40without wasting any time, let's start
  18. 0:42the video. So for that, you need to go
  19. 0:44to your favorite browser and search for
  20. 0:47free-llm-api.com, okay. So in this, we
  21. 0:50can see that the providers have
  22. 0:52increased; it now has 969 models and 62
  23. 0:54providers, which have updated to be
  24. 0:57much higher. They were fewer before,
  25. 1:00and we will get 7.4 billion free tokens
  26. 1:02per month in this. And frontier models
  27. 1:05that we will get for free. Out of which
  28. 1:08, these frontier models are right in
  29. 1:09front of you. In this, Gemini 1.5 Flash
  30. 1:13, GLM 4, Qwen 2.5, DeepSeek V3, and
  31. 1:17Minimax are all models you can see here
  32. 1:21. Quite excellent frontier models are
  33. 1:23available for you to use for free in
  34. 1:25this. Of course, there is a limit, but
  35. 1:28the smart fallback routing will ensure
  36. 1:31we don't feel that limit at all. From
  37. 1:34here, we need to click on the GitHub
  38. 1:36option. As soon as you click on the Git
  39. 1:38option, a Git repository will open in
  40. 1:40front of you. And here you can see that
  41. 1:43it already has 36,000 stars. And this
  42. 1:47is an open-source project that provides
  43. 1:49us with a service where we can connect
  44. 1:52all endpoints together and use free
  45. 1:55LLMs. Here we can see the supported
  46. 1:57providers. Like Google, Groq,
  47. 2:00OpenRouter—many excellent providers
  48. 2:02are available to see in this. So, to
  49. 2:05set this up, we need to click on Quick
  50. 2:07Start here. This is the URL you get.
  51. 2:11For this, you will require Docker. If
  52. 2:13Docker is installed on your system, you
  53. 2:15can install it directly with this
  54. 2:17command. But I will tell you the
  55. 2:19simplest way to use it. If you are on
  56. 2:22Windows, you can click here to download
  57. 2:25the exe file. But I am currently using
  58. 2:27a Mac. So I will click here for Mac OS.
  59. 2:32And as soon as you scroll, after
  60. 2:34scrolling, you will see the DMG file
  61. 2:37here. If you are also using a Mac, you
  62. 2:39can download this DMG file. Otherwise,
  63. 2:42you can also see EXE files here. If you
  64. 2:45are a Windows user, download the EXE
  65. 2:47file. It's a very simple process. You
  66. 2:49can install it easily. So if you are
  67. 2:51using an M-series, meaning an M-series
  68. 2:53MacBook. Then you can use the ARM 64
  69. 2:56version. So I am currently using an M5.
  70. 2:59So for the M5, I will download the ARM
  71. 3:0164. So I'll wait for it to finish
  72. 3:03downloading. After downloading, you
  73. 3:07need to open it and drag it into the
  74. 3:09Applications folder. And as soon as you
  75. 3:12hear this sound, your software will be
  76. 3:14successfully installed on your system.
  77. 3:16Now I will open the Free LLM API here.
  78. 3:25There are three steps to get started
  79. 3:25with this. Add provider keys, send a
  80. 3:28test request, and connect your app. So
  81. 3:30in this, what we need to do is add API
  82. 3:32keys from multiple providers. We get a
  83. 3:35playground option in this. From where
  84. 3:37we will test the request to see if it
  85. 3:39is working or not. Then we can directly
  86. 3:41connect any app, like any of our coding
  87. 3:44agents, with it. In today's video, I
  88. 3:46will show you how to connect and use it
  89. 3:48with Cloud Code. So here you can see
  90. 3:51that in models, we will get chat,
  91. 3:53embedding, image, video, audio, search,
  92. 3:55and fused models. And here we get the
  93. 3:57playground option, which is currently
  94. 3:59empty. We will add to it. So here we
  95. 4:02can chat using the keys that we are
  96. 4:04going to create. In this, we get to see
  97. 4:07agents that we might want to use it
  98. 4:10with. Like, we will use it with Cloud
  99. 4:12Code. In this, we can connect and use
  100. 4:15it with Codeium, Cline, Continue,
  101. 4:17OpenCode, and multiple other agents. We
  102. 4:20can also use it with Cursor. In
  103. 4:22analytics, we get an entire tab for
  104. 4:25this. Where we will get analytics for
  105. 4:27usage, requests, input-output tokens,
