Manifesto

Build agents,
not infrastructure.

Running models in production means capacity, failover, privacy, and cost, every hour of every day. We think builders should spend their time on what their agents do, not on keeping models online. Everything we build follows from that belief.

01

We run the models. You build the product.

Serving a model well takes capacity, redundancy, and people watching it around the clock. We deploy and operate the models your agents run on, so trouble on one deployment does not become your incident.

02

Speak the formats you already know.

You should not have to learn a new wire format to build on Aivene. Use OpenAI Chat Completions, OpenAI Responses, or Anthropic Messages, and your existing clients keep working.

03

Pay for what you use. Nothing else.

No plans, no seats, no minimums, no annual commitments. Top up once and every request is billed per token at the listed rate. If you stop calling, you stop paying.

04

Prices belong in plain sight.

Every rate is published before you make a single call: input, output, cache, and context window. When a model is discounted, we show the normal price next to it. When a price changes with the time of day, we label it. You should never have to reverse-engineer an invoice.

05

Your prompts are yours.

We serve requests, we do not mine them. By default we keep the metadata needed to bill and debug, such as timestamps, token counts, and latency, and not the content of your prompts or responses. See our Privacy Policy for the details.

06

Reliability is measured, not promised.

Infrastructure goes down. Pretending otherwise helps nobody. We track the health of every model we serve and publish its uptime, so you can decide with real numbers instead of marketing claims.

07

Built by developers, for developers.

Clear errors over vague ones. Docs you can copy from. A playground to try a model before you write a line of code. We ship what we would want to use ourselves, and we cut what we would not.

Build the agent. We keep the models running. That is the whole point.

View all models