Jina VLM
Model catalog reference rate; endpoint billing unverified
The catalog rate does not establish the endpoint’s actual billing; excluded from lowest-cost comparisons.
Type / status: reader / beta_api_alias_pending
Use cases: Document understanding, Web content processing
Supported languages: multilingual
Deployment options: api, license, huggingface, airgapped
Documented datacenters: US
Model release date: 2025-12-04
API endpoint: https://api-beta-vlm.jina.ai/v1/chat/completions
Open-weights license (hosted API terms are separate): CC-BY-NC-4.0
Excluded from default production recommendations; check model availability, pricing and usage conditions.
Official catalog input-token price. Embeddings produce vectors and rerankers produce rankings, not billable generated output tokens. Zero catalog completion/image/request values do not make the service free. Reader API billing is separate from the model-catalog price.
The Reader page advertises 10 million free tokens for a new API key. Actual allocation and expiry are subject to the official account; this is a trial, not permanent free access.
Subject to hosted service terms; buying API tokens does not license model weights. Each model has its own weight license. CC-BY-NC-4.0 and Qwen Research License must not be described as unrestricted commercial self-hosting. Official FAQ states API requests, inputs and outputs are not used to train models. Jina legal page directs current data processing to Elastic's Data Processing Addendum. Model catalog lists US datacenters; Reader/Search also document EU endpoints. Do not infer identical regions across products.
Official model ID: jina-ai/jina-vlm
Input / output: text, image → text
Model developer: Jina AI · Service provider: Jina AI
Model family: — · Currency: USD
| Price dimension | Current rate |
|---|---|
| Input | USD 0.05 |
| Cached read | Unverified |
jina-vlm is a 2.4B parameter vision-language model that achieves state-of-the-art multilingual visual question answering among open 2B-scale VLMs. The model couples a SigLIP2-So400M vision encoder (449M parameters) with a Qwen3-1.7B language backbone through an attention-pooling connector that reduces visual tokens by 4× while preserving spatial information. Using overlapping image tiling with 12 tiles plus a global thumbnail, it processes images of arbitrary resolution up to 4K. Training data comprises approximately 5M multimodal samples and 12B text tokens across 29 languages, with roughly half in English and the remainder spanning high- and moderate-resource languages including Chinese, Arabic, German, Spanish, French, Italian, Japanese, Korean, and more. Official announcement uses jina-vlm on the beta chat endpoint, whose live model list identifies jina-vlm-v1. Reader also documents X-Respond-With: vlm. Alias and beta commercial availability require confirmation. Endpoint or model-list evidence is recorded; request compatibility and service-specific pricing require confirmation.
Documented API context: 32,768 tokens
Official source · Last verified: 2026-10-15T09:33:13.684489+00:00