Llama 3.3 70B Instruct API in India

Llama 3.3 70B Instruct is Meta's widely used 70 billion parameter chat model, available on unoblox as meta-llama/llama-3.3-70b-instruct-turbo. It supports tool calling and Hindi among other languages, and bills in rupees with GST.

What Llama 3.3 70B Instruct Turbo is

Meta's Llama 3.3 70B is an instruction-tuned, text-in, text-out model with a 128k-token context window and grouped-query attention, trained on over 15 trillion tokens, with a knowledge cutoff of December 2023. Meta supports English plus French, German, Hindi, Italian, Portuguese, Spanish and Thai. unoblox lists a context length of 131,072 tokens and tool calling.

It has no reasoning mode and no image input, which keeps it predictable and cheap for plain chat and text tasks.

Where it fits

• Hindi and multilingual chat assistants.
• Text classification, summarisation and rewriting.
• Tool-calling workflows that do not need deep reasoning.

Choose it as a dependable mid-sized text model. For newer capabilities, such as image input or reasoning, look at the Llama 4 or Qwen models in the catalogue.

₹ pricing for Llama 3.3 70B Instruct Turbo

On unoblox, Llama 3.3 70B Instruct Turbo costs ₹9.63 per million input tokens and ₹30.81 per million output tokens. That displayed price is what you are billed per token; nothing is added on top. The model's context length on unoblox is 131,072 tokens.

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Llama 3.3 70B Instruct Turbo	₹9.63	₹30.81
Llama 4 Scout	₹9.63	₹28.88
Qwen3.6 35B A3B	₹9.63	₹91.47
Mistral Small 3.2 24B	₹7.22	₹19.26

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹315.84 on Llama 3.3 70B Instruct Turbo (₹192.60 for input plus ₹123.24 for output). Live rates are always on the model page, and each request is rounded up to the nearest paisa.

Calling Llama 3.3 70B Instruct Turbo from the unoblox endpoint

unoblox is OpenAI-compatible, so any OpenAI SDK works by changing the base URL and key.

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_UNOBLOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.3-70b-instruct-turbo",
    "messages": [{"role": "user", "content": "Summarise this support ticket in two lines."}],
    "max_tokens": 512
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_UNOBLOX_API_KEY",
    base_url="https://api.unoblox.ai/v1",
)
resp = client.chat.completions.create(
    model="meta-llama/llama-3.3-70b-instruct-turbo",
    messages=[{"role": "user", "content": "Summarise this support ticket in two lines."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)

Get a key at https://unoblox.ai/sign-in and top up your wallet in rupees.

Notes on parameters, billing and data

Use max_tokens for output limits. The model's knowledge stops at December 2023, so give it fresh facts in the prompt. It runs at an external provider and not in India, so no data-residency claim is made. unoblox provides rupee pricing, GST invoicing and one endpoint.

Frequently asked questions

Is Llama 3.3 70B available in India? Yes, as meta-llama/llama-3.3-70b-instruct-turbo on https://api.unoblox.ai/v1.

Does it support Hindi? Meta lists Hindi among its supported languages.

What context length is listed? 131,072 tokens.

Does it support tool calling? Yes.

Does it accept images? No, text only.

What is its knowledge cutoff? December 2023, per Meta's model card.

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