Jina AI Models
Usage
7.9B
1.7M
13 of 13
- jina-reranker-m0
- jina-embeddings-v4
- jina-embeddings-v3
- jina-deepsearch-v1
- jina-reranker-v3
- jina-embeddings-v5-text-small
- jina-reranker-v3.5
- jina-embeddings-v2-base-code
- 5 more models
- jina-embeddings-v3
- jina-reranker-m0
- jina-embeddings-v4
- jina-embeddings-v5-text-small
- jina-reranker-v3
- jina-colbert-v2
- jina-embeddings-v5-text-nano
- jina-embeddings-v2-base-code
- 5 more models
Which models that traffic went to
- Jina Reranker M032.5%2.6B
- Jina Embeddings V425.1%2B
- Jina Embeddings V322.9%1.8B
- Jina Deepsearch V111.1%870M
- Jina Reranker V34.4%348M
- Jina Embeddings V5 Text Small2.2%171M
- Jina Reranker V3.50.8%66.5M
- Jina Embeddings V2 Base Code0.5%40M
- 5 more models0.5%40M
- Jina Embeddings V377.9%1.3M
- Jina Reranker M013.1%219K
- Jina Embeddings V45.1%85.2K
- Jina Embeddings V5 Text Small2.3%38.8K
- Jina Reranker V30.9%15.1K
- Jina Colbert V20.2%4K
- Jina Embeddings V5 Text Nano0.1%1.9K
- Jina Embeddings V2 Base Code0.1%1.5K
- 5 more models0.1%2.1K
All 13 Jina AI Models
Open in model list| Modalities | |||||
|---|---|---|---|---|---|
| jina-deepsearch-v1 | Takes text, vision, returns text. | 1M | $0.05$0.05/M | 48 tok/s | 0.43 s |
| jina-reranker-v3 | Takes text, vision. Output modality not published. | 131K | $0.05$0.05/M | 53 tok/s | 0.13 s |
| jina-reranker-v3.5 | Takes text, vision. Output modality not published. | 131K | $0.05$0.05/M | 53 tok/s | 0.13 s |
| jina-clip-v2 | Takes text, vision. Output modality not published. | 8K | $0.05$0.05/M | — | — |
| jina-colbert-v2 | Takes text. Output modality not published. | 8K | $0.05$0.05/M | — | — |
| jina-embeddings-v2-base-code | Takes text. Output modality not published. | 8K | $0.05$0.05/M | — | — |
| jina-embeddings-v3 | Takes text. Output modality not published. | 8K | $0.05$0.05/M | — | — |
| jina-embeddings-v4 | Takes text, vision. Output modality not published. | — | $0.05$0.05/M | 112 tok/s | 0.58 s |
| jina-embeddings-v5-text-nano | Takes text, vision. Output modality not published. | — | $0.05$0.05/M | — | — |
| jina-embeddings-v5-text-small | Takes text, vision. Output modality not published. | — | $0.05$0.05/M | — | — |
| jina-reader | — | $0.05$0.05/M | — | — | |
| jina-reranker-m0 | Takes text, vision. Output modality not published. | — | $0.05$0.05/M | — | — |
| jina-search | — | $0.05$0.05/M | — | — |
Jina AI on AIHubMix
Which Jina AI model should I start with?
jina-clip-v2 at $0.05/M input — the cheapest entry here that declares a token price, and it carries a 8K context. Move up to jina-deepsearch-v1 when answer quality matters more than cost.
Which of these models reason before answering?
1 of the 13 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.
Start calling Jina AI in one line
One key, one endpoint, 859 models across 37 model authors.
AIHubMix