Esc to close · ⌘K / Ctrl-K opens search anywhere
FROM THE BHARATROUTER TEAM
Notes and how-tos from BharatRouter.
Explore model benchmarks, practical guides, and what we learn along the way.
LATEST FROM THE BLOG
Point Nous Research's Hermes agent at BharatRouter and code with GLM-5.3-Flash, gpt-oss-120b or any catalog model on one br- key — India-resident, metered, budgeted. Exact CLI and GUI setup with a working config (custom OpenAI-compatible provider), streaming + tool-calling, and the no-silent-fallback gotcha.
Read the articleKEEP EXPLORING
A fast, India-resident model with a 1M-token context and verified tool-calling. Where it sits vs the Claude/Codex tiers, the latency we measured from Bengaluru (~0.62s to first token, ~130 tok/s), why prefix caching makes agent loops cheap, and one-line setup for brcode, Codex CLI or any OpenAI-compatible client.
Read the articleRouters claim "~25ms overhead" — measured at their own edge. We measured the whole trip from Bengaluru: same model, same provider, raw vs routed, commands included. ~190ms end-to-end for us (~50–70ms of it gateway compute) — versus ~355ms of pure distance before a US-edge router even starts.
Read the articlePart 2: the same three models inside a real coding agent, priced per task through one neutral gateway. Kimi K3 lost single-turn on cost-per-correct — but wins the agent at ₹10.87/task, because caching is the whole game. Cache-accurate four-component cost; deterministic grading; 16/16 solved.
Read the articleA reproducible quality × cost benchmark of GPT-5.6 Sol, Claude Fable 5 and Kimi K3 through one gateway — accuracy AND ₹-per-correct-answer across 5 axes, deterministic grading, Wilson CIs. Sol wins both; open-weight Kimi beats Fable. And the twist: Kimi has the cheapest tokens but not the cheapest answers.
Read the articleMoonshot's Kimi K3 (2.8T MoE, 1M context, always-on reasoning) in brcode, OpenCode, Claude Code and Codex CLI — one BharatRouter key, your Moonshot key as BYOK. Copy-paste configs, a pricing comparison across providers, and sample code on GitHub.
Read the articleWarp is the terminal a TUI coding agent deserves. Launch configs for agent + shell panes, workflows for brcode commands, and one rule that keeps Warp AI and your agent out of each other's way.
Read the articleOne API for Indic and global models. Start with the quickstart.