External Model - Language Model - Claude

🛠

Frontier Text Reasoning via Anthropic's Claude Models

Read, reason over, or write text inside a CNAPS Studio flow with Anthropic's Claude family — Opus for frontier reasoning and complex agentic workflows, Sonnet as the balanced everyday default, Haiku for fast, economical tasks. Runs on Anthropic's servers via API.

🔑 Requires a Anthropic API key

Click to use Claude on CNAPS Studio

What it does

This node connects your CNAPS Studio flows to Anthropic's Claude large language models through the Anthropic API. Use it whenever a flow needs a model to read, reason over, or write text — interpreting the output of a vision model, drafting or enhancing prompts for image/video generators, summarizing, translating, or restructuring data. Because these run on Anthropic's servers, you get frontier general-purpose reasoning without hosting a model locally.

Problem it solves

• Frontier reasoning without infrastructure — No local GPU or weights; the node calls Anthropic's hosted models directly.
• Three clear tiers — Opus (deepest reasoning, agentic workflows), Sonnet (balanced speed/quality default), Haiku (fast and economical) — swap tiers without changing your flow.
• Glue between vision and generation nodes — Turn raw model output into readable reports, or expand simple text into detailed generation prompts.

Which tier to pick

Reach for an opus tier for the hardest multi-step reasoning, math, coding, and complex agentic workflows; claude-sonnet as the balanced everyday default; and haiku when speed and cost matter more than depth on simple tasks.

Configuring the Node

Basic Settings

Model name

System prompt or instruction — Tell the model how to behave. Examples:

• "Summarize the detection results in 2-3 sentences."
• "Convert these labels into a product description."
• "Translate the following text to French."

Advanced Options

Maximum tokens to generate (default: 2048)

• Controls response length. Increase for longer outputs.

Sampling temperature (default: 0.7, range: 0.0–1.0)

• Lower (0.0–0.3): Focused, consistent responses
• Higher (0.7–1.0): Creative, varied responses

Use Cases

Direction 1: Vision Model → Language Model (Analysis)

Best when vision output is complex or needs interpretation.

Example: Scene Segmentation → Report

Input - Image → Scene Segmentation (MaskFormer) → Language Model → Output - Text Viewer

System prompt:

Convert this segmentation data into a structured scene report. Include: 1) Setting type, 2) People count, 3) Key objects detected, 4) Overall scene summary. Use plain language, not raw data.

Direction 2: Language Model → Image Generation (Prompt Enhancement)

Input - Text Input → Language Model → Image Generation (Z-Image-Turbo) → Output - Image Viewer

System prompt:

You are an expert image prompt engineer. Transform the user's simple description into a detailed, vivid prompt optimized for AI image generation. Include: subject details, setting/environment, lighting, artistic style, mood/atmosphere, and composition. Output only the enhanced prompt, nothing else.

How Claude compares

Claude is one of three external LLM options in CNAPS Studio:

Compliance & Provenance

For more on how we classify models and mark outputs, see our AI Policy.

Run it now

Click to use ChatGPT