Akash Chat

Interact with the AkashChat API. AkashChat provides a simple interface to leading open-source AI models powered by the Akash Supercloud. - Akash is a permissionless marketplace for cloud resources with competitive pricing. - The API is easy to use and supports multiple open-source models. - Get your API key at: https://chatapi.akash.network/ - Docs: https://chatapi.akash.network/docs - Community: Akash Discord, GitHub Discussions.

Akash Chat

AI-generated

Overview

The Akash Chat node allows users to interact with the AkashChat API, which provides access to multiple open-source AI language models hosted on the Akash Supercloud. This node sends a user-defined prompt to a selected AI model and returns the generated response.

Common scenarios for this node include:

  • Generating natural language answers or explanations based on user questions.
  • Creating content or text completions using various AI models.
  • Experimenting with different open-source AI models for research or development purposes.

Practical example: A user can input a question like "What is Akash?" and select an AI model such as "Meta Llama 3 8B Instruct" to receive a detailed answer generated by that model.

Properties

Name Meaning
Prompt The prompt or question to send to the selected AI model. Example: "Ask anything... e.g. What is Akash?"
Model Select the AI model to use for generating a response. Options include:
- DeepSeek-R1 (base model)
- DeepSeek-R1-Distill-Llama-70B (Distilled Llama 70B)
- DeepSeek-R1-Distill-Qwen-14B (Distilled Qwen 14B)
- DeepSeek-R1-Distill-Qwen-32B (Distilled Qwen 32B)
- Meta-Llama-3-1-8B-Instruct-FP8 (Meta Llama 3 8B Instruct)
- Meta-Llama-3-2-3B-Instruct (Meta Llama 3 23B Instruct)
- Meta-Llama-3-3-70B-Instruct (Meta Llama 3 70B Instruct)
- Meta-Llama-4-Maverick-17B-128E-Instruct-FP8 (Meta Llama 4 Maverick 17B)
- Qwen3-235B-A22B-FP8 (Qwen3 235B A22B)

Output

The node outputs an array of JSON objects, each containing:

  • model: The AI model used for generating the response.
  • prompt: The original prompt sent to the AI model.
  • response: The textual content generated by the AI model in reply to the prompt.
  • fullResponse: The complete raw response object returned by the AkashChat API, which may contain additional metadata or information beyond the main text response.

The node does not output binary data.

Dependencies

  • Requires an API key credential for authenticating with the AkashChat API.
  • Makes HTTP POST requests to the endpoint: https://chatapi.akash.network/api/v1/chat/completions.
  • Users must obtain an API key from https://chatapi.akash.network/ and configure it in n8n credentials.
  • No other external dependencies are required.

Troubleshooting

  • Common issues:

    • Invalid or missing API key will cause authentication errors.
    • Network connectivity problems may prevent reaching the AkashChat API.
    • Providing an empty prompt may result in an error or no meaningful response.
    • Selecting an unsupported or deprecated model could cause API errors.

  • Error messages:

    • Errors thrown by the API are caught and either cause the node to fail or, if "Continue On Fail" is enabled, return an error message in the output JSON under the error field.
    • Typical error messages relate to authorization failures, invalid parameters, or rate limits.

  • Resolutions:

    • Verify the API key is correctly set and active.
    • Ensure the prompt is not empty.
    • Check network connectivity.
    • Confirm the selected model is valid and supported by the API.

Links and References

Discussion