# LiteLLM CURRENT_STATUS: UNKNOWN OBSERVATION: SPEC_ONLY FRESHNESS: UNKNOWN PAGE_TYPE: reference CANONICAL_URL: /tools/ea-164-litellm CLAIM_IDS: none EVIDENCE_IDS: EVD-EA-164-URL-DAB892839DF4, EVD-EA-164-URL-7A6936DA981A, EA-164-R11-RESEARCH, EA-164-R11-WEB-READBACK UNKNOWN_IDS: EA-164-UNKNOWN-01, EA-164-UNKNOWN-CURRENTNESS OPS_IDS: none ## Summary 「LiteLLMは、Python SDKとProxy Serverを通じて複数LLM providerを共通インターフェースへ寄せ、routing／retry／fallback、認証、ログ、guardrail、spend管理等を提供すると公式リポジトリで説明している。provider互換性、品質、価格、データ処理、fallback安全性はrelease・model・設定単位で再確認する。」 ## Current judgment 1. ESTABLISHED [S1+S2 support]: LiteLLM presents two boundaries: a Python SDK for direct application integration and a Proxy Server described as a central LLM gateway. The repository says both expose a unified interface across multiple LLMs. 2. ESTABLISHED [S1 support]: The repository documents gateway features including authentication/authorization hooks, multi-tenant spend tracking, logging, guardrails, caching, virtual keys, and a Router with retry/fallback across deployments. 3. ESTABLISHED [S1+S3 limit]: Provider/model support is a mutable implementation matrix. A checked cell is not proof that every endpoint, parameter, modality, tool schema, error, streaming mode, or release behaves identically. 4. INFERENCE [S1+S2]: LiteLLM can serve as a policy/normalization control plane, but the normalization boundary may hide provider-specific semantics and does not itself make model output, tool calls, data handling, or fallback outcomes equivalent. ## Scope provider mapping / gateway / implementation / operability / cost / governance / security ## Confirmed - ESTABLISHED [S1+S2 support]: LiteLLM presents two boundaries: a Python SDK for direct application integration and a Proxy Server described as a central LLM gateway. The repository says both expose a unified interface across multiple LLMs. - ESTABLISHED [S1 support]: The repository documents gateway features including authentication/authorization hooks, multi-tenant spend tracking, logging, guardrails, caching, virtual keys, and a Router with retry/fallback across deployments. - ESTABLISHED [S1+S3 limit]: Provider/model support is a mutable implementation matrix. A checked cell is not proof that every endpoint, parameter, modality, tool schema, error, streaming mode, or release behaves identically. - INFERENCE [S1+S2]: LiteLLM can serve as a policy/normalization control plane, but the normalization boundary may hide provider-specific semantics and does not itself make model output, tool calls, data handling, or fallback outcomes equivalent. ## UNKNOWN - EA-164-UNKNOWN-01: current stable release/commit; adapter parity; provider-specific parameter loss; tool/structured-output semantics; retry/fallback duplicate side effects; cache isolation; RBAC/audit/data-residency gates; cost calculation accuracy; public incidents; managed versus OSS feature difference. - EA-164-UNKNOWN-CURRENTNESS: 外部根拠の再確認日がcanonical body/control-planeで確定していないため、currentnessはUNKNOWNとして保持する。日付を推測補完しない。 ## Evidence - EVD-EA-164-URL-DAB892839DF4 (RESEARCH): LiteLLM repository | AUTHOR_ORG: BerriAI / LiteLLM maintainers | CANONICAL_URL: — https://github.com/BerriAI/litellm - EVD-EA-164-URL-7A6936DA981A (RESEARCH): Getting Started / Proxy | AUTHOR_ORG: LiteLLM project | CANONICAL_URL: — https://docs.litellm.ai/docs/ - EA-164-R11-RESEARCH (RESEARCH): EA-164 監査済みresearch / canonical revision binding - EA-164-R11-WEB-READBACK (IMPL): EA-164 Web body identity / canonical readback ## Failure / limits The repository's 100+ provider/API count and feature descriptions are project claims, not independent benchmark evidence. Default branch, stable tags, provider adapters, and upstream APIs change. Retry/fallback can duplicate or alter requests and may change model semantics; compatible request shape does not prove compatible safety, cost, context, tool, or response behavior. No release tag, deployment, or provider API was executed in this packet. ## Failure / limits Do not use LiteLLM's provider count as interoperability proof. Do not state that OpenAI-compatible input/output means equal model behavior, safety, tools, pricing, or SLA across providers. UNIT_CLOSE_STATUS: