How much does Bike4Mind cost?

Bike4Mind Professional is $30/month and includes a transparent credit Balance, metered at provider cost plus a flat 20% and printed in the open. Team is built for small teams and starts at 4 seats: $100/month includes 4 seats sharing one co-mingled Balance pool of 200,000 credits a month, and each additional seat is $25/month. Enterprise is a custom flat license deployed in your own AWS, with bring-your-own model keys at 0% markup. Every new account starts with 10,000 free credits; there is no ongoing free plan.

Does Bike4Mind use credits or dollars?

Bike4Mind meters in credits, with the conversion printed in the open: every credit costs $0.0006 and buys $0.0005 of provider compute — exactly cost plus 20%. Every model and API call draws from one transparent Balance, calls stop when the Balance runs out, so Bike4Mind never bills past what you hold, and bringing your own provider keys drops the markup to 0%.

Is there a free tier or free trial?

Bike4Mind gives every new account 10,000 free credits, granted after email verification, no card required. After that, subscribe or buy a credit pack — there is no ongoing free plan and no trial. Agents and bots are welcome to try (see bike4mind.com/agents); production use just needs a key. Professional access starts at $30/month, and you can run real code with no account on the in-browser Python demo at bike4mind.com/features.

Can I self-host Bike4Mind / does my data leave?

Yes. Bike4Mind deploys in your own AWS account with full source. Your data never leaves your cloud, you hold the encryption keys, and inference can run on AWS Bedrock or self-hosted open-weight models so no third-party model vendor is ever in the data path.

Is Bike4Mind open source?

Bike4Mind is open core: source-available today under the Business Source License 1.1, converting to Apache-2.0 in two years, locked by a published covenant so it cannot be quietly relicensed. You can read it, run it, self-host the whole thing, and build and sell your own products on it — the only thing off-limits is a competing hosted Bike4Mind service.

Can I bring my own API key (BYOK)?

Yes. Bike4Mind supports bring-your-own-key: supply your own model provider API keys and Bike4Mind adds 0% on top of what the provider charges you. Use your keys or Bike4Mind's — heavy users go direct on cost and stay on the platform.

What AI models does Bike4Mind support?

Bike4Mind supports 60+ AI models behind one interface: OpenAI, Anthropic, Google, xAI, Meta and AWS Bedrock, plus any open-weight model you self-host via Ollama. Inside Bike4Mind you swap between them mid-conversation, so no single vendor owns your work.

Is Bike4Mind HIPAA, SOC 2, and GDPR compliant?

Bike4Mind is architected for regulated workloads: deployed in your own AWS (or GovCloud), PHI never leaves your cloud, your KMS keys, full audit logging, and no prompt or response retention. Compliance is operated as a continuous program; request the security package for BAA terms and current SOC 2 status.

Does Bike4Mind have an API and a CLI?

Yes. Bike4Mind ships a REST API with keys you hold, a published command-line tool (npm i -g @bike4mind/cli), and MCP in both directions — Bike4Mind is an MCP host and ships MCP servers. See bike4mind.com/for-developers and bike4mind.com/agents.

Can I import my ChatGPT and Claude history?

Yes. Bike4Mind imports your entire ChatGPT or Claude history — every conversation, every attachment, preserved and searchable inside Bike4Mind. No starting over.

Feature

Manifold

Manifold scope hooks

September 30, 2026

Manifold adds scope hooks, authored as hooks files at the column, board, project or global tier and loaded on both the claude and opencode engines.