Jina
on Orq.ai
Use Jina’s search and retrieval APIs through a single Orq.ai endpoint. Route Jina’s embeddings, rerankers, and Reader API via Orq’s AI Router to power RAG, semantic search, and retrieval‑heavy workloads alongside your LLM stack.
Capabilities:
Chat
Embeddings
Speech
Models Supported:
jina-embeddings-v5-omni-nano
jina-embeddings-v5-omni-small
jina-embeddings-v5-text-nano
jina-embeddings-v5-text-small
jina-reranker-v3
Provider HQ:
Jina AI headquartered in Sunnyvale, California, USA.
Access Jina through Orq.ai’s AI Router
Jina AI provides a suite of “search foundation” APIs: multimodal embeddings, late‑interaction rerankers, and a Reader API that turns web pages or documents into clean text/Markdown, all with token‑based billing shared across products. These services are designed to be a complete retrieval layer for production RAG pipelines at low per‑token cost.
Jina models available on Orq.ai
Why use Jina through Orq.ai?
Capability | Provider / models | Direct | Through Orq.ai |
|---|---|---|---|
Embeddings | Jina embedding APIs (text / multimodal) | Call Jina’s embedding endpoints directly to generate vectors for text and multimodal content | Use Jina embeddings through Orq.ai’s router so retrieval stays observable and configurable alongside your LLM requests |
Rerank | Jina Reranker V2 Base (multilingual) and related | Use Jina rerankers directly to reorder search/RAG results based on neural relevance | Route rerank calls via Orq.ai and keep logs, metrics, and evals in the same place as your model traffic |
Reader | Reader API (web‑to‑Markdown) | Call Reader directly to turn URLs and documents into clean text/Markdown for indexing | Integrate Reader into Orq‑managed workflows so the same router that handles LLM calls also orchestrates content ingestion |
This gives teams a practical way to use Jina where it performs best while centralising routing, observability, evals, and cost controls across the wider model stack.
Pricing
Model rates
Jina pricing is token‑based and shared across APIs (embeddings, rerankers, Reader):
Free / non‑commercial tier: around 1–10M tokens included for experimentation.
Prototype tier: about 0.05 USD per 1M tokens (good for small‑scale production).
Production tier: about 0.045 USD per 1M tokens for high‑volume enterprise RAG.
Specific APIs like Jina Reranker V2 Base are listed at about 0.018 USD per 1M input and 0.018 USD per 1M output tokens.
Check the Orq.ai pricing page and your workspace’s provider configuration for current per‑API rates, quotas, and plan details.
Compatible frameworks and tools
Orq.ai exposes Jina via:
a Jina provider configuration in the AI Router / Model Garden, and
standard HTTP/OpenAI‑compatible integrations in supported frameworks.
That means:
Popular RAG stacks (for example Qdrant, LangChain‑style frameworks, AI SDKs) can call Jina embeddings and rerankers via Orq’s router instead of wiring each integration separately.
Agents, code assistants, and tools that already talk to Orq.ai (through OpenAI‑compatible or HTTP tools) can incorporate Jina for retrieval without changing their core integration.
Check the Orq.ai integration docs for the latest supported frameworks and tools for Jina.
FAQs
Do I need a separate Jina account to use Jina through Orq.ai?
You can either connect your own Jina API key into Orq.ai or, where available, use Jina usage billed via Orq.ai; the exact options depend on your Orq plan, region, and how Jina is configured in your workspace. In both cases, Orq.ai gives you one place to manage routing, observability, and cost controls around that Jina usage.
Can I route only some workflows to Jina and others to different providers?
Yes. You define routes per workflow in Orq.ai and decide which ones should use Jina vs other retrieval or embedding providers, so you can reserve Jina for specific RAG paths while sending other tasks to different stacks.
Does using Jina through Orq.ai add latency?
Orq.ai is designed as a lightweight router layer, so the added overhead is small compared to embedding, rerank, or Reader processing times. You can use routing policies, caching, and provider selection to keep end‑to‑end performance within your targets.
Alternatives to
Jina
Anthropic
Use Claude Opus 4.7, Sonnet 4.6, Haiku 4.5, and other supported Claude models through one API.
Chat
Code
Reasoning
Vision
Models:
claude-opus-5
claude-sonnet-5
claude-fable-5
Open AI
Use OpenAI's foundation models through a single Orq.ai API. Route models such as GPT-4.1, GPT-4.1-mini, o3-mini, and GPT-4o-class models via Orq's AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Image Generation
Reasoning
Speech
Vision
Models:
gpt-5.5 (EU)
gpt-5.6-luna (EU)
gpt-5.6-sol (EU)
Google AI
Use Google’s Gemini models through a single Orq.ai API. Route models such as Gemini 3.1 Pro, Gemini 2.5 Flash, and Gemini 2.0 Flash‑Lite via Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Image Generation
Reasoning
Speech
Vision
Models:
gemini-3.5-flash-lite (Gemini API)
gemini-3.6-flash (Gemini API)
Gemini 3 Pro Image
AWS
Use AWS Bedrock’s foundation models through a single Orq.ai API. Route models such as Amazon Nova, Amazon Titan Text, and compatible third‑party models exposed via Bedrock through Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Reasoning
Vision
Models:
eu.anthropic.claude-opus-5
global.anthropic.claude-opus-5
us.anthropic.claude-opus-5