INDIVIDUAL_BOUNDED_CLOSE / EVIDENCE_RECORDED / UNKNOWN_PRESERVED ## Practice LiteLLM release/tag/container image; Proxy versus SDK; provider adapter/version; model ID and API revision; endpoint/streaming/tool/structured-output support; credentials and secret store; auth/RBAC/virtual-key configuration; routing/fallback/retry policy; spend/rate limits; logging/guardrails/caching; data retention/residency; network egress; license/support/managed contract; audit export. ## Practice Evidence-only desk research. No LiteLLM process, proxy, model provider, key, request, or callback was run. ## Practice No cross-provider compatibility matrix was independently reproduced; no latency, cost, fallback-duplication, tool-call, schema, or safety benchmark was run. ## Practice Treat gateway logs, prompts, outputs, API keys, virtual keys, and provider metadata as sensitive. Audit should retain model/provider selected, all attempts, policy/rate decisions, request correlation, redaction status, token/cost source, and downstream result. Calculate cost at accepted outcome level, not only gateway token estimate. Test timeouts, retry idempotency, provider outage, partial stream, and cache leakage; not measured. ## Practice Future update Work should select one pinned LiteLLM release and two providers, then run a safe read-only TEST_PROFILE for request/response, streaming, tool/schema, timeout/retry, fallback duplication, rate limit, cost attribution, redaction, audit, and provider data policy. Preserve provider-specific failure records rather than collapsing them into the gateway claim. ## WHY_THIS_MATTERS_TO_UPDATE LiteLLM is a candidate self-hosted or managed gateway layer for normalizing multiple provider APIs, routing, fallback, spend, and policy. The update needs release-pinned implementation evidence and must not convert its compatibility table or marketing count into a universal guarantee. ## SCOPE_ROUTING provider mapping / gateway / implementation / operability / cost / governance / security ## CLAIM_OR_RESEARCH_QUESTION What does the author-maintained LiteLLM documentation/repository state about the SDK/proxy boundary, multi-provider normalization, routing/fallback, and gateway controls, and what remains unverified? ## EVIDENCE_TABLE [S1] SOURCE_CLASS: author_maintained_repo | EXACT_TITLE: BerriAI/litellm - LiteLLM repository | AUTHOR_ORG: BerriAI / LiteLLM maintainers | CANONICAL_URL: https://github.com/BerriAI/litellm | PUBLICATION_UPDATE_ACCESS: repository accessed 2026-09-14 00:16 JST | VERSION_RELEASE_TAG: default branch; not pinned; repository advertises stable Docker tag separately | SUPPORTING_LOCATOR: repository getting-started lines 540-549 for Proxy Server versus Python SDK, unified interface, gateway features, Router retry/fallback, and stable-tag note; About lines 750-754 for gateway description | EVIDENCE_LABEL: OSS_PRACTICE + PRODUCT_VOLATILE | RELATION: support for documented implementation surface; limit for mutable branch and provider parity. [S2] SOURCE_CLASS: official_project_docs | EXACT_TITLE: LiteLLM Documentation - Getting Started / Proxy | AUTHOR_ORG: LiteLLM project | CANONICAL_URL: https://docs.litellm.ai/docs/ | PUBLICATION_UPDATE_ACCESS: current documentation accessed 2026-09-14 00:16 JST | VERSION_RELEASE_TAG: current docs; page exposes provider/model examples and config paths but no immutable release pin in this capture | SUPPORTING_LOCATOR: documentation index and proxy guidance for OpenAI-compatible gateway, provider translation, authentication, logging, cost tracking, rate limiting, and guardrails | EVIDENCE_LABEL: VERIFIED_SPEC + PRODUCT_VOLATILE | RELATION: support/context; limit because documented option is not proof of configured deployment. [S3] SOURCE_CLASS: author_maintained_repo | EXACT_TITLE: LiteLLM provider support matrix | AUTHOR_ORG: BerriAI/LiteLLM maintainers | CANONICAL_URL: https://github.com/BerriAI/litellm | PUBLICATION_UPDATE_ACCESS: matrix in repository accessed 2026-09-14 00:16 JST | VERSION_RELEASE_TAG: default branch; support cells are mutable | SUPPORTING_LOCATOR: provider/model capability matrix around repository lines 519-536; treat cells as implementation claims requiring