LLM7 model guide
n8n with LLM7
Configure n8n with LLM7: eligible models, setup instructions, and a copyable configuration.
Requirements and limitations
This is a settings checklist, not an importable workflow. Agent workflows need a model with tool support. Responses-only built-in tools are unavailable through this configuration.
Setup
- Add an OpenAI Chat Model node to your workflow.
- Create custom OpenAI credentials with the API key and Base URL below.
- Enter the model ID manually if it is absent from the dropdown. Keep Use Responses API disabled.
Credential type: OpenAI
API Key: YOUR_LLM7_API_KEY
Base URL: https://api.llm7.io/v1
Node: OpenAI Chat Model
Model: DeepSeek-V4-Flash-0731
Use Responses API: disabled| Model | Pricing | Context | Tool calling |
|---|---|---|---|
| $0.02 USD input and $0.04 USD output per 1M tokens | 400,000 | Supported | |
| $1.00 USD input and $4.05 USD output per 1M tokens | 512,000 | Not supported | |
| $0.50 USD input and $1.20 USD output per 1M tokens | 512,000 | Supported | |
| $0.04 USD input and $0.05 USD output per 1M tokens | 8,000 | Not supported | |
| $0.40 USD input and $2.00 USD output per 1M tokens | 256,000 | Supported | |
| $1.00 USD input and $3.00 USD output per 1M tokens | 1,024,000 | Supported | |
| $4.50 USD input and $30.00 USD output per 1M tokens | 1,000,000 | Supported | |
| $4.00 USD input and $15.00 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.04 USD input and $0.20 USD output per 1M tokens | 200,000 | Supported | |
| $2.25 USD input and $12.19 USD output per 1M tokens | 1,000,000 | Supported | |
| $2.50 USD input and $12.50 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.12 USD input and $0.45 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.45 USD input and $2.25 USD output per 1M tokens Minimum: $0.000784/request | 1,000,000 | Supported | |
| $0.01 USD input and $0.02 USD output per 1M tokens | 32,000 | Supported | |
| $0.06 USD input and $0.18 USD output per 1M tokens | 1,024,000 | Supported | |
| $0.18 USD input and $0.60 USD output per 1M tokens | 1,000,000 | Supported | |
| $1.11 USD input and $3.33 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.03 USD input and $0.08 USD output per 1M tokens | 1,048,576 | Supported | |
| $0.02 USD input and $0.04 USD output per 1M tokens | 256,000 | Supported | |
| $0.06 USD input and $0.30 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.05 USD input and $0.15 USD output per 1M tokens | 1,000,000 | Supported | |
| gemma4:31b | $0.07 USD input and $0.23 USD output per 1M tokens | 262,000 | Supported |
| $0.50 USD input and $2.00 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.15 USD input and $0.55 USD output per 1M tokens | 1,048,576 | Supported | |
| $0.20 USD input and $1.00 USD output per 1M tokens Minimum: $0.0001/request | 1,050,000 | Supported | |
| $0.45 USD input and $0.58 USD output per 1M tokens | Unknown context | Supported | |
| $1.92 USD input and $5.40 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.24 USD input and $1.00 USD output per 1M tokens | 1,000,000 | Supported | |
| $5.00 USD input and $10.00 USD output per 1M tokens | 1,000,000 | Supported | |
| $0.30 USD input and $1.00 USD output per 1M tokens | 500,000 | Supported | |
| $0.40 USD input and $0.50 USD output per 1M tokens | 500,000 | Supported | |
| $2.00 USD input and $10.00 USD output per 1M tokens | 1,000,000 | Supported | |
| llama-4-maverick | $0.19 USD input and $0.75 USD output per 1M tokens | 1,048,576 | Supported |
| $0.03 USD input and $0.05 USD output per 1M tokens | 180,000 | Supported | |
| $0.03 USD input and $0.03 USD output per 1M tokens | 128,000 | Not supported | |
| $0.06 USD input and $0.08 USD output per 1M tokens | 32,000 | Not supported | |
| $0.10 USD input and $0.40 USD output per 1M tokens | 250,000 | Supported |
Instructions reviewed 2026-09-14. Sources: n8n documentation 1n8n documentation 2
Explore related pages
Model catalogModel comparisonsCapabilitiesIntegrationsCost calculatorsToken calculatorTool calling modelsVision modelsLong context modelsJSON mode modelsStreaming modelsReasoning modelsHermes Agent with LLM7OpenClaw with LLM7LangChain with LLM7Vercel AI SDK with LLM7Customer support cost calculatorDocument processing cost calculator