FAQ
Questions, answered directly.
Straight answers about what Bahulam is, how pricing and BYOK work, and how to verify our benchmark claims yourself.
FAQ · Product
Product questions
Bahulam is a reliability-first AI platform combining public Chat, the Bahulam Code coding agent CLI, and purpose-built Workspaces on one shared credit pool. It supports 40+ models via BYOK or OpenRouter, is self-hostable, and publishes its benchmark results so every claim is independently reproducible.
Bahulam Code is Bahulam's coding agent CLI. It reads your codebase, plans changes, edits files, and verifies its own work by running tests — self-correcting on failure instead of stopping at the first error. Install with `npm i -g @bahulam/code`.
A workspace is a place to ship real things — Twitter marketing, 3D design, BI reporting — composed of coding, tooling, workflows, and chat. It's purpose-built for a specific job, not a general-purpose run.
Yes. Workflows are predefined multi-step processes for the repetitive parts of a job — they can run standalone or as steps inside a Workspace session, alongside coding, tooling, and chat.
FAQ · Technical
Technical questions
Yes. Every paid plan supports BYOK — bring your own provider key and route requests directly, at 0 platform credits. Pick the model that fits your budget and quality bar, and switch mid-session if you change your mind.
Yes. There's no vendor lock-in — deploy the Bahulam Code runtime on your own infrastructure, keep your data in your VPC, and pin the CLI version. Use the hosted platform instead when convenience matters more than isolation.
Just Bahulam Code (the coding agent runtime) today. Deploy it on your own infrastructure and keep your data in your VPC. Chat and Workspaces are currently hosted platform surfaces.
Bahulam Code routes to 40+ models via direct providers or OpenRouter, including Anthropic, OpenAI, DeepSeek, GLM, Tencent, and Google. Sub-agents can each use a different model — a fast model to scan, a reasoning model to plan, a coding model to write.
Bahulam Code splits a run across sub-agents by role: Explorer reads your codebase, Planner designs the change, Coder writes it. Each uses the model that fits its role, and you compose the team — Bahulam Code handles the routing between them.
Yes. Every reported score — 58.7% on SWE-bench Lite, 67.8% on SWE-bench Verified — runs through a Docker-eval harness, and the full artifacts (predictions, evaluator reports, costs) are public at github.com/BahulamAI/bahulam-benchmarks. The full methodology, including what counts as "resolved," is published at /benchmarks/methodology.
FAQ · Pricing
Pricing questions
Bahulam Code is free to install. Usage is billed through Bahulam's shared credit pool (the Free plan includes a 250-credit pool to validate the platform) or via bring-your-own-key (BYOK), which costs 0 platform credits.
One account, one credit pool. Chat, Bahulam Code, and Workspaces share the same credits and BYOK configuration — what you set up once works everywhere. Plans range from Free (validate) through Pro, Studio, and Max, up to custom Enterprise terms.
Included monthly credits reset each billing cycle. Purchased top-up credit packs roll over and do not expire. BYOK calls are recorded but charged 0 credits.
Still have a question?
Reach the support team directly — billing, accounts, technical issues, all of it.