version/provider recheck | EVIDENCE_LABEL: PRODUCT_VOLATILE + OSS_PRACTICE | RELATION: support for existence of a maintained mapping surface; limit/counterevidence to universal compatibility. ## FINDINGS 1. ESTABLISHED [S1+S2 support]: LiteLLM presents two boundaries: a Python SDK for direct application integration and a Proxy Server described as a central LLM gateway. The repository says both expose a unified interface across multiple LLMs. 2. ESTABLISHED [S1 support]: The repository documents gateway features including authentication/authorization hooks, multi-tenant spend tracking, logging, guardrails, caching, virtual keys, and a Router with retry/fallback across deployments. 3. ESTABLISHED [S1+S3 limit]: Provider/model support is a mutable implementation matrix. A checked cell is not proof that every endpoint, parameter, modality, tool schema, error, streaming mode, or release behaves identically. 4. INFERENCE [S1+S2]: LiteLLM can serve as a policy/normalization control plane, but the normalization boundary may hide provider-specific semantics and does not itself make model output, tool calls, data handling, or fallback outcomes equivalent. ## LIMITS / COUNTEREVIDENCE / FAILURE ENVELOPE The repository's 100+ provider/API count and feature descriptions are project claims, not independent benchmark evidence. Default branch, stable tags, provider adapters, and upstream APIs change. Retry/fallback can duplicate or alter requests and may change model semantics; compatible request shape does not prove compatible safety, cost, context, tool, or response behavior. No release tag, deployment, or provider API was executed in this packet. ## AVAILABILITY_GATES LiteLLM release/tag/container image; Proxy versus SDK; provider adapter/version; model ID and API revision; endpoint/streaming/tool/structured-output support; credentials and secret store; auth/RBAC/virtual-key configuration; routing/fallback/retry policy; spend/rate limits; logging/guardrails/caching; data retention/residency; network egress; license/support/managed contract; audit export. ## IMPLEMENTATION_STATE Evidence-only desk research. No LiteLLM process, proxy, model provider, key, request, or callback was run. ## BENCHMARK_OR_EVAL No cross-provider compatibility matrix was independently reproduced; no latency, cost, fallback-duplication, tool-call, schema, or safety benchmark was run. ## SECURITY / PRIVACY / AUDIT / COST / OPERABILITY Treat gateway logs, prompts, outputs, API keys, virtual keys, and provider metadata as sensitive. Audit should retain model/provider selected, all attempts, policy/rate decisions, request correlation, redaction status, token/cost source, and downstream result. Calculate cost at accepted outcome level, not only gateway token estimate. Test timeouts, retry idempotency, provider outage, partial stream, and cache leakage; not measured. ## SAFE_WORDING_FOR_FUTURE_BOOK 「LiteLLMは、Python SDKとProxy Serverを通じて複数LLM providerを共通インターフェースへ寄せ、routing／retry／fallback、認証、ログ、guardrail、spend管理等を提供すると公式リポジトリで説明している。provider互換性、品質、価格、データ処理、fallback安全性はrelease・model・設定単位で再確認する。」 ## UPDATE_WORK_HANDOFF Future update Work should select one pinned LiteLLM release and two providers, then run a safe read-only TEST_PROFILE for request/response, streaming, tool/schema, timeout/retry, fallback duplication, rate limit, cost attribution, redaction, audit, and provider data policy. Preserve provider-specific failure records rather than collapsing them into the gateway claim. ## OPEN_UNKNOWN current stable release/commit; adapter parity; provider-specific parameter loss; tool/structured-output semantics; retry/fallback duplicate side effects; cache isolation; RBAC/audit/data-residency gates; cost calculation accuracy; public incidents; managed versus OSS feature difference. ## STOP_CONDITION Do not use LiteLLM's provider count as interoperability proof. Do not state that OpenAI-compatible input/output means equal model behavior, safety, tools, pricing, or SLA across providers. UNIT_CLOSE_STATUS: INDIVIDUAL_BOUNDED_CLOSE / EVIDENCE_RECORDED / UNKNOWN_PRESERVED ## EVIDENCE PACKET --- NEXT: /agent/start.json STOP: This is a knowledge projection, not an execution order.