← Back to LLM Wiki
LLM Wiki · Frontier · Closed Weights

Claude

Anthropic's model family — Opus, Sonnet, Haiku — built around Constitutional AI, long-context reasoning, and tool-use reliability.
Claude is the reference model for agentic workloads at Organized AI. The family is organized by capability tier (Opus for depth, Sonnet for balance, Haiku for speed), shares a common tool-use protocol, and supports prompt caching and extended thinking — three features that materially change the unit economics of production agents.
Anthropic 200K–1M ctx Tool Use Prompt Caching Extended Thinking

Quick Facts

Vendor
Anthropic (San Francisco)
Released
Claude 1 (March 2023); Claude 4 family (2025–2026)
Current line
Opus 4.7 · Sonnet 4.6 · Haiku 4.5
License
Proprietary; hosted API only
Hosting
Anthropic API, Amazon Bedrock, Google Vertex AI
Context window
200K tokens standard; 1M tokens on select Opus tiers
Modalities
Text, image (vision), PDF, code
Alignment approach
Constitutional AI / RLHF

Summary

Claude is Anthropic's general-purpose LLM family, launched in 2023 as a direct competitor to OpenAI's GPT series. The defining design choice is Constitutional AI: an alignment technique that trains the model against a written set of principles rather than relying solely on human feedback. In practice this produces a model that refuses fewer legitimate requests, explains its reasoning more readily, and degrades more gracefully on ambiguous edge cases.

For agent infrastructure, three features matter most: (1) structured tool use with a well-defined JSON protocol that agent frameworks can target; (2) prompt caching, which drops the cost of long system prompts and repeated context by up to 90% — turning otherwise uneconomical agent loops into viable workloads; and (3) extended thinking, a reasoning mode that lets the model think before responding, closing the gap with dedicated reasoning models on math and code benchmarks.

Model Lineup

Where Claude Fits

Claude is the default choice when any of the following dominate your requirements: long-running coding agents, multi-step tool loops with strict reliability requirements, or workloads that benefit from prompt caching (long system prompts, RAG pipelines, document-grounded Q&A). The Claude Code CLI and the Claude Agent SDK are built on the same tool-use protocol, so infrastructure built around one transfers cleanly to the other.

Tradeoffs

Deployment Notes

Within the Claw ecosystem, Claude powers the human-facing control plane: Claude Code Slack for operator conversations, Claude Agent SDK for bespoke agent loops, and the observability layer that turns agent traces into KPIs. Open-weights models (Qwen, Llama) handle the high-volume interior loops where self-hosting on Mac Mini edge hardware beats API economics. See The Agent Infrastructure Stack for the full architecture.

References

  1. Anthropic — Claude
  2. Anthropic API Documentation
  3. Constitutional AI: Harmlessness from AI Feedback
  4. The Agent Infrastructure Stack — Organized AI