Dewiar Chat Model icon

Dewiar Chat Model

Universal LLM for working with models from OpenAI, Google, Anthropic and others via Dewiar API
Join our community

Overview

This node integrates with the Dewiar API to provide a universal large language model (LLM) interface supporting multiple AI models from providers like OpenAI, Google, Anthropic, xAI, DeepSeek, and Dewiar itself. It allows users to select a model, configure response creativity (temperature), and set maximum token limits for generated responses. The node is useful for generating AI-driven text completions, chat responses, or other language model outputs in workflows, supporting advanced AI capabilities across various providers through a single interface.

Use Case Examples

  1. Generating creative or precise text completions using OpenAI's GPT-5 models.
  2. Using Anthropic's Claude models for conversational AI tasks.
  3. Accessing Google's Gemini models for advanced language understanding.
  4. Employing xAI's Grok models for specialized AI interactions.

Properties

Name Meaning
Model Selects the AI model to use for response generation from a list of supported models including OpenAI, Anthropic, Google, xAI, DeepSeek, and Dewiar.
Temperature Controls the creativity of the AI response. Lower values produce more predictable outputs, higher values produce more creative outputs.
Max Tokens Sets the maximum number of tokens allowed in the AI-generated response.
Provider API Key (BYOK) Optionally provide your own API key for the selected AI provider instead of using the Dewiar balance.

Output

JSON

  • generations
    • 0
      * text - The generated text response from the AI model.
      * message - The AI message object containing the content and any tool calls.
      * generationInfo
      * finishReason - Reason why the generation stopped (e.g., 'stop').
  • llmOutput
    • usage - Token usage statistics from the API response.
    • model - The model identifier used for generating the response.

Dependencies

  • Dewiar API for AI model interaction

Troubleshooting

  • Ensure the Dewiar API credentials are correctly configured and the base URL is set, as missing or incorrect credentials will cause API call failures.
  • If the API returns an error, check the error message for details; common issues include invalid API keys or exceeding token limits.
  • The node does not support streaming responses; attempting to use streaming features will result in errors.
  • If the response format from the API is invalid or missing expected fields, verify the API service status and request parameters.

Links

Discussion