Rewriting the economics of intelligence

An inference platform for open-weight models.

By signing up, you agree to our Terms of Service and Privacy Policy.

Try Boundless with a prompt

Hand this to Claude Code, Codex, Cursor or any harness.

try-boundless.md

Try the Boundless inference API for me.1. Mint a trial key — no account, no credentials:   POST https://inference.boundless.network/api/agent-key   Send no body. The response carries "key" and "baseUrl".2. Make one chat completion with it:   POST https://api.inference.boundless.network/v1/chat/completions   Authorization: Bearer <key>   {"model": "glm-5.2", "messages": [{"role": "user", "content": "Say hello"}]}3. Report the reply, its token counts, and what the call cost.The key carries $0.01 of credit, expires in 24 hours, limited to 6 requests and 30,000 tokens per minute.Everything else this service publishes: https://inference.boundless.network/llms.txt

Boundless inference, without the console

Boundless is an inference platform for developers building with open-weight language models. The gateway serves a curated model lineup through an OpenAI-compatible API and the Anthropic Messages API, so existing clients and coding agents can connect with familiar request formats. Streaming responses, tool use, and exact input and output token counts are available through the public API.

Access is sold on prepaid credits. Requests stop when the shared Team balance reaches zero, rather than creating an unbounded invoice. Published per-token rates and exact usage make each request cost reproducible. API keys can have their own spend budgets, while Team accounts share credits, usage, and billing across members.

JavaScript is required for the account console, including sign-in, key creation, the playground, usage reports, billing, and Team management. It is not required to read the public documentation, nor to try the API: a trial key needs no account and no browser — POST https://inference.boundless.network/api/agent-key, no body, and one comes back. Start with the documentation, review API compatibility, or see the current model pricing.

Read the documentation to see what we offer.
If you are an agent, read our llms.txt file.