The independent audit layer for LLM transit providers. Detect model substitution, compare by price & trust, verify what you actually pay for.
# npm install -g truthprobe-mcp # Add to your AI tool's MCP config: { "mcpServers": { "truthprobe": { "command": "truthprobe-mcp" } } } # Done. Ask your AI: "Is my provider honest?"
Three capabilities that keep your LLM provider accountable.
| # | PROVIDER | HONEST | SPEED | SCORE | Status |
|---|---|---|---|---|---|
| 1 | OR OpenRouter US / Multi-provider | 94 | 88 | 91 | Trusted |
| 2 | CA CloseAI Asia CN / Enterprise | 82 | 86 | 84 | Acceptable |
| 3 | A2 API2D CN / Aggregator | 76 | 82 | 79 | Acceptable |
| 4 | YW 云雾 API CN / Budget | 62 | 76 | 68 | Flagged |
| 5 | V3 V-API (V36) CN / Reseller | 41 | 82 | 48 | Avoid |
Scores based on 100+ automated probes per provider. Updated weekly. Tests funded by TruthProbe.
Passively verify your provider actually serves the model you pay for. Multi-signal detection catches downgrades with zero extra cost to you.
85-97% detection accuracy — Multi-signal detection runs on every request at zero cost to you.
One integration. Both trust verification and cost optimization happen automatically.
What you see after every request:
Both free. MCP for AI coding tools, SDK for Python scripts.
Integrates directly into your AI tool. Zero code changes, continuous monitoring.
The SDK automatically logs every request and builds a full audit report. Zero config, zero cost.
npm install -g truthprobe-mcpAdd truthprobe to your AI tool's MCP settings (Claude Code, Codex CLI, Cursor, Windsurf, Hermes, etc.)
Done! Ask your AI: "Is my provider honest?" — all tools are now available.