Llama 4 Maverick API in India: use Llama 4 Scout

Looking for the Llama 4 Maverick API in India? Llama 4 Maverick is not available on unoblox. It is not in the live model list (/v1/models), and requests for it will not route. Meta's Llama family is still here, through two live models: Llama 4 Scout and Llama 3.3 70B Instruct Turbo. Both are billed in rupees and called through the same OpenAI-compatible endpoint as every other model.

Llama models you can call today

Rates below are as listed on 7 October 2026; the model page always shows the live rate.

Model	Model id	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Llama 4 Scout	meta-llama/llama-4-scout-17b-16e-instruct	₹10.12	₹30.37
Llama 3.3 70B Instruct Turbo	meta-llama/llama-3.3-70b-instruct-turbo	₹10.12	₹32.40

Model	Input types	Context window	Tool calling
Llama 4 Scout	text and image	327,680 tokens	Yes
Llama 3.3 70B Instruct Turbo	text only	131,072 tokens	Yes

Every listed rate already includes unoblox's 5% platform fee, and you are charged exactly the listed rate.

Moving a Maverick integration to Llama 4 Scout

If your code was written for Maverick, the change is the model string. Llama 4 Scout is the other Llama 4 model and accepts both text and images. Llama 3.3 70B is text-only.

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-scout-17b-16e-instruct",
    "messages": [{"role": "user", "content": "Summarise this support ticket in two lines."}]
  }'

Scout and Maverick are different models, so re-run your own evaluation prompts before you switch production traffic. Don't assume the outputs will match.

What a month costs

Take a workload of 10 million input tokens and 2 million output tokens a month:

• Llama 4 Scout: (10 × ₹10.12) + (2 × ₹30.37) = ₹161.94
• Llama 3.3 70B Instruct Turbo: (10 × ₹10.12) + (2 × ₹32.40) = ₹166.00

For a free starting point, two open-weight models are priced at ₹0: Qwen3.8-27B and Gemma 4 26B A4B. Both take text and image input. Fair-use limits apply; see Freemium access.

Billing

Usage is paid from a prepaid rupee wallet. GST at 18% is added when you top up (pay ₹118 and ₹100 of credit lands in your wallet), and one GST tax invoice is issued for each top-up; individual requests carry no separate invoice. There's no separate Meta account and no foreign-currency charge.

Frequently asked questions

Is Llama 4 Maverick available on unoblox? No. It is not in the live catalog. The live Llama models are Llama 4 Scout and Llama 3.3 70B Instruct Turbo.

What does Llama 4 Scout cost? ₹10.12 per 1M input tokens and ₹30.37 per 1M output tokens. See the model page for the live rate.

Does Llama 4 Scout accept images? Yes. The catalog lists text and image input for Scout. Llama 3.3 70B is text-only.

Does Llama run in India on unoblox? No. Both Llama models run at an upstream provider outside India. What's India-specific is rupee billing, a GST invoice for each top-up, and one endpoint.

Do I need a new SDK? No. Any OpenAI-compatible SDK works. Set the base URL to https://api.unoblox.ai/v1 and use your ub-gw- key.

Will Maverick be added? We don't announce models ahead of time. The model list shows what is live right now.

Get started in rupees → https://unoblox.ai/sign-in