⌘K

Llm

Tag

4 integrations tagged with "llm"

Workflow

Action

AI Prompt

Prompt an AI model with custom instructions and optional context data via OpenRouter (GPT-4, Claude, Llama, etc.). Supports structured JSON output with schema enforcement via OpenRouter (best with OpenAI models). Pass in data from previous workflow steps as context. Ideal for: AI-driven decisions, data analysis, content generation, automated reasoning in workflows.

7 workflows

44k runs

100% success

ai llm chat+5

Type:ai-llm-chat

Fields:8 (1 required)

Action

List AI Models

List AI models available via OpenRouter (Anthropic, OpenAI, Google, Meta, DeepSeek, etc.) with context window and USD pricing per 1M tokens. Supports an optional search filter on id/name. Ideal for: discovering valid 'model' values for the AI Prompt action, comparing model pricing.

ai llm openrouter+2

Type:openrouter-list-models

Fields:1 (0 required)

Action

AI Market Sentiment

Classify a short text's sentiment toward a specific asset — a crypto coin OR a US stock ticker — with live market context (price, trend, crypto Fear & Greed, equity/cashtag identity) gathered automatically so the model resolves market-native rhetoric — 'inverse BTC', contrarian/fade language, cashtag proxies — against actual market direction. Subjects resolve via CoinGecko (crypto) with a Finnhub equity fallback for tickers like AAPL/NVDA. Runs on Caddie's task-graph runtime; the action is a signed proxy. Single LLM call, fixed structured output. Ideal for: tweet/headline-triggered trading workflows, sentiment-based alerts, contrarian signal detection. Drop-in replacement for an AI Prompt node doing sentiment classification — the failure mode it fixes is the model never seeing market state.

ai llm sentiment+6

Type:ai-market-sentiment

Fields:9 (2 required)

Action

Chat with NanoChat LLM (d32 Model)

Stream real-time responses from NanoChat, a 32-layer transformer language model built by Andrej Karpathy in 2025. Access this lightweight LLM via the NanoBrain platform for conversational AI tasks with streaming token-by-token output. | Input: Accepts an empty request body (no parameters required) to initiate a chat session | Output: Returns streaming server-sent events (SSE) with token-by-token text generation from the NanoChat d32 model, including model identification and completion markers | Use cases: I want to chat with a lightweight language model for quick responses; Get streaming AI responses for conversational tasks; I need to integrate a compact LLM into my application; Generate text responses using the NanoChat d32 model | Cost: 0.01 USDC on base

x402 payment-gated ai+7

Type:x402ep_d5s9k9smd1grabgljr70

Fields:1 (1 required)

Status unavailable

DocsTermsPrivacy