> ## Documentation Index > Fetch the complete documentation index at: https://docs.requesty.ai/llms.txt > Use this file to discover all available pages before exploring further. # n8n > Requesty community nodes for n8n: chat models and image generation [n8n](https://n8n.io) is a workflow automation platform where you build AI agents and pipelines visually. The Requesty community node package gives you two nodes: the **Requesty Chat Model** node drives any AI workflow with 300+ models through Requesty's unified gateway, and the **Requesty Image Generation** node creates images from text prompts, all with a single API key. Using the Requesty integration, you can: * Access **300+ models** from OpenAI, Anthropic, Google, Meta, Mistral, Cohere, and many other providers through one API key. * **Generate images** from text prompts, in any workflow or as an AI Agent tool. * Enforce **strict JSON Schema** server side for real structured output, not prompt engineered. * Give the model a **native web search** tool for up to date information. * Tune **reasoning effort** for reasoning capable models. * Apply [fallback policies](/features/fallback-policies), [load balancing](/features/load-balancing-policies), and [latency routing](/features/latency-routing) to keep your workflows responsive. * Track and manage your spend in a single location. ## Prerequisites * A running n8n instance (Cloud or self hosted). * A Requesty API key from the [API Keys page](https://app.requesty.ai/api-keys). ## Installation Follow the [community nodes installation guide](https://docs.n8n.io/integrations/community-nodes/installation/) in the n8n documentation. In your n8n instance, go to **Settings > Community Nodes** and install: ``` @requesty/n8n-nodes-requesty ``` ## Credentials 1. Sign up at [app.requesty.ai](https://app.requesty.ai/sign-up). 2. Generate an API key on the [API Keys page](https://app.requesty.ai/api-keys). 3. In n8n, create a new **Requesty API** credential and paste your key. ## Usage ### Chat models The **Requesty Chat Model** node connects to any model available through Requesty's unified gateway. Use it anywhere n8n accepts a chat model, such as the AI Agent node, Basic LLM Chain, or any AI workflow. Once your API key is saved, the **Model** dropdown auto populates with all available models. You can also set a model ID directly using an expression, for example `anthropic/claude-sonnet-4-6` or `openai/gpt-5.4`. To route through a policy, use the `policy/policy-name` format such as `policy/reliable-coding`. See [Routing Policies](/features/fallback-policies) for how to create a policy that automatically falls back between models. #### Configuration options | Option | Default | Description | | ----------------------- | --------- | ---------------------------------------------------------------------- | | Response Format | Text | Text, JSON Object, or JSON Schema (strict structured output) | | JSON Schema | (example) | The schema the response must match when Response Format is JSON Schema | | Reasoning Effort | Default | Reasoning level (low, medium, high) for reasoning capable models | | Base URL | (gateway) | Override the gateway URL for self hosted Requesty deployments | | Enable Web Search | off | Give the model a native web search tool for up to date information | | Web Search Context Size | medium | How much context the web search retrieves per query | | Sampling Temperature | 0.7 | Controls randomness (0 is deterministic, 2 is very random) | | Maximum Tokens | unlimited | Maximum number of tokens to generate | | Top P | 1 | Nucleus sampling probability mass | | Frequency Penalty | 0 | Penalizes token repetition | | Presence Penalty | 0 | Penalizes already seen tokens | ### Image generation The **Requesty Image Generation** node turns a text prompt into an image using models available through the gateway, such as `azure/openai/gpt-image-1`. Use it as a regular node in any workflow, or attach it to an AI Agent as a tool. By default the node outputs binary image data, so you get a preview right in the n8n output panel and can pass the image to downstream nodes like Write Binary File or HTTP Request. Enable **Return Image URLs** to receive URLs in the JSON output instead. #### Configuration options | Option | Default | Description | | ----------------- | -------------------------- | ---------------------------------------------------------- | | Model | `azure/openai/gpt-image-1` | The model to use for image generation | | Prompt | (required) | A text description of the desired image | | Size | `1024x1024` | Image dimensions: `1024x1024`, `1536x1024`, or `1024x1536` | | Quality | auto | Image quality: auto, high, medium, or low | | Number of Images | 1 | How many images to generate (1 to 10) | | Background | auto | Background type: auto, transparent, or opaque | | Output Format | png | File format: png, jpeg, or webp | | Return Image URLs | off | Return URLs instead of binary image data | | Base URL | (gateway) | Override the gateway URL for self hosted deployments | | Custom Headers | (none) | Extra HTTP headers for tagging and tracking | #### Using image generation as an AI Agent tool The node can act as a tool that an AI Agent calls on its own when a user asks for an image: 1. Set the environment variable `N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true` on your n8n instance. 2. Add the **Requesty Image Generation** node to your workflow. 3. Connect it to the AI Agent's **Tools** input. 4. The agent decides when to generate images and writes the prompt itself. When used as a tool, enable **Return Image URLs** so the agent receives URLs it can reference in its response. ### Key features * **300+ models**: Access models from OpenAI, Anthropic, Google, Meta, Mistral, Cohere, and more. * **Image generation**: Create images from text prompts, in workflows or as an AI Agent tool. * **Responses API**: Built on the Responses API, unlocking richer capabilities than plain chat completions. * **Structured output**: Enforce a strict JSON Schema server side ([structured outputs](/features/structured-outputs)). * **Native web search**: Let the model search the web for current information ([web search](/features/web-search)). * **Reasoning control**: Tune reasoning effort for reasoning capable models ([reasoning](/features/reasoning)). * **Intelligent routing**: Automatic fallbacks and load balancing across providers. * **Self hosted friendly**: Point the nodes at your own Requesty deployment via the Base URL option. ## Verification Add the **Requesty Chat Model** node to a workflow (for example connected to an AI Agent), run it, and confirm you get a response. For images, add the **Requesty Image Generation** node with a prompt and run it, then check the output panel for the image preview. Finally, open the [Requesty analytics dashboard](https://app.requesty.ai/analytics) to confirm the requests were logged. ## Resources * [Requesty community nodes on npm](https://www.npmjs.com/package/@requesty/n8n-nodes-requesty) * [n8n-requesty on GitHub](https://github.com/requestyai/n8n-requesty) * [n8n Community Nodes](https://docs.n8n.io/integrations/community-nodes/installation/) * [Requesty Model Library](https://app.requesty.ai/model-list)