GitHub Models for WhatsApp business
GPT, Claude, Llama, Phi via GitHub — free for verified students & OSS.
- Free tier ✓
- Cost: Free–$10/mo
- Speed: Moderate
- Best for: GitHub developers + students
It's a WhatsApp bot powered by AI models accessed through GitHub Models / Copilot. With ChatMitra you bring your GitHub Personal Access Token — setup takes about 5 minutes.
What it looks like in real businesses
Four chats from real industries, all using GitHub Models (openai/gpt-5-mini) inside ChatMitra. Mix of English, Hindi, and Hinglish — the way customers actually type.
Picked by ChatMitra customers who are developers running side projects — Copilot Pro doubles as their bot's AI key.
In simple terms: this is the safest middle-ground for developers who already use GitHub. Free Copilot tier (2,000 completions + 50 chats / month) covers low-volume; $10/month Pro is great for solo devs; $39/month Pro+ unlocks everything.
Not 100% sure GitHub Models is right for you?
That's okay — you can switch any time inside ChatMitra. Quick orientation:
- • If cost is your main concern, Groq or DeepSeek are worth a look
- • If top-shelf quality matters more, OpenAI or Anthropic are the usual picks
- • If you want balance, Gemini sits well in the middle
Still unsure? Start with GitHub Models — switching later is one click inside ChatMitra without rebuilding your bot.
What is GitHub Models, really?
Honestly, this is the safest middle-ground for developers who already live in GitHub. Models are accessed through your existing GitHub account — no separate signup, no separate billing.
GitHub Models is Microsoft / GitHub's AI gateway, launched in 2024 as part of Copilot. They offer GPT-4o, GPT-4.1, GPT-5 mini, Claude variants, Gemini, and Llama models. All Copilot plans transition to usage-based 'AI Credits' on June 1, 2026.
GitHub Models models in 2026
The model with the green badge is what we usually recommend for everyday WhatsApp business chats. Step up only if you actually need it.
Pricing in USD as published on GitHub Models's pricing page. INR figures are approximate. Verified on 2026-04-30.
Source: official model docs · official pricing page
What will GitHub Models cost my business?
Three rough volumes, costs in approximate INR. Your actual number will vary — see assumptions below.
- • Avg 15–20 messages per conversation
- • Avg 50–100 tokens per message
- • Pricing as published by GitHub Models on 2026-04-30 — may change. Source: github.com/features/copilot/plans
Best for these businesses
Pick GitHub Models when you already use GitHub for your code and want one less account / billing relationship.
- Solo developers / freelancers already on Copilot Pro
- Verified students, teachers, OSS maintainers (free)
- Small dev shops bundling multiple AI features into one Copilot subscription
- Non-developer business owners — Copilot Pro pays mostly for IDE features you won't use
- Heavy production traffic — usage-based pricing kicks in fast
GitHub Models is great if you're already on GitHub. As a standalone WhatsApp chatbot AI choice, you're paying for IDE features you don't need — go direct to OpenAI / Gemini instead.
How to get your GitHub Models API key
Whole flow takes about 5 minutes. Mockups below are deliberately generic — GitHub Models's dashboard may look slightly different by the time you read this, but the steps stay roughly the same.
2. (Optional) Subscribe to Copilot Pro
If you don't have Pro yet, subscribe at github.com/settings/copilot. Free tier exists but is limited (50 chats / month).
github.com/settings/copilot3. Generate a Personal Access Token
Go to github.com/settings/tokens and click 'Generate new token (classic)'. Give it the 'models:read' scope.
github.com/settings/tokens4. Copy the token
Token starts with 'ghp_'. Copy it now — GitHub won't show it again.
5. Paste it into ChatMitra
In ChatMitra's AI Chatbot wizard (Step 2), pick GitHub Models, paste your ghp_... token. Validation happens on the spot.
UI may change slightly as GitHub Models updates their dashboard. The flow stays roughly the same — sign up, add a payment method (if needed), find the API keys section, create a key, copy it.
