Open-weight mixture-of-experts model with about 2.5B active parameters for local coding agentsFlint by recursive is offered by 3 providers on this page. It also has 3 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 262,144 tokens, with an output limit of 262,144 tokens. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2026-06.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Vercel AI Gateway recursive/flint-v1.0 | Cloud | Free | — | — | 262,144 | 262,144 | ||
| OpenCode flint-40b-free | Gateway | Free | $0 | — | 262,144 | 65,536 | ||
| Kilo Gateway recursive/flint-v1.0 | Gateway | Free | — | — | 262,144 | 262,144 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 3 providers.
This model is $0 across all listed channels (Vercel AI Gateway, OpenCode, Kilo Gateway).
Price history accumulates from each data sync; currently only 1 sample(s) (2026-10-22). Each future sync adds a point, and once accumulated a line is drawn here.