Esc to close · ⌘K / Ctrl-K opens search anywhere
🇮🇳 india routechatOpen weightsid: llama-3.1-8b-instruct
| Route | Residency | ₹ in / Mtok | ₹ out / Mtok | Live | p50 / p95 | tokens/s | 7d success |
|---|---|---|---|---|---|---|---|
| BharatRouter | 🇮🇳 india | ₹2 | ₹4 | … | — | — | — |
| OpenRouter | global | ₹2 | ₹3 | … | — | — | — |
| Groq | global | ₹5 | ₹8 | … | — | — | — |
| Fireworks AI BYOK | global | ₹19 | ₹19 | … | — | — | — |
Latency, throughput and success rate are measured from real traffic over the trailing 7 days (/v1/models/llama-3.1-8b-instruct/stats) — compare providers, then chain them: the failover playground proves this model keeps answering when its first provider goes down.
curl https://api.bharatrouter.com/v1/chat/completions \
-H "Authorization: Bearer br-..." -H "Content-Type: application/json" \
-d '{"model": "llama-3.1-8b-instruct", "messages": [{"role": "user", "content": "namaste"}], "data_policy": "india_only"}'llama-3.1-8b-instruct is served on BharatRouter through 4 routes with automatic failover — same OpenAI-compatible API, INR billing, and optimize routing (price / latency / quality) as every other model in the catalog.
Open-weight model — licence and weights on Hugging Face ↗
Card maintained by BharatRouter. Languages: en, hi.