Kolibri 1

What you can use today

Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.

Exact checkpoint ID: Aleph-Alpha/Kolibri-1. This exact FP8 checkpoint supports text and tool calls through its serving parser. Thinking levels are configured through the chat template; an omitted default is unverified.

Available thinking settings: none, low, medium, high. We do not yet have comparable independent results for these settings. The default applied when a request omits effort is unverified.

The checkpoint declares Apache 2.0. Running it yourself requires hardware, serving and operational work; it does not establish a zero-cost hosted API.

The card states 262,144 native context tokens and validates extension to 1,048,576. It recommends at most 262,144 for complex tasks and serving efficiency. These are checkpoint claims, not a hosted API guarantee.

This model is absent from the reviewed routed catalog. Subscription access does not establish a public per-token API rate. Your bill can also include tools, retries and charged thinking tokens. Check the offer used by your application.

Provider release and specifications ↗

Check availability and plans ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.