  106. 4:30how much we are using, and how much is
  107. 4:32being spent, all of that we will see
  108. 4:34here. Alright? And in the premium
  109. 4:36section, we will get the options to buy
  110. 4:38their plans and such. All right? So now
  111. 4:40let's go to models and I'll click on
  112. 4:42add key. I'm clicking on add key.
  113. 4:45Select provider, here you can select
  114. 4:47any provider you want. I will select
  115. 4:49Google AI Studio first here. And here I
  116. 4:52search for Google AI Studio. I will
  117. 4:56open Google AI Studio here. From here,
  118. 4:59I click on API key. Get API key,
  119. 5:02continue, create API key. From here, I
  120. 5:07click on create key. The key has been
  121. 5:08created successfully. I copy the key
  122. 5:10from here and go back into it. I paste
  123. 5:13the key here. The label is optional.
  124. 5:17You can provide it here if you want.
  125. 5:18Otherwise, you don't have to. I will
  126. 5:20write Google here. I click on add key.
  127. 5:24Here you can see that 15 models are
  128. 5:27selected for us. We will get this many
  129. 5:30models inside this. Like 3.5 Flash, 3.6
  130. 5:33, 3.7, 3, and even 3.8 will be
  131. 5:35available in this. So after this, we
  132. 5:38have to click on save. After clicking
  133. 5:41on save here, we have to click on check
  134. 5:43now here. After clicking on check now,
  135. 5:45it has become healthy here. Earlier,
  136. 5:47there was an issue here. All right? We
  137. 5:48have successfully added the first one.
  138. 5:51Now, I can go to the playground, sorry,
  139. 5:54to the models, and show you that we
  140. 5:56have received 96 million tokens for now
  141. 5:59. 96 million tokens, and we can use
  142. 6:04these. Now I click on open playground
  143. 6:07and give it a prompt by clicking here.
  144. 6:10It is selected to auto. This will
  145. 6:12automatically generate a response for
  146. 6:14us on auto. It can choose any model. It
  147. 6:16has used 3.5 Flash. And it has
  148. 6:19generated a response for us in this
  149. 6:22many milliseconds. Now I go back into
  150. 6:25models. I go into keys. And I click on
  151. 6:28add key again here to select the
  152. 6:29provider. There are multiple providers
  153. 6:32here. You must be able to see them here
  154. 6:33. Select any provider you want and keep
  155. 6:35adding them into it. All right? I am
  156. 6:37adding Open Router to it now. So now I
  157. 6:40will create an API key for Open Router.
  158. 6:44I come to the Open Router website. And
  159. 6:46obviously, I will have to sign up here.
  160. 6:49Okay. So, I have successfully created
  161. 6:51the account. And I click on API keys.
  162. 6:54Okay. So, here I click on the new
  163. 6:55button. I define a name for it. And the
  164. 6:58expiration will be one hour
  165. 7:01automatically. And No limit, and I
  166. 7:06click on create. Our key has been
  167. 7:09created here. I copy it from here. And
  168. 7:12I paste this key here. And here I write
  169. 7:19OpenRouter. And you can see guys, we
  170. 7:22have received so many models in this.
  171. 7:25So, I will save it from here. After
  172. 7:27saving, I will check it again from here
  173. 7:29. And its status has become healthy
  174. 7:32again. In this same way, you can select
  175. 7:34multiple models inside it. And here,
  176. 7:36you have obtained 102 million tokens.
  177. 7:39So, in this way, you connect multiple
  178. 7:42models. Like, you can connect your
  179. 7:43providers from here. Add all the models
  180. 7:46from all the multiple providers you see
  181. 7:48here. Like, there is Grok. There are
  182. 7:50quite a few in this. You should try
  183. 7:52them all once. Add as many as you can
  184. 7:54inside this. I am not connecting all
  185. 7:56the providers. But to show you how to
  186. 7:59use it, I have connected two providers
  187. 8:01to try it out. And we need to use this
  188. 8:04in Continue Code. Click on Agents. Here
  189. 8:08we will find the Continue Code option.
  190. 8:10We are seeing an automatic setup inside
  191. 8:13this. This one. Okay? So, I copy this.
  192. 8:16Uh. I will paste this command inside
  193. 8:18the terminal. And I press enter. I
