Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.spojit.com/llms.txt

Use this file to discover all available pages before exploring further.

Spojit uses two kinds of models:
  • Chat / agent models power agent mode in connector nodes and the AI chat sidebar.
  • Embedding models turn documents into vectors so the Knowledge feature can do semantic search.
You can choose which model to use per connector node and per knowledge collection, or leave the defaults.

Chat / agent models

Anthropic Claude

ModelContextStrengthsNotes
Claude Opus 4.71M tokensTop-tier reasoning, tool use, multi-step problem solvingLatest Claude release. Recommended for complex workflows.
Claude Opus 4.61M tokensSame Opus-class capability as 4.7Current default for new workflows. Previous-generation Opus.
Claude Opus 4.5200K tokensEarlier Opus generationKept available for comparison; you generally want 4.6 or 4.7.
Claude Sonnet 4.61M tokensBalanced quality and speed at lower cost than OpusGood middle-ground for high-throughput agent steps.
Claude Haiku 4.5200K tokensFastest and lowest cost in the Claude familyBest for simple steps, lookups, and high-volume runs.

Google Gemini

ModelContextStrengthsNotes
Gemini 3.1 Pro2M tokensLargest context window; strong reasoningCurrently in preview — capabilities may change.
Gemini 2.5 Pro1M tokensStrong general-purpose reasoningStable alternative to Claude Opus when you prefer Google.
Gemini 2.5 Flash1M tokensVery fast and very low costBest for high-volume simple steps.

Embedding models

Embedding models convert text into high-dimensional vectors that capture semantic meaning. Spojit uses them whenever you upload a document to a Knowledge collection — and again at query time so the same vector space is used for search.
ModelDimensionsStrengthsNotes
Gemini Embedding 0013072Higher-quality semantic search; best recall on nuanced queriesDefault for new collections. Higher cost per token.
Text Embedding 004768Faster and much cheaper per tokenGood choice for high-volume document ingestion when peak quality isn’t required.
Both models support documents up to about 2,000 tokens per chunk — Spojit handles the chunking automatically during upload.
Once a collection is created with a given embedding model, every document and query in that collection must use the same model — vectors from different models aren’t comparable. Choose your embedding model when you create the collection.

Where model selection appears

Connector nodes (agent mode)

When configuring a connector node in agent mode, the Model dropdown in the properties panel lets you pick which model runs that step. If you don’t select one, the default model is used. Each connector node can use a different model — you’re not locked into one choice for the entire workflow.

Chat sidebar

The chat sidebar has a model picker in the header bar. Select a model from the dropdown to change which model powers your chat session. Your selection persists across page reloads.

Choosing a model

  • Start with the default. Claude Opus 4.6 is a strong all-rounder and a good starting point for most workflows.
  • Reach for Opus 4.7 for the hardest reasoning steps — multi-tool chains, ambiguous instructions, or long-context tasks.
  • Use Sonnet 4.6 or Gemini 2.5 Flash for high-throughput steps where cost and latency matter more than peak reasoning quality.
  • Use Haiku 4.5 for the simplest steps — short lookups, classification, simple formatting.
  • Mix models in a single workflow. Different steps can use different models — pick the right tool for each step rather than committing to one model for the whole flow.