🎬 New — watch the 2-minute guide videos →

30 providers. One gateway.

Every provider below works through the same BharatRouter API — same SDKs, same INR billing, same routing and failover. 5 of them run on BharatRouter's own platform keys out of the box; for the rest, save your own key once (encrypted, never shown again) and everything that provider serves becomes routable — even models beyond our catalog, as provider/model.

Save your keys How BYOK works

Krutrim Cloud

🇮🇳 India residency platform fallback

Ola's Krutrim Cloud — India's own AI cloud, serving Krutrim models and open weights (gpt-oss, Gemma 4, Qwen) from Indian datacenters. The natural home for india_only routing.

Details →

Sarvam AI

🇮🇳 India residency platform fallback

India's sovereign-LLM flagship — sarvam-30b and sarvam-105b understand 11 Indian languages and are served from India.

Details →

OpenAI

global platform fallback

GPT-5, GPT-5-mini and GPT-4o-mini — the global frontier with BharatRouter routing, INR billing and automatic failover.

Details →

OpenRouter

global platform fallback

A meta-gateway that unlocks hundreds of global models — Claude, Gemini, DeepSeek and more — through one upstream.

Details →

Groq

global platform fallback

LPU inference — some of the fastest tokens in the industry for Llama, Qwen, Kimi K2 and gpt-oss models.

Details →

Mistral AI

global your key only

Europe's frontier lab — Mistral Large and Medium plus the open Mixtral and Ministral families.

Details →

DeepSeek

global your key only

DeepSeek V3 and R1 — frontier-class open-weight chat and reasoning models at disruptive prices.

Details →

Together AI

global your key only

Serverless inference and fine-tuning across 200+ open-weight models.

Details →

Fireworks AI

global your key only

Low-latency serving of open models with strong function-calling and JSON-mode support.

Details →

Cerebras

global your key only

Wafer-scale hardware serving open models at thousands of tokens per second.

Details →

xAI

global your key only

Grok models from xAI.

Details →

Moonshot AI

global your key only

Kimi K2 — the trillion-parameter open-weight MoE family from Moonshot AI.

Details →

DeepInfra

global your key only

Pay-per-token hosting for the most popular open-weight models.

Details →

Novita AI

global your key only

Budget GPU cloud with a broad open-model catalog.

Details →

SambaNova

global your key only

RDU-accelerated inference serving open models at very high throughput.

Details →

Nebius AI Studio

global your key only

AI Studio serving open models from European datacenters.

Details →

Hyperbolic

global your key only

Open-model serving on a decentralized GPU marketplace.

Details →

NVIDIA NIM

global your key only

NVIDIA NIM — optimized inference microservices for open models on NVIDIA infrastructure.

Details →

Perplexity

global your key only

Sonar models with built-in web grounding for answer-style completions.

Details →

AI21 Labs

global your key only

Jamba hybrid SSM-Transformer models with very long context windows.

Details →

Upstage

global your key only

Solar models — compact, capable LLMs with strong document-AI roots.

Details →

MiniMax

global your key only

MiniMax long-context models from one of China's leading labs.

Details →

Alibaba Qwen (Intl)

global your key only

The Qwen family served from Alibaba Cloud's international regions.

Details →

Z.ai (Zhipu)

global your key only

GLM models from Z.ai, including the open GLM-4 line.

Details →

Featherless

global your key only

Serverless access to thousands of Hugging Face model checkpoints.

Details →

kluster.ai

global your key only

Distributed inference cloud for open-weight models.

Details →

Lambda

global your key only

Lambda's inference API on their GPU cloud.

Details →

Chutes

global your key only

Decentralized serverless AI compute built on Bittensor.

Details →

Cohere

global your key only

Command models built for enterprise RAG and tool use.

Details →

Google Gemini

global your key only

Google's Gemini family through the AI Studio endpoint.

Details →

Why one gateway for every provider

Indian teams end up holding keys for half a dozen AI providers — an Indian lab for Indic language work, a frontier lab for hard reasoning, a fast-inference cloud for latency-critical paths. Each comes with its own dashboard, billing currency, rate limits and failure modes. BharatRouter collapses that into one API key, one INR invoice and one routing policy: optimize each request for price, latency or uptime, pin a provider when you must, and let circuit-breaker failover handle the rest.

Residency is a first-class request field, not a promise: data_policy: "india_only" restricts routing to India-resident endpoints like Krutrim Cloud and Sarvam AI — which is why they lead this page. Your provider keys are encrypted with AES-256-GCM, decrypted only in-flight per request, and revocable in one click. Agents get the same surface programmatically: an MCP server, a machine-readable catalog and scoped keys they can mint themselves.

Frequently asked questions

What does "bring your own key" (BYOK) mean on BharatRouter?

You save a provider's API key once in your BharatRouter account — encrypted with AES-256-GCM, never shown again — and every request to that provider rides your own account and your negotiated rates. BharatRouter adds routing, failover, one bill-view and team sharing on top. BYOK requests are free during beta.

Which providers can fall back to BharatRouter's own keys?

Krutrim Cloud, Sarvam AI, OpenAI, OpenRouter, Groq have BharatRouter platform keys: if your key hits a rate limit or fails, requests automatically fall back to ours (disable per provider with the "always use my key" pin). The rest route exclusively through your key.

Can I use models that are not in the BharatRouter catalog?

Yes. When you save a provider key, BharatRouter discovers every model that key can serve and makes them routable as provider/model — for your organisation only, beyond the public catalog.

Which providers serve from India?

Krutrim Cloud and Sarvam AI serve from Indian datacenters. Send data_policy: "india_only" and BharatRouter routes only to India-resident endpoints — DPDP-aligned by construction.

How do I add a provider key?

Sign in, open Account Settings → Provider keys (BYOK), pick the provider and paste the key. It is verified live against the provider, encrypted at rest, and active within a minute.

Get a key Browse models