Jina AI Models

14 modelsGeneral models free to startUp to 1M context

Usage

Last 30 days · 2026-09-07 to 2026-10-06

Tokens

8.4B

Requests

1.4M

Models in use

14 of 14

Tokens per day, stacked by model

0374M748M09-0709-1409-2109-2810-052026-09-07 — 314,258,925 tokens jina-reranker-m0: 119,085,650 jina-reranker-v3.5: 80,215,245 jina-embeddings-v3: 44,427,845 jina-embeddings-v4: 35,047,085 jina-embeddings-v5-text-small: 26,733,625 jina-reranker-v3: 6,919,295 6 more models: 1,811,960 jina-deepsearch-v1: 18,2202026-09-08 — 340,944,995 tokens jina-reranker-m0: 118,805,890 jina-reranker-v3.5: 96,164,520 jina-embeddings-v3: 54,982,775 6 more models: 24,410,050 jina-embeddings-v4: 23,503,485 jina-embeddings-v5-text-small: 20,545,675 jina-reranker-v3: 2,168,730 jina-search: 292,115 jina-deepsearch-v1: 71,7552026-09-09 — 482,736,925 tokens jina-search: 191,349,360 jina-reranker-m0: 102,285,920 jina-embeddings-v4: 58,599,335 jina-embeddings-v3: 52,306,075 jina-reranker-v3: 21,802,595 jina-embeddings-v5-text-small: 21,216,990 jina-reranker-v3.5: 20,860,700 jina-deepsearch-v1: 13,753,065 6 more models: 562,8852026-09-10 — 330,975,830 tokens jina-reranker-m0: 99,396,830 jina-reranker-v3.5: 87,231,790 jina-embeddings-v3: 51,732,335 jina-deepsearch-v1: 36,172,130 jina-reranker-v3: 20,077,120 jina-embeddings-v5-text-small: 17,899,770 jina-embeddings-v4: 14,716,315 6 more models: 3,731,700 jina-search: 17,8402026-09-11 — 748,168,870 tokens jina-deepsearch-v1: 443,474,895 jina-reranker-v3.5: 117,834,555 jina-reranker-m0: 98,767,000 jina-embeddings-v3: 59,536,810 jina-embeddings-v5-text-small: 20,803,885 jina-reranker-v3: 7,506,320 jina-embeddings-v4: 235,510 6 more models: 9,8952026-09-12 — 614,071,265 tokens jina-deepsearch-v1: 445,573,730 jina-reranker-m0: 58,053,805 jina-embeddings-v3: 53,762,500 jina-reranker-v3.5: 23,730,355 jina-embeddings-v5-text-small: 22,306,620 jina-reranker-v3: 8,613,140 6 more models: 1,868,110 jina-embeddings-v4: 163,0052026-09-13 — 154,021,560 tokens jina-embeddings-v3: 56,900,780 jina-reranker-m0: 31,154,795 jina-reranker-v3.5: 26,890,465 jina-embeddings-v5-text-small: 22,184,675 jina-embeddings-v4: 10,812,070 jina-reranker-v3: 3,054,085 jina-deepsearch-v1: 2,484,235 6 more models: 540,4552026-09-14 — 336,511,570 tokens jina-reranker-m0: 101,071,165 jina-reranker-v3.5: 99,870,605 jina-embeddings-v3: 65,519,825 jina-embeddings-v4: 26,679,870 jina-reranker-v3: 17,070,370 jina-embeddings-v5-text-small: 16,092,495 6 more models: 7,534,105 jina-deepsearch-v1: 2,673,1352026-09-15 — 311,275,635 tokens jina-reranker-m0: 117,138,175 jina-reranker-v3.5: 101,253,760 jina-embeddings-v3: 42,686,105 jina-embeddings-v5-text-small: 19,523,065 jina-embeddings-v4: 13,680,515 jina-reranker-v3: 12,461,030 6 more models: 4,515,045 jina-deepsearch-v1: 17,9402026-09-16 — 407,768,740 tokens jina-reranker-v3.5: 216,536,890 jina-reranker-m0: 103,825,480 jina-embeddings-v3: 47,991,260 jina-embeddings-v5-text-small: 16,998,185 jina-embeddings-v4: 9,518,720 jina-reranker-v3: 8,685,150 6 more models: 4,141,415 jina-deepsearch-v1: 71,6402026-09-17 — 320,004,155 tokens jina-reranker-v3.5: 132,781,630 jina-reranker-m0: 100,527,025 jina-embeddings-v3: 49,409,705 jina-embeddings-v5-text-small: 15,895,535 jina-embeddings-v4: 12,086,210 jina-reranker-v3: 4,864,590 6 more models: 4,403,580 jina-deepsearch-v1: 35,8802026-09-18 — 253,313,580 tokens jina-reranker-m0: 88,397,520 jina-embeddings-v3: 63,566,280 jina-reranker-v3.5: 59,336,350 jina-reranker-v3: 16,746,380 jina-embeddings-v5-text-small: 14,769,205 jina-embeddings-v4: 6,957,170 6 more models: 3,469,165 jina-deepsearch-v1: 71,5102026-09-19 — 178,969,175 tokens jina-embeddings-v3: 51,474,585 jina-reranker-v3.5: 46,073,295 jina-reranker-m0: 41,118,860 jina-embeddings-v5-text-small: 18,452,690 jina-embeddings-v4: 8,781,955 jina-reranker-v3: 8,542,175 jina-deepsearch-v1: 2,512,680 6 more models: 2,012,9352026-09-20 — 230,009,410 tokens jina-reranker-m0: 72,835,445 jina-embeddings-v3: 53,273,050 jina-reranker-v3.5: 51,318,105 jina-embeddings-v4: 21,226,215 jina-embeddings-v5-text-small: 19,928,730 jina-reranker-v3: 6,894,525 6 more models: 4,514,565 jina-deepsearch-v1: 18,7752026-09-21 — 379,373,825 tokens jina-reranker-m0: 98,461,740 jina-reranker-v3.5: 89,503,770 jina-embeddings-v5-text-small: 71,837,655 jina-embeddings-v3: 33,514,215 6 more models: 30,052,565 jina-deepsearch-v1: 22,118,055 