Recursive Models

1 modelGeneral models free to start

Usage

Last 29 days · 2026-10-25 to 2026-11-22

Tokens

31.1M

Requests

1K

Models in use

1 of 1

Tokens per day, stacked by model

02.7M5.5M10-2511-0111-0811-1511-222026-10-25 — 10,195 tokens flint-v1.0-free: 10,1952026-10-26 — 374,860 tokens flint-v1.0-free: 374,8602026-10-27 — 22,165 tokens flint-v1.0-free: 22,1652026-10-28 — 80,735 tokens flint-v1.0-free: 80,7352026-10-29 — 5,158,350 tokens flint-v1.0-free: 5,158,3502026-10-30 — 6,800 tokens flint-v1.0-free: 6,8002026-10-31 — 0 tokens2026-11-01 — 0 tokens2026-11-02 — 0 tokens2026-11-03 — 0 tokens2026-11-04 — 4,520,405 tokens flint-v1.0-free: 4,520,4052026-11-05 — 935,520 tokens flint-v1.0-free: 935,5202026-11-06 — 209,445 tokens flint-v1.0-free: 209,4452026-11-07 — 915,875 tokens flint-v1.0-free: 915,8752026-11-08 — 676,415 tokens flint-v1.0-free: 676,4152026-11-09 — 1,883,150 tokens flint-v1.0-free: 1,883,1502026-11-10 — 1,759,355 tokens flint-v1.0-free: 1,759,3552026-11-11 — 83,970 tokens flint-v1.0-free: 83,9702026-11-12 — 654,945 tokens flint-v1.0-free: 654,9452026-11-13 — 364,795 tokens flint-v1.0-free: 364,7952026-11-14 — 702,535 tokens flint-v1.0-free: 702,5352026-11-15 — 99,480 tokens flint-v1.0-free: 99,4802026-11-16 — 379,855 tokens flint-v1.0-free: 379,8552026-11-17 — 1,186,775 tokens flint-v1.0-free: 1,186,7752026-11-18 — 172,940 tokens flint-v1.0-free: 172,9402026-11-19 — 5,480,820 tokens flint-v1.0-free: 5,480,8202026-11-20 — 67,715 tokens flint-v1.0-free: 67,7152026-11-21 — 301,955 tokens flint-v1.0-free: 301,9552026-11-22 — 5,062,755 tokens flint-v1.0-free: 5,062,755

Which models that traffic went to

  1. Flint V1.0 (free)100.0%31.1M

Share of 31.1M tokens.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 29 days, counting the 1 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 1 Recursive Models

Open in model list
Recursive models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
flint-v1.0-freeTakes text, returns text.FreeFree/M

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Recursive on AIHubMix

Which Recursive model should I start with?

flint-v1.0-free is free on input — the cheapest entry here that declares a token price.

Do I need a separate Recursive account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Start calling Recursive in one line

One key, one endpoint, 985 models across 49 model authors.