Now in beta · India-first LLM gateway
Every model. One API key. No 429s.
Access GPT-4o, Claude, Gemini, and 30+ frontier models through a single API. Pay in INR with UPI. No credit card required.
28+ models from 8 providers
Frontier and budget models, all through a single unified API
OpenAIAnthropicGoogleMistralMetaCohereDeepSeekQwen
| Model | Provider | Context | Input /1M | Output /1M |
|---|---|---|---|---|
GPT-4oFRONTIER | OpenAI | 128K | $2.50 | $10.00 |
GPT-4o mini | OpenAI | 128K | $0.15 | $0.60 |
o1FRONTIER | OpenAI | 200K | $15.00 | $60.00 |
o3-mini | OpenAI | 200K | $1.10 | $4.40 |
Claude Sonnet 4.6FRONTIER | Anthropic | 200K | $3.00 | $15.00 |
Claude Opus 4.6FRONTIER | Anthropic | 200K | $15.00 | $75.00 |
Claude Haiku 4.5 | Anthropic | 200K | $0.80 | $4.00 |
Gemini 2.0 Flash | 1M | $0.10 | $0.40 | |
Gemini 2.0 ProFRONTIER | 1M | $1.25 | $5.00 | |
Mistral LargeFRONTIER | Mistral | 128K | $2.00 | $6.00 |
Codestral | Mistral | 256K | $0.30 | $0.90 |
Llama 3.1 405BFRONTIER | Meta | 128K | $3.00 | $3.00 |
DeepSeek V3 | DeepSeek | 128K | $0.27 | $1.10 |
DeepSeek R1 | DeepSeek | 128K | $0.55 | $2.19 |
India Latency Observatory
Real-time provider health measured from our Mumbai PoP.
OpenAIOperational
Latency p50118ms
30-day uptime99.98%
AnthropicOperational
Latency p50143ms
30-day uptime99.95%
GoogleDegraded
Latency p50382ms
30-day uptime99.12%
MetaOperational
Latency p5092ms
30-day uptime99.99%
Transparent pricing
Provider list price + 5% platform fee + 18% GST. No hidden costs.
Example: GPT-4o input
Provider price$2.50/1M tokens
Platform fee (5%)$0.13
GST (18%)$0.47
Total$3.10/1M tokens
Built for India
🏢
India Pvt Ltd
Product Forge India Pvt Ltd — fully incorporated
🧾
GST invoicing
Compliant GST invoices for every transaction
💳
UPI payments
Pay with UPI, Razorpay, or bank transfer
⚡
Low latency
Optimized routing through Indian endpoints
Start building in minutes
Sign up, add ₹500 to your wallet, and get your API key. Your first call is one curl away.
Get started free