Mistral Small API in India

Mistral Small is Mistral AI's compact open-weight-lineage model, and on unoblox it's available from India through the same ₹-billed, OpenAI-compatible endpoint as every other model in the catalogue — one ub-gw- key, one monthly GST invoice, no international card needed to start calling it.

What Mistral Small brings to the catalogue

Mistral Small gives Indian teams another option in the mid-size, general-purpose bracket alongside models like Llama 4 Scout and Gemma 4 — useful when you want to compare a European-lineage model's behaviour on a task against the American and Chinese-lineage alternatives already in the catalogue. It's a general-purpose instruct model, a reasonable default to test first for chat, summarisation and structured-output tasks before reaching for a larger, pricier model.

₹ pricing for Mistral Small

Mistral Small's live ₹ rate is on its model page rather than fixed in this note. For context, here's where similarly sized open-weight models in the catalogue sit:

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Llama 4 Scout	10.08	30.24
Gemma 4 31B	13.10	38.30

Check the exact current figure for Mistral Small on its model page before sizing a workload against these.

Calling Mistral Small from the unoblox endpoint

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-small-3.2-24b-instruct-2506",
    "messages": [{"role": "user", "content": "Summarise this contract clause in plain English."}]
  }'

Mistral Small vs Llama 4 Scout vs Gemma 4

• Mistral Small — a solid general-purpose default; worth A/B testing against Scout and Gemma 4 on your own prompts rather than assuming any one wins by lineage alone.
• Llama 4 Scout — Meta's comparable-tier model, priced at ₹10.08 / ₹30.24 per 1M tokens.
• Gemma 4 31B — Google's comparable-tier model, priced at ₹13.10 / ₹38.30 per 1M tokens.

Because all three sit behind the same endpoint and key, running the same evaluation prompt across all three costs only the tokens used, with no separate accounts or SDKs to set up.

Frequently asked questions

Is Mistral Small available in India through unoblox? Yes, mistralai/mistral-small-3.2-24b-instruct-2506 is callable on https://api.unoblox.ai/v1 immediately after signup, billed in rupees.

What does Mistral Small cost on unoblox? It isn't in our fixed indicative price list; see the live ₹ rate on its model page.

How does Mistral Small compare to Llama 4 Scout or Gemma 4? All three are similarly sized general-purpose models from different labs; behaviour and quality vary by task, so testing your own prompt across each is the reliable way to choose.

Does Mistral Small run on infrastructure in India? No, it's served the same way as the rest of the catalogue's external models. The India-specific benefit is ₹ billing, a GST invoice and one endpoint, not data residency.

Can I call Mistral Small and a larger model like Qwen3 Max with the same key? Yes, the same ub-gw- key authenticates every model in the catalogue.

Is a GST invoice issued for Mistral Small usage? Yes, combined with all other model usage into one monthly GST invoice from an Indian entity, input tax credit claimable.

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