How to use Jina AI API Key for AI chat
Ann Ng
Jina AIAbout Jina AI
Jina AI is a specialized AI platform providing best-in-class search infrastructure through embeddings, rerankers, web readers, and small language models for multilingual and multimodal data.
Key offerings include jina-embeddings-v3 (570M parameter model supporting 89 languages with 8K token context and task-specific LoRA adapters for retrieval, clustering, and classification), jina-embeddings-v4 (3.8B parameter multimodal model unifying text and images), Reader API (converts any URL to LLM-ready Markdown using ReaderLM-v2), Reranker API (improves search result accuracy), and DeepSearch (comprehensive search agent combining web search, reading, and reasoning with OpenAI-compatible API).
The platform features FlashAttention 2 optimization, 1024-dimensional embeddings, late-chunking for better snippet selection, and integration with popular frameworks, making it ideal for RAG systems and semantic search applications.
Step by step guide to use Jina AI API Key to chat with AI
1. Get Your Jina AI API Key
First, you'll need to obtain an API key from Jina AI. This key allows you to access their AI models directly and pay only for what you use.
- Visit Jina AI's API console
- Sign up or log in to your account
- Navigate to the API keys section
- Generate a new API key (copy it immediately as some providers only show it once)
- Save your API key in a secure password manager or encrypted note
2. Connect Your Jina AI API Key on TypingMind
Once you have your Jina AI API key, connecting it to TypingMind to chat with AI is straightforward:
- Open TypingMind in your browser
- Click the "Settings" icon (gear symbol)
- Navigate to "Models" section
- Click "Add Custom Model"
- Fill in the model information:Name:
jina-deepsearch-v1 via Jina AI(or your preferred name)Endpoint:https://deepsearch.jina.ai/v1/chat/completionsModel ID:jina-deepsearch-v1for example (check Jina AI model list)Context Length: Enter the model's context window (e.g., 32000 for jina-deepsearch-v1)
jina-deepsearch-v1https://deepsearch.jina.ai/v1/chat/completionsjina-deepsearch-v1 via Jina AIhttps://www.typingmind.com/model-logo.webp32000 - Add custom headers by clicking "Add Custom Headers" in the Advanced Settings section:Authorization:
Bearer <JINA_API_KEY>:X-Title:typingmind.comHTTP-Referer:https://www.typingmind.com - Enable "Support Plugins (via OpenAI Functions)" if the model supports the "functions" or "tool_calls" parameter, or enable "Support OpenAI Vision" if the model supports vision.
- Click "Test" to verify the configuration
- If you see "Nice, the endpoint is working!", click "Add Model"
3. Start Chatting with Jina AI models
Now you can start chatting with Jina AI models through TypingMind:
- Select your preferred Jina AI model from the model dropdown menu
- Start typing your message in the chat input
- Enjoy faster responses and better features than the official interface
- Switch between different AI models as needed
jina-deepsearch-v1- Use specific, detailed prompts for better responses (How to use Prompt Library)
- Create AI agents with custom instructions for repeated tasks (How to create AI Agents)
- Use plugins to extend Jina AI capabilities (How to use plugins)
- Upload documents and images directly to chat for AI analysis and discussion (Chat with documents)
4. Monitor Your AI Usage and Costs
One of the biggest advantages of using API keys with TypingMind is cost transparency and control. Unlike fixed subscriptions, you pay only for what you actually use. Visit https://jina.ai/api-dashboard/key-manager to monitor your Jina AI API usage and set spending limits.
- Use less expensive models for simple tasks
- Keep prompts concise but specific to reduce token usage
- Use TypingMind's prompt caching to reduce repeat costs (How to enable prompt caching)
- Using RAG (retrieval-augmented generation) for large documents to reduce repeat costs (How to use RAG)
OpenAI: GPT-4o-mini (2024-07-18)Access OpenAI: GPT-4o-mini (2024-07-18) via OpenRouter
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/). Check out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more. #multimodal
OpenAI: GPT-4o-miniAccess OpenAI: GPT-4o-mini via OpenRouter
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/). Check out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more. #multimodal
Google: Gemma 2 27BAccess Google: Gemma 2 27B via OpenRouter
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
Google: Gemma 2 9B (free)Access Google: Gemma 2 9B (free) via OpenRouter
Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class. Designed for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
Google: Gemma 2 9BAccess Google: Gemma 2 9B via OpenRouter
Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class. Designed for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).
Anthropic: Claude 3.5 Sonnet (2024-06-20)Access Anthropic: Claude 3.5 Sonnet (2024-06-20) via OpenRouter
Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at: - Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems) For the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet). #multimodal
Sao10k: Llama 3 Euryale 70B v2.1Access Sao10k: Llama 3 Euryale 70B v2.1 via OpenRouter
Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much better to unique and custom formatting / reply formats. - Very creative, lots of unique swipes. - Is not restrictive during roleplays.
Mistral: Mistral 7B Instruct (free)Access Mistral: Mistral 7B Instruct (free) via OpenRouter
A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to be the latest version.*
Mistral: Mistral 7B InstructAccess Mistral: Mistral 7B Instruct via OpenRouter
A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. *Mistral 7B Instruct has multiple version variants, and this is intended to be the latest version.*
Mistral: Mistral 7B Instruct v0.3Access Mistral: Mistral 7B Instruct v0.3 via OpenRouter
A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. An improved version of [Mistral 7B Instruct v0.2](/models/mistralai/mistral-7b-instruct-v0.2), with the following changes: - Extended vocabulary to 32768 - Supports v3 Tokenizer - Supports function calling NOTE: Support for function calling depends on the provider.
NousResearch: Hermes 2 Pro - Llama-3 8BAccess NousResearch: Hermes 2 Pro - Llama-3 8B via OpenRouter
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
Microsoft: Phi-3 Mini 128K InstructAccess Microsoft: Phi-3 Mini 128K Instruct via OpenRouter
Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. This model is static, trained on an offline dataset with an October 2023 cutoff date.
