Configure and send prompts to OpenRouter models as a subagent, with reasoning controls, temperature, and optional multi-model Fusion synthesis.
MIT
622,051 tools. Updated 2026-09-29 17:22
"OpenRouter thinking or reasoning capabilities" matching MCP tools:
- Replace a previous thought with updated reasoning, preserving the original in revision history. Corrects incomplete or wrong thinking.MIT
- Toggle ask-fable reasoning-trace capture and live thinking at runtime. Persist trace_mode (full/safe) and stream_reasoning settings without editing config files or restarting.MIT
- List available models, default selections, reasoning capabilities, and active backend status to choose the right configuration for your requests.MIT
- Break down complex problems into structured reasoning steps to track thinking, expected outcomes, and next actions for systematic problem-solving.MIT
- Classify prompt complexity to select the optimal model tier and thinking effort, returning tier, effort, suggested model, confidence, and reasoning.MIT
Matching MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables multi-step AI reasoning by sending prompts to OpenRouter, performing a verification pass, and returning both responses with provider reasoning fields when available.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.62 npm1MIT
Matching MCP Connectors
OpenRouter Models MCP.
Deterministic company, entity and location lookups for agents - per call, x402 or API key.
- Execute complex reasoning tasks using high-performance models for analytical responses.MIT
- Send a design prompt to a specific model via OpenRouter, using either an OpenRouter model ID or a Design Arena model name.MIT
- Initiate structured reasoning sessions to analyze problems through sequential thinking steps, enabling systematic problem-solving with revision capabilities.MIT
- Retrieve full details for a specific language model by ID, name, or OpenRouter ID. Use it to inspect model capabilities before routing tasks.MIT
- Extract reasoning and thinking steps from a trace by matching tool names or content. Use a trace_id to retrieve only the reasoning chain.MIT
- List available image generation models from OpenRouter with pricing and capabilities. Filter by substring on model ID or name.MIT
- Generate AI responses by combining DeepSeek's reasoning with Claude's generation through OpenRouter, maintaining conversation context for enhanced interactions.MIT
- Run advanced reasoning queries with Perplexity using Claude Opus 4.8 extended thinking. Requires Max subscription, uses 1 Pro search credit.MIT
- Find OpenRouter models by keyword, provider, or capabilities. Filter results to locate AI models supporting vision, audio, or video.Apache 2.0
- Break down complex problems into manageable steps, revise reasoning as understanding deepens, and explore alternative paths through structured sequential thinking.-
- Force update the model cache from OpenRouter to retrieve the most current model details, pricing, and capabilities.-
- Perform deep reasoning and complex analysis by automatically routing to optimal AI capabilities for multi-step problem-solving and research questions.-
- Set up your OpenRouter API key to enable image generation and editing capabilities using the Gemini 2.5 Flash Image model.-
- Generate sequential reasoning chains to structure complex thinking processes by breaking topics into logical steps for clearer analysis.MIT
- Apply a 9-step reasoning framework to systematically analyze complex problems, breaking them down with structured logical thinking and methodical approaches for clear solutions.MIT