The request names Claude Opus 4.6, so the product itself comes first: Anthropic's model is served by Replicate 1 (action anthropic/claude-opus-4.6 11) and OpenRouter 3 lists Claude models via tool calling and structured outputs 13, while Anthropic's own site and Claude API reference 212 cover the official route. Alternatives for calling the model are the AI SDK's Anthropic provider 10 and the Claude Agent SDK via OpenClaw Direct 414.
- 1
- 2
Replicatereplicate.comverified and signed
Hosts Anthropic's Claude Opus 4.6 as a runnable model through its cloud API, with the action anthropic/claude-opus-4.6 described as Anthropic's most intelligent model for coding, reasoning and agentic work 11.
for agents: anthropic/claude-opus-4.6
- 3
OpenRouteropenrouter.aiverified and signed
A unified interface that routes requests to Claude and other models, with tool calling and structured JSON outputs 13.
for agents: tool-calling · tool-calling · structured-outputs
- 4
AI SDK Anthropicai-sdk.devverified and signed
The Vercel AI SDK's official Anthropic provider (@ai-sdk/anthropic) for calling Claude models from TypeScript apps 10.
official:SDK · @ai-sdk/anthropic
for agents: ai
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 2Home \ Anthropicanthropic.com · read 2026-10-29
- 3OpenRouteropenrouter.ai · read 2026-10-29
- 4Fully Managed OpenClaw Hosting — AI Assistant — OpenClaw.Directopenclaw.direct · read 2026-10-29
- 10AI SDKai-sdk.dev · read 2026-10-29
- 11anthropic/claude-opus-4.6: declares "anthropic/claude-opus-4.6" (the record we read and signed)unfragile.ai · read 2026-10-24
- 12claude-api: declares "claude-api" (the record we read and signed)unfragile.ai · read 2026-10-24
- 13Anthropic: Claude Opus 4.6 (batch): declares "tool-calling" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14teams-anthropic-integration: declares "teams-anthropic-integration" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
anthropic/claude-opus-4.6 · anthropic/claude-opus-4.6 verified and signed
Anthropic's most intelligent model with state-of-the-art coding, reasoning, and agentic capabilities
anthropic/claude-sonnet-4.6 · anthropic/claude-sonnet-4.6 verified and signed
Claude Sonnet 4.6 from Anthropic: a full upgrade to coding, computer use, long-context reasoning, agent planning, knowledge work, and design, with a 1 million token context window in beta.
claude-api · claude-api verified and signed
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any fo
anthropic/claude-opus-4.7 · anthropic/claude-opus-4.7 verified and signed
Anthropic's most capable model with a step-change improvement in agentic coding, better vision, and stronger multi-step reasoning
tool-calling · Anthropic: Claude Opus 4.6 (batch) verified and signed
Can call tools (function calling).
anthropic · claude-agent-sdk verified and signed
anthropic/claude-4.5-sonnet · anthropic/claude-4.5-sonnet verified and signed
Claude Sonnet 4.5 is the best coding model to date, with significant improvements across the entire development lifecycle
tool-calling · Anthropic: Claude Opus Latest verified and signed
Can call tools (function calling).
teams-anthropic-integration · teams-anthropic-integration verified and signed
Use @youdotcom-oss/teams-anthropic to add Anthropic Claude models (Opus, Sonnet, Haiku) to Microsoft Teams.ai applications. Optionally integrate You.com MCP server for web search and content extraction.
tool-calling · Anthropic: Claude Opus 4.5 verified and signed
Can call tools (function calling).
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.