Llama 4 API in India

Meta's Llama 4 Scout — the efficient model of the Llama 4 family — is live on unoblox's OpenAI-compatible gateway in India, with predictable ₹-native pricing, a GST invoice, and no international licensing to sort out.

Llama 4 pricing

Model	Input (₹/1M)	Output (₹/1M)	Best for
Scout	₹10.12	₹30.36	Cost-first, high-volume

Rates as of 6 October 2026; the live price is on the model page. Llama 4 Maverick is not currently offered on unoblox.

Open weights mean there's no licensing fee layered on top — you pay only for inference.

Why Llama 4 now

Meta's latest generation closed a lot of the gap with proprietary models on reasoning, coding, and multilingual tasks. At these rates, Llama becomes a strong default for:

• Cost-sensitive agents — multi-turn workflows that need to stay profitable at scale.
• Batch processing — Scout is well-suited to high-volume summarization, classification, and tagging.
• RAG and search — Scout's long context window (327,680 tokens on unoblox) suits retrieval-heavy pipelines.
• Hindi and Indian languages — noticeably better multilingual coverage than earlier Llama generations.

Quick start

Base URL: https://api.unoblox.ai/v1
Model: meta-llama/llama-4-scout-17b-16e-instruct
API Key: ub-gw-[your-key]

Test on Scout first; if you need more quality, compare a stronger model such as DeepSeek V3.2 on the same key.

Llama for Indian teams

Open-source, no lock-in — you can always run Llama yourself on any cloud; unoblox just removes the DevOps overhead of the API path.

Competitive pricing — Scout's ₹10.12 per million input tokens is one of the more economical rates on the catalog.

GST-compliant invoicing — a GST tax invoice issued at each top-up, input-tax credit claimable.

Frequently asked questions

Can I fine-tune Llama through unoblox? Not through the API today. For custom LoRA adapters, reach out to support to discuss options.

Does Scout run locally too? Yes — Llama's weights are open, so you can download and self-host Scout if you outgrow the managed API.

Which Llama should I choose? Llama 4 Scout is the Llama 4 model on unoblox. Llama 3.3 70B Instruct Turbo is also available at the same input price (₹10.12 per 1M tokens) if you want a text-only alternative.

Is Llama good at coding? Scout is fine for simpler code tasks. It is not the top choice for the hardest coding problems, but it is competitive for the price.

What's the practical context limit? Check the model card on /models for the current maximum — it's generous enough for most document and chat use cases.

Can I use Llama for production chatbots? Yes — Scout is responsive enough for real-time chat and suits high-volume, simple interactions.

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