Jina
on Orq.ai
Access Jina’s retrieval and search capabilities through Orq.ai for embeddings, reranking, content extraction, and RAG workloads alongside your wider model stack.
Capabilities:
Embeddings
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
jina-code-embeddings-0.5b
jina-code-embeddings-1.5b
jina-embeddings-v4
jina-reranker-m0
jina-clip-v2
...
Provider HQ:
Sunnyvale, California
Access Jina through Orq.ai’s AI Router
Jina AI provides models and APIs for semantic search and retrieval, including embeddings, reranking, and tools for converting web content into structured text. These capabilities can support retrieval-heavy applications such as RAG, semantic search, document discovery, and content ingestion.
Jina models available on Orq.ai
Compare the Jina models and APIs currently available through Orq.ai, including their supported capabilities, pricing, and availability.
Model
Type
Context
Input / 1M
Output / 1M
jina-embeddings-v5-omni-nano
embedding
Audio
Video
8.2K
$0.02
$0.00
jina-embeddings-v5-omni-small
embedding
Audio
Video
33K
$0.05
$0.00
jina-embeddings-v5-text-nano
embedding
8.2K
$0.02
$0.00
Why use Jina through Orq.ai?
Using Jina through Orq.ai lets teams combine retrieval, reranking, and content ingestion with a wider AI stack without maintaining separate observability and workflow logic for every provider.
Capability | Provider | Direct | Through Orq.ai |
|---|---|---|---|
Embeddings | Jina embedding models | Use supported Jina models directly to generate vector representations for text and multimodal content. | Route embedding workloads through Orq.ai alongside the rest of your model stack while keeping observability and configuration in a shared platform. |
Rerank | Jina reranking models | Use supported reranking models to reorder retrieved results based on relevance to a query or instruction. | Incorporate reranking into Orq.ai-managed retrieval workflows while keeping logs, evaluations, and experiments connected to the wider application. |
Reader | Jina content extraction APIs | Use supported APIs to turn web pages and documents into clean text or structured content for downstream retrieval. | Combine content ingestion with retrieval, generation, and other model workflows managed through Orq.ai. |
Pricing
Jina pricing varies by model, API, usage volume, and billing configuration.
Different Jina capabilities may use different usage and billing models depending on the API being called. You can connect supported Jina credentials to Orq.ai or use other available access options depending on your workspace configuration.
Check Orq.ai and your Jina setup for current rates, quotas, and billing details.
Compatible frameworks and tools
Jina capabilities can be incorporated into supported Orq.ai retrieval and RAG workflows through available provider and API integrations. Compatibility depends on the model, API, and integration configuration being used.
Check the Orq.ai integration documentation for the latest setup options and compatibility information for Jina.
FAQs
Do I need a separate Jina account to use Jina through Orq.ai?
You can connect supported Jina credentials to Orq.ai or use other available access options depending on your workspace, plan, and region. Orq.ai provides a shared environment for managing retrieval and AI workflows around that usage.
Can I route only some workflows to Jina and others to different providers?
Yes. Orq.ai lets you use different providers for different parts of a workflow, so you can use Jina for embeddings, reranking, retrieval, or content ingestion while routing other AI workloads elsewhere.
Does using Jina through Orq.ai add latency?
Orq.ai adds an integration layer between your application and the provider. End-to-end latency depends on the retrieval operation, selected model or API, provider performance, and workflow configuration, and can be monitored where supported.
Alternatives to
Jina
Anthropic
Access Anthropic’s Claude models through Orq.ai for reasoning, coding, vision, and agentic workflows through one API.
Chat
Reasoning
Vision
Models:
claude-opus-5
claude-sonnet-5
claude-fable-5
Open AI
Access OpenAI models through Orq.ai for reasoning, coding, multimodal, and other AI workloads through one API.
Chat
Reasoning
Vision
Code
Models:
gpt-5.5 (EU)
gpt-5.6-luna (EU)
gpt-5.6-sol (EU)
Google AI
Access Google’s AI models through Orq.ai for reasoning, coding, multimodal, and other AI workloads through one API.
Chat
Reasoning
Vision
Code
Models:
gemini-3.5-flash-lite (Gemini API)
gemini-3.6-flash (Gemini API)
Gemini 3 Pro Image
AWS
Access foundation models available through Amazon Bedrock using Orq.ai for reasoning, coding, multimodal, and other AI workloads through one API.
Chat
Reasoning
Vision
Code
Models:
eu.anthropic.claude-opus-5
global.anthropic.claude-opus-5
us.anthropic.claude-opus-5
