AutomationFlowsAI & RAG › High-speed AI Chat with Openai's Gpt-oss-120b Model via Cerebras Inference

High-speed AI Chat with Openai's Gpt-oss-120b Model via Cerebras Inference

ByAitor | 1Node @aitoralonso on n8n.io

This n8n workflow provides seamless integration with Cerebras' high-performance inference platform to leverage OpenAI's open-source GPT-OSS-120B model. With industry-leading speeds of thousands of tokens per second and ultra-low latency under 0.5 seconds, this template enables…

Chat trigger trigger★★☆☆☆ complexityAI-powered6 nodesChat TriggerHTTP Request
AI & RAG Trigger: Chat trigger Nodes: 6 Complexity: ★★☆☆☆ AI nodes: yes Added:

This workflow corresponds to n8n.io template #7651 — we link there as the canonical source.

This workflow follows the Chat Trigger → HTTP Request recipe pattern — see all workflows that pair these two integrations.

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

Download .json
{
  "id": "fFKIMw0PeIP2TuOx",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "cerebras with gpt oss 120b",
  "tags": [],
  "nodes": [
    {
      "id": "dc93a613-c19f-4dd4-b633-a1112970455d",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        208,
        0
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.3
    },
    {
      "id": "a941ace5-5a7e-495a-a37d-8dee620f2bb5",
      "name": "Return Output",
      "type": "n8n-nodes-base.set",
      "position": [
        880,
        0
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "409dd10e-b29c-4fac-b471-3204a46034a1",
              "name": "output",
              "type": "string",
              "value": "={{ $json.choices[0].message.content }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "849f0355-d1e5-475c-bc1b-1fdd6c693745",
      "name": "Set API Key",
      "type": "n8n-nodes-base.set",
      "position": [
        432,
        0
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "f828da75-ee7e-482b-83e5-123005f9878d",
              "name": "apiKey",
              "type": "string",
              "value": "your-api-key"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "1f1590ef-2682-40cc-9e5f-447a2513dcc0",
      "name": "Cerebras endpoint",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        656,
        0
      ],
      "parameters": {
        "url": "https://api.cerebras.ai/v1/chat/completions",
        "method": "POST",
        "options": {
          "redirect": {
            "redirect": {}
          }
        },
        "jsonBody": "={\n  \"model\": \"gpt-oss-120b\",\n  \"stream\": false,\n  \"messages\": [\n    {\n      \"content\": \"{{ $('When chat message received').item.json.chatInput }}\",\n      \"role\": \"user\"\n    }\n  ],\n  \"temperature\": 0,\n  \"max_completion_tokens\": -1,\n  \"seed\": 0,\n  \"top_p\": 1\n}",
        "sendBody": true,
        "sendHeaders": true,
        "specifyBody": "json",
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $json.apiKey }}"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "9eb60d7e-b40e-4e26-87ce-000e99c45985",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        384,
        -144
      ],
      "parameters": {
        "width": 192,
        "height": 304,
        "content": "## Set API key \n**Create an account and [get your Cerebras key](https://cerebras.ai)**"
      },
      "typeVersion": 1
    },
    {
      "id": "4eba1448-d1eb-4ceb-85df-de10a942a91a",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        592,
        176
      ],
      "parameters": {
        "width": 272,
        "height": 240,
        "content": "## Parameters\nSet your endpoint parameters as needed\n- temperature\n- completion tokens\n- top P\n- reasoning effort\n\n[Review the endpoint](https://inference-docs.cerebras.ai/api-reference/chat-completions)"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "4a9e3b9f-4132-4871-b159-6c0663bcb49d",
  "connections": {
    "Set API Key": {
      "main": [
        [
          {
            "node": "Cerebras endpoint",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Cerebras endpoint": {
      "main": [
        [
          {
            "node": "Return Output",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "Set API Key",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

This n8n workflow provides seamless integration with Cerebras' high-performance inference platform to leverage OpenAI's open-source GPT-OSS-120B model. With industry-leading speeds of thousands of tokens per second and ultra-low latency under 0.5 seconds, this template enables…

Source: https://n8n.io/workflows/7651/ — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

AI & RAG

Transform your creative pipeline by letting n8n call OpenAI ImageGen1’s _edit image_ endpoint, automatically replacing or augmenting parts of any image you supply and returning a brand-new version in

HTTP Request, Chat Trigger
AI & RAG

This workflow allows users to ask portfolio-related questions in a simple format (). It validates the input, fetches client data and holdings from Google Sheets, retrieves live market prices via API,

Chat Trigger, Google Sheets, HTTP Request +2
AI & RAG

This workflow is for: People who want to quickly launch simple landing pages without paying monthly fees to landing page creators. It’s ideal for rapid prototyping, generation of large amounts of land

Google Gemini, OpenAI, Chat Trigger +3
AI & RAG

This n8n template demonstrates how to automatically download an Instagram Reel, analyze its content using AI video understanding, and regenerate a similar video using AI video generation models. The w

Chat Trigger, HTTP Request
AI & RAG

Automate the creation of high-performing YouTube Shorts in minutes! Content Creators: Generate engaging short videos effortlessly. Marketing Agencies: Produce client-ready content quickly. Business Ow

Chat Trigger, HTTP Request, OpenAI