  194. 8:20press Y here. I press enter. So, it is
  195. 8:23asking for the unified API key. So, we
  196. 8:26need to click on show API key and copy
  197. 8:30the unified API key. And I paste it
  198. 8:34here and hit enter. Continue settings
  199. 8:38dot json, I press enter. And you can
  200. 8:41see here that my API key, base URL, and
  201. 8:44everything has been selected
  202. 8:45automatically. So, before this, you
  203. 8:48must have Continue Code installed on
  204. 8:51your system. Only then will it work.
  205. 8:53Okay? So now, I will open Anti-Gravity.
  206. 8:57I will close this for a moment. And so,
  207. 8:59I open the terminal here. And I will
  208. 9:02write Claude. After writing Claude, yes
  209. 9:05I trust this folder. And here you can
  210. 9:07see that the API is on auto-use billing
  211. 9:10. I will click on slash status here. So
  212. 9:14here you can see all the information is
  213. 9:17visible to you. Okay? So by clicking on
  214. 9:20its button, I will send a 'Hi' message
  215. 9:22to it here. So let's see what kind of
  216. 9:24response we get. Since you have given
  217. 9:26the prompt for the first time, it might
  218. 9:28take a little longer. And also, after
  219. 9:31clicking on Playground, as soon as you
  220. 9:33give it a prompt, I'll type 'Hi, how
  221. 9:35are you' again. As soon as you provide
  222. 9:39the prompt, you will be able to see all
  223. 9:42its requests in the Analytics section.
  224. 9:45I have made 11 requests so far. And
  225. 9:47these are the input tokens. And look,
  226. 9:50we can check the usage and everything
  227. 9:53here. And in the Playground, you get to
  228. 9:56see many other settings as well. So
  229. 9:59okay. So here we got the response after
  230. 10:02a minute because it took quite some
  231. 10:04time. If you use it for the first time,
  232. 10:06it might take some time. So let's ask
  233. 10:10this question, "Which model are you
  234. 10:12using?" It says auto-select; the model
  235. 10:16here is on auto-select, and as you can
  236. 10:19see, I would recommend you to use auto.
  237. 10:24You have Haiku, Auto, and if you need
  238. 10:27to do high-level thinking work, you can
  239. 10:31use Opus. You can use Sonnet when you
  240. 10:34need to do normal tasks. And if you
  241. 10:36have very easy, simple tasks to be done
  242. 10:39, you can use Haiku. So basically, you
  243. 10:42can use it this way. It was a very
  244. 10:45simple process. And obviously, you will
  245. 10:48get limits within this. And the more
  246. 10:51providers you use, the more you can add
  247. 10:53multiple providers to this, which will
  248. 10:55give you access to multiple models. So
  249. 10:57as soon as we come to the website, we
  250. 11:00come to keys here. So here we get to
  251. 11:04see "Add Key" for providers. So there
  252. 11:07are many providers in this. So you can
  253. 11:10use any of them. Add it. In the
  254. 11:12Playground, you have it selected on
  255. 11:14auto. Here, you can also use your
  256. 11:15models according to your preferences.
  257. 11:17Whichever model you want to choose, you
  258. 11:19can select it and use it. You will also
  259. 11:22find many other settings and things
  260. 11:24here. So, this is what you will get to
  261. 11:27see inside. And if you are new to the
  262. 11:29channel, make sure to subscribe. And do
  263. 11:31check out the channel once. I have made
  264. 11:33a lot of videos for you on YouTube.
  265. 11:35Some really great ones. So do check
  266. 11:36them out. And see you in the next video
  267. 11:38. Until then, bye bye.

About this transcript

This page contains the full transcript of Get 7.4 Billion Free Tokens for Claude Code (Full Setup) by Verma Tech icon, generated from the public captions YouTube serves with the video. The transcript has 1,971 words across 267 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.

What you can do with it

Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to translate the transcript into 100+ languages.

Free YouTube transcript tool

YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, translation to 100+ languages, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.