jina-reranker-v3: 21,834,565 jina-embeddings-v4: 12,051,2602026-09-22 — 243,773,695 tokens jina-reranker-m0: 96,335,415 jina-reranker-v3.5: 63,192,495 jina-embeddings-v3: 30,857,945 jina-reranker-v3: 19,659,675 jina-embeddings-v5-text-small: 18,227,405 jina-embeddings-v4: 10,365,755 6 more models: 5,051,655 jina-deepsearch-v1: 83,3502026-09-23 — 238,632,095 tokens jina-reranker-m0: 89,840,340 jina-reranker-v3.5: 62,140,405 jina-embeddings-v3: 36,493,085 jina-reranker-v3: 17,185,580 jina-embeddings-v5-text-small: 15,306,970 jina-embeddings-v4: 10,314,790 6 more models: 7,297,195 jina-deepsearch-v1: 53,7302026-09-24 — 220,696,700 tokens jina-reranker-m0: 90,054,150 jina-reranker-v3.5: 50,544,770 jina-embeddings-v3: 38,116,050 jina-embeddings-v5-text-small: 22,369,070 6 more models: 11,078,150 jina-reranker-v3: 4,730,600 jina-embeddings-v4: 3,750,070 jina-deepsearch-v1: 53,8402026-09-25 — 170,183,720 tokens jina-reranker-v3.5: 47,404,310 jina-reranker-m0: 44,813,945 jina-embeddings-v3: 29,345,610 jina-embeddings-v5-text-small: 21,142,345 6 more models: 18,207,700 jina-embeddings-v4: 5,062,645 jina-reranker-v3: 4,170,910 jina-deepsearch-v1: 36,2552026-09-26 — 152,417,890 tokens jina-reranker-v3.5: 60,396,875 jina-reranker-m0: 39,138,120 jina-embeddings-v3: 26,374,135 jina-embeddings-v5-text-small: 16,745,040 jina-embeddings-v4: 5,258,710 jina-reranker-v3: 4,202,855 jina-deepsearch-v1: 211,845 6 more models: 90,3102026-09-27 — 183,140,105 tokens jina-reranker-v3.5: 76,785,280 jina-reranker-m0: 42,648,855 jina-embeddings-v3: 28,361,535 jina-embeddings-v5-text-small: 20,799,170 jina-embeddings-v4: 5,525,250 jina-reranker-v3: 4,790,475 jina-deepsearch-v1: 3,065,470 6 more models: 1,164,0702026-09-28 — 221,593,265 tokens jina-reranker-m0: 97,413,295 jina-reranker-v3.5: 68,200,895 jina-embeddings-v3: 33,420,915 jina-embeddings-v4: 10,805,145 jina-reranker-v3: 4,854,185 jina-deepsearch-v1: 3,607,285 jina-embeddings-v5-text-small: 1,637,075 6 more models: 1,636,590 jina-search: 17,8802026-09-29 — 273,751,480 tokens jina-reranker-m0: 85,882,030 jina-embeddings-v4: 82,885,645 jina-reranker-v3.5: 57,662,975 jina-embeddings-v3: 29,842,815 6 more models: 11,949,880 jina-reranker-v3: 4,508,815 jina-embeddings-v5-text-small: 983,290 jina-deepsearch-v1: 36,0302026-09-30 — 202,451,915 tokens jina-reranker-m0: 62,827,220 jina-reranker-v3.5: 62,179,465 jina-embeddings-v3: 31,535,580 6 more models: 28,045,970 jina-deepsearch-v1: 8,557,360 jina-embeddings-v4: 6,100,890 jina-reranker-v3: 2,750,235 jina-embeddings-v5-text-small: 437,150 jina-search: 18,0452026-10-01 — 148,157,755 tokens jina-reranker-v3.5: 65,488,930 jina-reranker-m0: 43,520,900 jina-embeddings-v3: 29,828,280 6 more models: 5,871,835 jina-embeddings-v4: 2,028,830 jina-reranker-v3: 1,004,430 jina-embeddings-v5-text-small: 378,465 jina-deepsearch-v1: 36,0852026-10-02 — 202,690,665 tokens jina-embeddings-v3: 74,872,460 jina-reranker-v3.5: 68,889,315 jina-reranker-m0: 45,016,620 6 more models: 3,834,190 jina-reranker-v3: 3,679,420 jina-embeddings-v4: 3,253,365 jina-deepsearch-v1: 2,599,425 jina-embeddings-v5-text-small: 545,8702026-10-03 — 109,434,490 tokens jina-reranker-v3.5: 41,154,290 jina-reranker-m0: 34,849,170 jina-embeddings-v3: 27,562,230 jina-embeddings-v4: 2,665,335 6 more models: 1,634,430 jina-reranker-v3: 808,925 jina-deepsearch-v1: 416,585 jina-embeddings-v5-text-small: 343,5252026-10-04 — 164,187,870 tokens jina-reranker-m0: 59,377,285 jina-reranker-v3.5: 52,951,095 jina-embeddings-v3: 39,169,695 6 more models: 9,048,410 jina-embeddings-v4: 1,943,425 jina-reranker-v3: 1,648,980 jina-embeddings-v5-text-small: 48,9802026-10-05 — 199,783,460 tokens jina-reranker-m0: 82,731,755 jina-reranker-v3.5: 64,428,165 jina-embeddings-v3: 37,608,810 6 more models: 7,380,105 jina-embeddings-v4: 3,243,905 jina-deepsearch-v1: 2,834,660 jina-reranker-v3: 1,218,000 jina-embeddings-v5-text-small: 320,250 jina-search: 17,8102026-10-06 — 262,075,690 tokens jina-embeddings-v4: 80,222,375 jina-reranker-m0: 78,285,000 jina-reranker-v3.5: 55,926,835 jina-embeddings-v3: 31,078,150 6 more models: 9,079,325 jina-reranker-v3: 3,916,190 jina-deepsearch-v1: 3,228,000 jina-embeddings-v5-text-small: 339,815
  • jina-reranker-m0
  • jina-reranker-v3.5
  • jina-embeddings-v3
  • jina-deepsearch-v1
  • jina-embeddings-v4
  • jina-embeddings-v5-text-small
  • jina-reranker-v3
  • jina-search
  • 6 more models

