⚡ नवीन — Kimi K3 आता लाइव: तुमची Moonshot की जोडा →

50 providers. एक gateway.

खाली दिलेल्या प्रत्येक provider सोबत एकच BharatRouter API काम करते — तेच SDKs, तेच INR billing, तेच routing आणि failover. तुमची key आणा (BYOK): तुमची key एकदा सेव्ह करा (encrypted, पुन्हा दिसणार नाही) आणि तो provider जे काही serve करेल ते routable होऊन जाते — आमच्या catalog च्या पलीकडील models देखील, provider/model या स्वरूपात.

तुमच्या keys सेव्ह कराBYOK कसे काम करते

Krutrim Cloud

🇮🇳 India residencybring your own key

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.

तपशील →

Sarvam AI

🇮🇳 India residencybring your own key

India's sovereign-LLM flagship — sarvam-30b and sarvam-105b understand 11 Indian languages and are India-resident, available via BYOK.

तपशील →

OpenAI

globalbring your own key

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

तपशील →

OpenRouter

globalbring your own key

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

तपशील →

Groq

globalbring your own key

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

तपशील →

Mistral AI

globalbring your own key

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

तपशील →

DeepSeek

globalbring your own key

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

तपशील →

Together AI

globalbring your own key

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

तपशील →

Fireworks AI

globalbring your own key

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

तपशील →

Cerebras

globalbring your own key

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

तपशील →

xAI

globalbring your own key

Grok models from xAI.

तपशील →

Moonshot AI

globalbring your own key

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

तपशील →

DeepInfra

globalbring your own key

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

तपशील →

Novita AI

globalbring your own key

Budget GPU cloud with a broad open-model catalog.

तपशील →

SambaNova

globalbring your own key

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

तपशील →

Nebius AI Studio

globalbring your own key

AI Studio serving open models from European datacenters.

तपशील →

Hyperbolic

globalbring your own key

Open-model serving on a decentralized GPU marketplace.

तपशील →

NVIDIA NIM

globalbring your own key

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

तपशील →

Perplexity

globalbring your own key

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

तपशील →

AI21 Labs

globalbring your own key

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

तपशील →

Upstage

globalbring your own key

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

तपशील →

MiniMax

globalbring your own key

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

तपशील →

Alibaba Qwen (Intl)

globalbring your own key

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

तपशील →

Z.ai (Zhipu)

globalbring your own key

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

तपशील →

Featherless

globalbring your own key

Serverless access to thousands of Hugging Face model checkpoints.

तपशील →

kluster.ai

globalbring your own key

Distributed inference cloud for open-weight models.

तपशील →

Lambda

globalbring your own key

Lambda's inference API on their GPU cloud.

तपशील →

Chutes

globalbring your own key

Decentralized serverless AI compute built on Bittensor.

तपशील →

Cohere

globalbring your own key

Command models built for enterprise RAG and tool use.

तपशील →

Google Gemini

globalbring your own key

Google's Gemini family through the AI Studio endpoint.

तपशील →

AI/ML API

globalbring your own key

One API for 300+ models across providers — aggregator access with usage-based pricing.

तपशील →

FriendliAI

globalbring your own key

GPU-efficient serving of open-weight models through fast, low-cost serverless endpoints.

तपशील →

Inception (Mercury)

globalbring your own key

Mercury — diffusion-based LLMs that generate text in parallel for very low latency.

तपशील →

Jina AI

globalbring your own key

Embeddings and rerankers (jina-embeddings, jina-reranker) behind an OpenAI-compatible API.

तपशील →

OVHcloud AI Endpoints

globalbring your own key

European sovereign-cloud inference for popular open-weight models.

तपशील →

Venice AI

globalbring your own key

Privacy-first inference — no prompt logging or retention, open-weight models only.

तपशील →

SiliconFlow

globalbring your own key

A large aggregator of open-weight models — Qwen, DeepSeek, GLM and more — at low prices.

तपशील →

Baseten

globalbring your own key

Production model serving with fast cold-starts via OpenAI-compatible Model APIs.

तपशील →

Nscale

globalbring your own key

Sustainable GPU cloud with serverless inference for open-weight models.

तपशील →

Meta Llama API

globalbring your own key

Meta's official Llama API — the latest Llama models straight from the source.

तपशील →

StepFun

globalbring your own key

The Step family of multimodal and reasoning models from StepFun.

तपशील →

GMI Cloud

globalbring your own key

GPU cloud with serverless inference for open-weight models.

