Langflow logo
Bot builders

Use TokenRex with Langflow

Use TokenRex in Langflow's agent and language-model steps through its OpenAI Compatible provider.

Langflow discovers models from the provider's models endpoint. Enable only models appropriate for the flow: language models for chat/agents, embedding models for retrieval. Tool permissions belong to your Langflow flow. Provider setup checked against the official reference. Live execution inside this third-party tool has not been tested; model limits, streaming and tool behavior must be verified separately.

Before you start

  • Current Langflow with OpenAI Compatible provider
  • A TokenRex API key
  • An enabled chat model

Setup methods

1

Provider setup

  1. 1.

    Install Langflow using https://docs.langflow.org/get-started-installation. The OpenAI Compatible provider is included with current Langflow installations.

  2. 2.

    Create a TokenRex API key, then copy an enabled chat model's exact ID from Models & Pricing. The examples use openai/gpt-6-astra; replace it with your selected ID.

  3. 3.

    Click your profile icon → Settings → Model Providers → OpenAI Compatible.

  4. 4.

    Set Base URL to https://tokenrex.ai/api/public/v1 and API Key to your TokenRex key. Save to validate the connection and discover enabled models. This is the provider base, not the full chat-completions URL.

  5. 5.

    Enable openai/gpt-6-astra, or the exact enabled chat model you chose, under Language Models. In a Language Model or Agent field, select OpenAI Compatible and that model.

  6. 6.

    Save your flow and send a short message in its playground. If model discovery fails, check the saved key and base address before attaching additional tools.

Configuration
text
Provider: OpenAI-compatible
API base URL: https://tokenrex.ai/api/public/v1
API key: <your TokenRex API key>
Model ID: openai/gpt-6-astra
API mode: Chat Completions
Setup reference

Verify the connection

Send a short message with the selected model, read its response, then confirm the exact model appears in your TokenRex usage. Test streaming and tool use separately before larger agent tasks.