TypeSafe Models

3 modelsGeneral models from $0.0462/M inputUp to 64K contextOfficial site ↗

Usage

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

Tokens

173B

Requests

18.8M

Models in use

3 of 3

Tokens per day, stacked by model

05.9B11.9B10-2410-3111-0711-1411-212026-10-24 — 1,992,889,900 tokens jev-1.14: 1,658,811,035 jev-1.13: 308,746,035 jev-latest: 25,332,8302026-10-25 — 1,628,690,590 tokens jev-1.14: 1,201,307,930 jev-1.13: 400,181,515 jev-latest: 27,201,1452026-10-26 — 8,028,865,720 tokens jev-latest: 6,925,543,365 jev-1.14: 671,717,280 jev-1.13: 431,605,0752026-10-27 — 3,427,884,340 tokens jev-1.14: 2,295,920,495 jev-latest: 735,331,155 jev-1.13: 396,632,6902026-10-28 — 4,245,101,895 tokens jev-latest: 1,636,737,040 jev-1.14: 1,584,757,470 jev-1.13: 1,023,607,3852026-10-29 — 7,194,577,260 tokens jev-1.13: 5,160,473,805 jev-latest: 1,228,304,780 jev-1.14: 805,798,6752026-10-30 — 6,092,645,645 tokens jev-1.13: 4,335,118,550 jev-latest: 1,249,877,435 jev-1.14: 507,649,6602026-10-31 — 2,237,592,600 tokens jev-latest: 1,135,211,895 jev-1.13: 674,771,490 jev-1.14: 427,609,2152026-11-01 — 1,562,781,460 tokens jev-1.13: 702,086,510 jev-1.14: 475,510,850 jev-latest: 385,184,1002026-11-02 — 5,815,522,780 tokens jev-1.13: 4,424,028,660 jev-1.14: 1,178,975,650 jev-latest: 212,518,4702026-11-03 — 9,371,800,230 tokens jev-1.13: 5,500,331,615 jev-1.14: 2,506,859,840 jev-latest: 1,364,608,7752026-11-04 — 7,044,885,665 tokens jev-1.13: 3,521,539,070 jev-1.14: 2,886,244,520 jev-latest: 637,102,0752026-11-05 — 3,712,811,430 tokens jev-1.14: 2,900,393,040 jev-latest: 506,994,210 jev-1.13: 305,424,1802026-11-06 — 3,905,032,270 tokens jev-1.14: 2,951,269,050 jev-latest: 710,746,980 jev-1.13: 243,016,2402026-11-07 — 3,808,302,655 tokens jev-1.14: 3,018,317,005 jev-1.13: 410,031,650 jev-latest: 379,954,0002026-11-08 — 3,370,414,760 tokens jev-1.14: 2,660,971,480 jev-1.13: 545,269,345 jev-latest: 164,173,9352026-11-09 — 8,994,076,130 tokens jev-1.13: 4,719,400,350 jev-1.14: 3,201,850,210 jev-latest: 1,072,825,5702026-11-10 — 8,362,775,115 tokens jev-1.13: 4,002,126,165 jev-1.14: 3,247,566,645 jev-latest: 1,113,082,3052026-11-11 — 8,183,747,860 tokens jev-1.13: 4,642,609,500 jev-1.14: 2,366,269,215 jev-latest: 1,174,869,1452026-11-12 — 7,938,468,895 tokens jev-1.13: 5,190,488,805 jev-1.14: 1,719,684,450 jev-latest: 1,028,295,6402026-11-13 — 11,875,204,150 tokens jev-1.13: 7,748,745,485 jev-1.14: 3,236,769,705 jev-latest: 889,688,9602026-11-14 — 3,720,440,290 tokens jev-1.14: 2,883,125,790 jev-1.13: 609,677,515 jev-latest: 227,636,9852026-11-15 — 3,551,247,515 tokens jev-1.14: 2,690,129,845 jev-1.13: 504,806,690 jev-latest: 356,310,9802026-11-16 — 6,779,793,260 tokens jev-1.14: 2,877,109,060 jev-1.13: 2,759,973,210 jev-latest: 1,142,710,9902026-11-17 — 6,717,085,930 tokens jev-1.14: 3,449,501,925 jev-1.13: 2,343,222,200 jev-latest: 924,361,8052026-11-18 — 7,045,024,745 tokens jev-1.14: 2,964,715,790 jev-latest: 2,168,398,385 jev-1.13: 1,911,910,5702026-11-19 — 9,602,201,050 tokens jev-1.13: 6,124,193,990 jev-1.14: 2,905,474,875 jev-latest: 572,532,1852026-11-20 — 8,660,345,730 tokens jev-1.13: 4,493,069,585 jev-1.14: 3,236,172,125 jev-latest: 931,104,0202026-11-21 — 5,297,555,605 tokens jev-1.14: 4,079,648,975 jev-1.13: 1,085,832,415 jev-latest: 132,074,2152026-11-22 — 3,130,685,210 tokens jev-1.14: 2,356,754,910 jev-1.13: 617,434,010 jev-latest: 156,496,290
  • jev-1.13
  • jev-1.14
  • jev-latest

Which models that traffic went to

  1. Jev 1.1343.4%75.1B
  2. Jev 1.1439.8%68.9B
  3. Jev16.9%29.2B

Share of 173B 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 3 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 3 TypeSafe Models

Open in model list
TypeSafe 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
jev-1.13Takes text, vision. Output modality not published.64K$0.0462$0.0462/M
jev-1.14Takes text, vision. Output modality not published.64K$0.0462$0.0462/M
jev-latestTakes text, vision. Output modality not published.64K$0.0462$0.0462/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.

TypeSafe on AIHubMix

Which TypeSafe model should I start with?

jev-1.13 at $0.0462/M input — the cheapest entry here that declares a token price, and it carries a 64K context. Move up to jev-1.14 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 TypeSafe 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 TypeSafe in one line

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