तपशील →

Scaleway

globalbring your own key

European cloud's Generative APIs — open-weight models served from the EU.

तपशील →

DigitalOcean Gradient

globalbring your own key

DigitalOcean's Gradient inference platform for open-weight models.

तपशील →

Volcano Engine (ByteDance)

globalbring your own key

ByteDance's cloud — Doubao and open models via the Ark OpenAI-compatible API.

तपशील →

Baidu ERNIE

globalbring your own key

Baidu's ERNIE models via the Qianfan platform.

तपशील →

Parasail

globalbring your own key

On-demand serverless inference for open-weight models.

तपशील →

W&B Inference

globalbring your own key

Weights & Biases Inference — hosted open models alongside the W&B tooling.

तपशील →

ElevenLabs

globalbring your own key

Voice AI — high-fidelity text-to-speech and speech-to-text, available via BYOK for the audio plane.

तपशील →

GitHub Models

globalbring your own key

GitHub's hosted model catalog (OpenAI, Llama, Mistral and more) reached with a GitHub token.

तपशील →

प्रत्येक provider साठी एक gateway का

भारतीय teams कडे अर्धा डझन AI providers च्या keys असतात — Indic language कामासाठी एक Indian lab, कठीण reasoning साठी एक frontier lab, latency-critical paths साठी एक fast-inference cloud. प्रत्येकाचे स्वतःचे dashboard, billing currency, rate limits आणि failure modes असतात. BharatRouter हे सर्व एका API key, एका INR invoice आणि एका routing policy मध्ये एकत्र आणते: प्रत्येक request ला price,latency किंवा uptime साठी optimize करा, गरज पडल्यास provider pin करा, आणि बाकीचे काम circuit-breaker failover वर सोडून द्या.

Residency हे एक first-class request field आहे, कोणतेही वचन नाही: data_policy: "india_only" routing ला Krutrim Cloud आणि Sarvam AI सारख्या India-resident endpoints पर्यंत मर्यादित करते — म्हणूनच ते या पेजवर सर्वात आघाडीवर आहेत. तुमच्या provider keys AES-256-GCM ने encrypt होतात, फक्त प्रति request in-flight decrypt होतात, आणि एका click मध्ये revoke केल्या जाऊ शकतात. Agents ना तीच सुविधा programmatically मिळते: एक MCP server, एक machine-readable catalog आणि scoped keys ज्या ते स्वतः mint करू शकतात.

वारंवार विचारले जाणारे प्रश्न

BharatRouter वर "bring your own key" (BYOK) चा अर्थ काय आहे?

तुम्ही तुमच्या BharatRouter अकाउंटमध्ये एकदा एखाद्या provider ची API key सेव्ह करता — AES-256-GCM ने एन्क्रिप्टेड, पुन्हा कधीही दिसत नाही — आणि त्या provider कडे जाणाऱ्या प्रत्येक request वर तुमचेच अकाउंट आणि तुमचे negotiated rates लागू होतात. BharatRouter त्यावर routing, failover, एक बिल-व्ह्यू आणि team sharing देते. Beta दरम्यान BYOK requests मोफत आहेत.

मला प्रत्येक provider साठी माझी key लागते का?

होय — BharatRouter तुमच्या स्वतःच्या provider keys (BYOK) वर route करते. जो कोणताही provider वापरायचा असेल त्यासाठी एकदा key सेव्ह करा, आणि BharatRouter त्या सर्वांमध्ये routing, failover आणि एक बिल-व्ह्यू सांभाळते. fallback साठी कोणतीही platform key नाही.

BharatRouter catalog मध्ये नसलेले models मी वापरू शकतो का?

होय. जेव्हा तुम्ही एखादी provider key सेव्ह करता, तेव्हा BharatRouter ती key serve करू शकणारे सर्व models discover करते आणि त्यांना provider/model या स्वरूपात routable बनवते — फक्त तुमच्या organisation साठी, public catalog च्या पलीकडे.

कोणते providers भारतातून serve करतात?

Krutrim Cloud आणि Sarvam AI Indian datacenters मधून serve करतात. data_policy: "india_only" पाठवा आणि BharatRouter फक्त India-resident endpoints वरच route करेल — DPDP-aligned, by construction.

Provider key कशी जोडावी?

Sign in करा, Account Settings → Provider keys (BYOK) उघडा, provider निवडा आणि key paste करा. ती provider विरुद्ध live verify होते, rest वर encrypt होते, आणि एका मिनिटात active होते.

Key मिळवाModels पाहा