intern-ai Models

2 modelsGeneral models free to startUp to 262K context

Usage

Last 30 days · 2026-10-24 to 2026-11-22

Tokens

243M

Requests

6.1K

Models in use

2 of 2

Tokens per day, stacked by model

011.1M22.3M10-2410-3111-0711-1411-212026-10-24 — 12,208,655 tokens agents-a1-free: 9,897,890 intern-s2-free: 2,310,7652026-10-25 — 6,922,430 tokens agents-a1-free: 4,847,795 intern-s2-free: 2,074,6352026-10-26 — 3,872,060 tokens agents-a1-free: 3,428,475 intern-s2-free: 443,5852026-10-27 — 6,576,970 tokens agents-a1-free: 6,060,330 intern-s2-free: 516,6402026-10-28 — 6,622,700 tokens agents-a1-free: 3,587,870 intern-s2-free: 3,034,8302026-10-29 — 5,416,700 tokens agents-a1-free: 4,218,565 intern-s2-free: 1,198,1352026-10-30 — 3,703,035 tokens agents-a1-free: 2,932,715 intern-s2-free: 770,3202026-10-31 — 5,520,185 tokens agents-a1-free: 3,764,725 intern-s2-free: 1,755,4602026-11-01 — 2,353,995 tokens agents-a1-free: 1,220,390 intern-s2-free: 1,133,6052026-11-02 — 6,597,455 tokens agents-a1-free: 4,325,235 intern-s2-free: 2,272,2202026-11-03 — 5,797,930 tokens intern-s2-free: 4,093,265 agents-a1-free: 1,704,6652026-11-04 — 8,545,045 tokens agents-a1-free: 5,588,190 intern-s2-free: 2,956,8552026-11-05 — 7,835,660 tokens agents-a1-free: 7,220,770 intern-s2-free: 614,8902026-11-06 — 9,369,805 tokens agents-a1-free: 7,183,930 intern-s2-free: 2,185,8752026-11-07 — 2,466,115 tokens intern-s2-free: 1,478,135 agents-a1-free: 987,9802026-11-08 — 13,019,570 tokens agents-a1-free: 8,430,765 intern-s2-free: 4,588,8052026-11-09 — 4,390,930 tokens agents-a1-free: 3,779,325 intern-s2-free: 611,6052026-11-10 — 6,371,405 tokens agents-a1-free: 3,659,215 intern-s2-free: 2,712,1902026-11-11 — 9,161,470 tokens agents-a1-free: 7,538,000 intern-s2-free: 1,623,4702026-11-12 — 22,290,215 tokens agents-a1-free: 18,882,325 intern-s2-free: 3,407,8902026-11-13 — 12,003,930 tokens agents-a1-free: 11,903,965 intern-s2-free: 99,9652026-11-14 — 15,637,490 tokens agents-a1-free: 15,529,055 intern-s2-free: 108,4352026-11-15 — 13,512,330 tokens agents-a1-free: 13,418,755 intern-s2-free: 93,5752026-11-16 — 4,006,435 tokens agents-a1-free: 3,890,855 intern-s2-free: 115,5802026-11-17 — 8,879,615 tokens agents-a1-free: 8,165,260 intern-s2-free: 714,3552026-11-18 — 13,499,415 tokens agents-a1-free: 12,460,535 intern-s2-free: 1,038,8802026-11-19 — 7,047,450 tokens agents-a1-free: 6,689,885 intern-s2-free: 357,5652026-11-20 — 3,633,515 tokens agents-a1-free: 3,374,740 intern-s2-free: 258,7752026-11-21 — 9,534,235 tokens agents-a1-free: 9,003,520 intern-s2-free: 530,7152026-11-22 — 5,792,150 tokens intern-s2-free: 4,496,085 agents-a1-free: 1,296,065
  • agents-a1-free
  • intern-s2-free

Which models that traffic went to

  1. Agents A1 (free)80.4%195M
  2. Intern S2 (free)19.6%47.6M

Share of 243M 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 30 days, counting the 2 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 2 intern-ai Models

Open in model list
intern-ai 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
agents-a1-freeTakes text, vision, returns text.262KFreeFree/M
intern-s2-freeTakes text, vision, returns text.262KFreeFree/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.

intern-ai on AIHubMix

Which intern-ai model should I start with?

agents-a1-free is free on input — the cheapest entry here that declares a token price, and it carries a 262K context. Move up to intern-s2-free when answer quality matters more than cost.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

Do I need a separate intern-ai 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 intern-ai in one line

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