Integrations

Works with the traces you already have.

No new SDK and nothing in your request path: rightmodeler reads the traces your agent already emits, measures cheaper candidates against accepted outputs, and reports the evidence, sample size, and abstentions.

Reads your traces

Autodetected and folded into one per-step schema.

Claude CodeRun the rightmodeler skill on ~/.claude/projects: it replays every session step through cheaper models and measures each against what you accepted.
Codex CLIRun rightmodeler on Codex sessions to replay each step through cheaper models and judge every output against the result you accepted.
LangSmithExport a LangSmith run tree: rightmodeler replays each step through cheaper models and measures every output against what you accepted.
the OpenAI SDKPoint rightmodeler at your OpenAI SDK request log: it replays every call through cheaper models and measures each output against what you accepted.
LangfuseExport Langfuse observations to disk and rightmodeler replays each step through cheaper models, judging every candidate against the output you already shipped.
BraintrustFetch Braintrust span rows: rightmodeler replays each step through cheaper models and measures every candidate against the output you accepted.
PhoenixExport OpenInference spans from Phoenix: rightmodeler replays each step on cheaper models and measures every output against what you accepted.
OpenTelemetryPoint rightmodeler at OTLP span exports with gen_ai.* attributes. It replays each step on cheaper models and measures candidate agreement with accepted output.

Replays through

Where the candidate calls actually run.

OpenRouterUse one OpenRouter API key to shortlist cheaper models, replay steps at temperature 0, and price every swap with provider-reported usage costs.
LiteLLMReplay your real pipeline through a LiteLLM proxy, let tools and loops run, and use rightmodeler to verify whether each model swap survives.
Vercel AI GatewayUse your Vercel AI Gateway key to discover cheaper candidates live, replay real steps at temperature 0, judge quality, and record provider-reported costs.
RelatedHow it worksReduce LLM costsCompare alternativesGlossary