Which models that traffic went to

  1. Jina Reranker M027.9%2.3B
  2. Jina Reranker V3.525.6%2.1B
  3. Jina Embeddings V315.6%1.3B
  4. Jina Deepsearch V111.8%994M
  5. Jina Embeddings V45.8%487M
  6. Jina Embeddings V5 Text Small5.5%465M
  7. Jina Reranker V32.9%246M
  8. Jina Search2.3%192M
  9. 6 more models2.6%215M

Share of 8.4B 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 14 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 14 Jina AI Models

Open in model list
Jina 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
jina-deepsearch-v1Takes text, vision, returns text.1M$0.05$0.05/M94 tok/s0.48 s
jina-reranker-v3Takes text, vision. Output modality not published.131K$0.05$0.05/M53 tok/s0.13 s
jina-reranker-v3.5Takes text. Output modality not published.131K$0.05$0.05/M51 tok/s0.73 s
jina-ocr-v1Takes vision, returns text.32KFreeFree/M56 tok/s0.56 s
jina-clip-v2Takes text, vision. Output modality not published.8K$0.05$0.05/M96 tok/s1.50 s
jina-colbert-v2Takes text. Output modality not published.8K$0.05$0.05/M52 tok/s0.67 s
jina-embeddings-v2-base-codeTakes text. Output modality not published.8K$0.05$0.05/M——
jina-embeddings-v3Takes text. Output modality not published.8K$0.05$0.05/M——
jina-embeddings-v4Takes text, vision. Output modality not published.—$0.05$0.05/M59 tok/s0.48 s
jina-embeddings-v5-text-nanoTakes text, vision. Output modality not published.—$0.05$0.05/M59 tok/s0.46 s
jina-embeddings-v5-text-smallTakes text, vision. Output modality not published.—$0.05$0.05/M——
jina-reader—$0.05$0.05/M——
jina-reranker-m0Takes text, vision. Output modality not published.—$0.05$0.05/M——
jina-search—$0.05$0.05/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.

Jina AI on AIHubMix

Which Jina AI model should I start with?

jina-ocr-v1 is free on input — the cheapest entry here that declares a token price, and it carries a 32K context. Move up to jina-deepsearch-v1 when answer quality matters more than cost.

Which of these models reason before answering?

1 of the 14 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.

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 Jina 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.

Other Model Authors

See all model authors →
Qwen
149 modelsOpenAI
142 modelsGoogle
88 modelsZ.AI
71 modelsLlama
53 models

Start calling Jina AI in one line

One key, one endpoint, 913 models across 42 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Connect

Terms & Policies