Grok API in India: not on unoblox, alternatives

xAI's Grok models are not available on unoblox. They are not in the live model list (/v1/models), and a request for a Grok model id will not route. This page lists what unoblox does offer, in case one of those models fits your workload.

What unoblox offers instead

unoblox is an OpenAI-compatible gateway with 65 models in its live model list, all billed in rupees. Some general-purpose options, at live rates per 1M tokens:

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

Model	Model id	Input (₹ / 1M)	Output (₹ / 1M)	Context window
GPT 5	openai/gpt-5	₹126.58	₹1,012.69	400,000
Claude Sonnet 5	anthropic/claude-sonnet-5	₹202.53	₹1,012.69	1,000,000
Kimi K3	moonshotai/kimi-k3	₹288.61	₹1,443.08	1,048,576
DeepSeek V4 Flash	deepseek-ai/deepseek-v4-flash	₹9.11	₹18.22	1,048,576
Qwen3.8-27B	qwen/qwen3.8-27b	₹0	₹0	262,144

Every listed rate already includes unoblox's 5% platform fee, and you are charged exactly the listed rate. Qwen3.8-27B is free, with a fair-use limit of 10 requests per minute per workspace (see Freemium access).

Calling a model

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-5","messages":[{"role":"user","content":"Summarise these release notes."}]}'

Any OpenAI-compatible SDK works. Set the base URL to https://api.unoblox.ai/v1 and use your ub-gw- key.

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. You don't need an international card.

Frequently asked questions

Can I call Grok through unoblox? No. Grok is not in the catalog. The model list shows everything that's live.

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

Do the models above run in India? Qwen3.8-27B runs on unoblox's own GPUs in India. The other models in the table run at upstream providers outside India. For those, what's India-specific is rupee billing, a GST invoice for each top-up, and one endpoint.

How do I compare costs? Every model page shows the live input and output rate per 1M tokens. Your dashboard shows actual spend per model.

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