Skip to model comparison
AI Agent Store/Model comparisonsBuild an AI worker ↗

Recursive · New hosted model verified

Recursive Flint · OpenRouter free

Try Flint for coding and tool-assisted text tasks through a currently free OpenRouter offer. Check availability before building around a free service.

Catalog added 2026-10-21 UTC · Checked 2026-11-03. Catalog addition and provider launch are separate dates.

We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.

Input / 1M tokens$0Routed catalog offer · USD
Output / 1M tokens$0Routed catalog offer · USD
Provider-listed capacity262KSee input limits below
Cached input / 1M—Routed catalog offer · USD

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 catalog ID: recursive/flint-v1.0:free. Reasoning is required; the catalog does not establish named effort levels or a default effort. Your application runs the tools.

The free hosting offer has its own limits. Apache 2.0 weights are separately downloadable; hosting terms and data handling are separate.

OpenRouter lists 262,144 context and 235,929 maximum output tokens. Thinking and the answer share the output budget.

Input and output are currently quoted at zero. No expiry date or permanent free-access promise is verified. Allow for retries and any tool fees. Models that think before answering may also charge for that work.

Provider release and specifications ↗

Inspect the exact catalog model ↗

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.

Compare caching and long-context costs ↗
AI Agent Store · Model comparisons · Data reviewed 2026-11-03Sources, limitations & corrections ↗