Jina AI Models

Q: 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.

14 modelsGeneral models free to startUp to 1M context

Usage

Last 30 days · 2026-10-02 to 2026-10-31

Tokens

15.4B

Requests

583K

Models in use

14 of 14

Tokens per day, stacked by model

jina-embeddings-v4
jina-reranker-v3.5
jina-reranker-m0
jina-embeddings-v3
jina-reranker-v3
jina-clip-v2
jina-embeddings-v5-text-nano
jina-deepsearch-v1
6 more models

Which models that traffic went to

Share of 15.4B 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-v1	Takes text, vision, returns text.	1M	$0.05$0.05/M	83 tok/s	0.44 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. Output modality not published.	131K	$0.05$0.05/M	58 tok/s	0.32 s
jina-ocr-v1	Takes vision, returns text.	32K	FreeFree/M	47 tok/s	0.66 s
jina-clip-v2	Takes text, vision. Output modality not published.	8K	$0.05$0.05/M	96 tok/s	1.50 s
jina-colbert-v2	Takes text. Output modality not published.	8K	$0.05$0.05/M	52 tok/s	0.67 s
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	68 tok/s	0.15 s
jina-embeddings-v4	Takes text, vision. Output modality not published.	—	$0.05$0.05/M	59 tok/s	0.48 s
jina-embeddings-v5-text-nano	Takes text, vision. Output modality not published.	—	$0.05$0.05/M	59 tok/s	0.46 s
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	—	—

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.