Ainfera
for agents · the primary user

Your agent doesn't need ten API keys.
It needs one line.

Point any OpenAI- or Anthropic-compatible agent at Ainfera, set model="ainfera-inference", and every call routes to the model most likely to finish the task — neutral across providers, settled per call, signed on chain. No model-pinning, no ten-vendor key sprawl.

Start building →for agents → /llms.txt
the one line · pythoncopy
# pip install openai · key from `ainfera install`
client = OpenAI(base_url="https://api.ainfera.ai/v1", api_key=AINFERA_KEY)
res = client.chat.completions.create(model="ainfera-inference", messages=msgs)
/// how an agent uses Ainfera

One key. No pinning. Settled per call.

one key

A single ainfera_ key

One ainfera_ key for the whole fleet — scoped per agent, with caps and a pause toggle on the agent, not a drawer of provider keys to rotate.

no pinning

You don't choose the model

Send model=ainfera-inference and we route within your caps to whatever finishes the task. Pin a specific model any time to opt out — we still settle and audit it.

settlement

Per-call x402 settlement

Each call settles on its own over x402 — sub-$0.001 granularity, no monthly invoice to reconcile. Pricing: /pricing.

outcome

Routed to what finishes it

The route is decided per call on the likely outcome, then signed on chain. The mechanism stays ours; the result is yours to verify — how routing works →

/// agent-native by default

Built to be driven by software, headless.

MCP

MCP skill

Reachable as an MCP server at mcp.ainfera.ai — your agent discovers and calls Ainfera as a tool, no glue code.

headless

Works without a UI

Sign up, mint a key, call, and verify — all over the API. No dashboard required to operate; the dashboard is for humans who want to watch.

machine-readable

Every surface has a twin

The catalog, the index and the audit trail are all JSON or plain text — /v1/models, /llms.txt, /v1/audit/public.

/// framework quickstarts

Drop into the framework you already run.

primary · native skill

OpenClaw & Hermes Agent

First-class adapters: route every step through ainfera-inference with one config line. Setup in the docs.

also supported

LangGraph · CrewAI · ADK

Anything that speaks the OpenAI or Anthropic API works unchanged — point the base URL at Ainfera and set the model. Framework guides in the docs.

/// the agent's-eye view

Answer "what can I use, and what did it cost?" without a dashboard.

the setGET https://api.ainfera.ai/v1/models
every model it can route to — lab, host, context, modalities, origin
the proofGET https://api.ainfera.ai/v1/audit/public
routed decisions + outcomes, signed — keyless, anyone can verify
the indexGET https://ainfera.ai/llms.txt
the whole site, agent-shaped
spend · savings · balancelandinga read-API so your agent reads its own spend, savings and balance without opening the dashboard. Shipping with the dashboard read-models.
Copy the quickstart →GET /v1/models
routing · activeblock #12,273models · 245audit · on-chainainfera · the inference of ai agents