Set up GitHub Models in ChatMitra (about 5 minutes)
Once you've copied your API key from GitHub Models, the rest happens inside ChatMitra. Same wizard you'd use for any other provider — just pre-filled for GitHub Models.
Pick GitHub Models as your AI
In the ChatMitra AI Chatbot wizard, Step 2 shows the provider grid. Click GitHub Models's tile, paste the API key you just copied. ChatMitra checks the key right then — green tick = ready.
Pick a model
ChatMitra auto-selects openai/gpt-5-mini as the default — that's our pick for everyday WhatsApp business chat. You can override if you want a different one.
Write the bot's personality
Tell ChatMitra about your business — name, industry, a one-line description. Then write the personality prompt yourself, or click Generate with AI and tweak the draft. GitHub Models reads this prompt before every reply.
Add a fallback (optional, recommended)
Add up to 3 backup providers. If GitHub Models rate-limits or has an outage, ChatMitra automatically switches to the backup — your customers don't see an error. Most teams add one of Openrouter or Openai here.
Test, then activate
Built-in chat simulator lets you message your bot before any real customer does. Try a tricky question. When it looks right, hit Activate — and the bot starts answering on the WhatsApp number you've already connected to ChatMitra.
Worried about getting locked in? You can change AI providers any time inside ChatMitra. The bot's personality, conversation history, and customer data stay exactly where they are — only the underlying AI changes. Try GitHub Models first, switch later if something better fits.
GitHub Models for Indian SMBs — pros & cons
What's good
- Free tier for everyone (50 chats / month) and totally free for verified students / teachers / OSS maintainers
- $10/month Pro is excellent value if you're already using Copilot for coding
- One account / billing relationship for IDE + chatbot AI
What to watch out for
- Usage-based AI Credits start June 1, 2026 — pricing model changes
- If you don't already use Copilot, $10/month is mostly for features you won't use as a non-developer
- Smaller model catalog than OpenRouter
Compare with other providers
Which is better — GitHub Models or OpenRouter? It depends what you need.
- GitHub developers + students → pick GitHub Models
- Multi-provider gateway → pick OpenRouter
- All-rounder + free tier → pick Google Gemini
Each label is what the provider does best. Match it to your priority — that's usually the right pick.
Top picks by category:
- OpenAI — best for accuracy and complex replies
- Groq — best for cost and high-volume chat
- Google Gemini — best balanced choice for most Indian SMBs
- GitHub Models — gpt, claude, llama, phi via github — free for verified students & oss
Direct comparisons:
Or explore other ChatMitra options:
Sources & references
Every model name, context window, and price on this page is copied from GitHub Models's own public pages on 2026-04-30. Providers update pricing fairly often — please double-check before you commit to a plan.
- Models & specs: docs.github.com/en/github-models
- Pricing: github.com/features/copilot/plans
- Get your API key: github.com/settings/tokens
Try GitHub Models on your WhatsApp in 5 minutes
15 days free. No card. Switch providers any time without rebuilding your bot.
Frequently Asked Questions
Is GitHub Models free?
There's a Free tier (50 chats / month + 2,000 completions). Pro is $10/month, Pro+ is $39/month. Verified students, teachers, and OSS maintainers get Pro free via GitHub Education.
Should I use GitHub Models for my WhatsApp chatbot?
Only if you already pay for Copilot for coding. Otherwise you're paying $10/month mostly for IDE features. Go direct to OpenAI ($5 free credit, then pay-per-token) instead.
What changes on June 1, 2026?
All Copilot plans transition to usage-based 'AI Credits'. Code completions stay unlimited; everything else (chat, agents, AI calls) consumes credits. Watch for billing changes.
Can I use GitHub Models in production for WhatsApp?
Yes — Pro and Pro+ plans support production use within their AI Credits allotment. Free tier (50 chats / month) is for testing only.
Which model should I pick on GitHub Models?
GPT-5 Mini or Llama 3.3 70B for everyday chat. GPT-4o for higher-quality replies. Claude 3.5 Sonnet if you specifically want Claude behaviour.