--- title: "v1.104.3 - Decisions Providers, SDK and Guardrail" url: "/release_notes/v1.104.3/v1-104-3" canonical_url: "https://docs.litellm.ai/release_notes/v1.104.3/v1-104-3" type: "release-notes" last_updated: "2026-10-12" related: - "/release_notes/v1.105.0/v1-105-0" - "/release_notes/v1.104.2/v1-104-2" --- # v1.104.3 - Decisions Providers, SDK and Guardrail > Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt ## Deploy this version **Docker** ```bash docker run \ -e LITELLM_MASTER_KEY=sk- \ -e DATABASE_URL=postgresql://:@:5432/ \ -e STORE_MODEL_IN_DB=True \ -p 4000:4000 \ docker.litellm.ai/berriai/litellm:1.104.3 ``` **Pip** ```bash pip install litellm==1.104.3 ``` This release is published as [`ghcr.io/berriai/litellm:v1.104.3`](https://github.com/BerriAI/litellm/pkgs/container/litellm). See the [GitHub release](https://github.com/BerriAI/litellm/releases/tag/v1.104.3) and the full [releases page](https://github.com/BerriAI/litellm/releases) :::danger Breaking Changes **Decisions requests that send `safety_identifier` to a provider other than OpenAI now return 400** instead of 200 with the identifier silently dropped. This covers Perplexity, TypeSafe, OpenRouter, Strands Decider and Cloudflare on `/v1/decisions`, `/v1/systemone` and `litellm.decisions()`. Set `drop_params: true` on the deployment, under `litellm_settings`, in the request body or on `litellm.drop_params` to keep the old behavior. `/v1/systemone` requests are also logged with call type `asystemone` instead of `adecisions`. See [PR #44955](https://github.com/BerriAI/litellm/pull/44955) and [PR #45846](https://github.com/BerriAI/litellm/pull/45846) ::: `v1.104.3` is a patch release on top of [`v1.104.2`](/release_notes/v1.104.2/v1-104-2). It backports the Decisions follow-ups from `main`: two more providers, Strands Decider on AgentCore, a `litellm.systemone()` SDK entry point, OpenRouter billing from the cost OpenRouter reports, a decision model guardrail and decision-model Auto Router setup. There are no new database migrations. The `v1.104.3` tag points at [`3645fe0`](https://github.com/BerriAI/litellm/commit/3645fe0a1cada9e3b4f0cbd50d5e1d436d5b21cb) ## Decisions API - **New providers**: `hosted_vllm/` (requires `api_base`, or `HOSTED_VLLM_API_BASE`) and `azure_ai/` for Microsoft-Decision-1, joining OpenAI, Perplexity, TypeSafe, OpenRouter, Cloudflare and Strands Decider. See the [Decisions docs](../../docs/decisions) - **Strands Decider on AgentCore**: a `strands_decider/` deployment whose `api_base` is an AgentCore runtime ARN calls `InvokeAgentRuntime`, signed with the deployment's `aws_*` credentials - **SDK**: the new `litellm.systemone()` takes the System One format and `litellm.decisions()` takes the OpenAI format. `litellm.decisions(state=...)` still works and warns that it is deprecated in favor of `litellm.systemone()` - **`safety_identifier`**: providers that cannot take it return 400 unless `drop_params` drops it. OpenAI keeps passing it through from either route - **Spend tracking**: OpenRouter Decisions calls and the `/openrouter/alpha/decisions` pass-through bill the cost OpenRouter reports in `usage.cost` - **Decision model guardrail**: a new `decision_model` guardrail screens messages and tool-call arguments with admin-written yes/no questions, each set to block or log above its threshold, and is configured from the Admin UI and the Guardrail Garden - **Auto Router**: a new router can use an onboarded decision model deployment as its classifier, and existing router configurations keep working - **Admin UI and docs**: TypeSafe and Strands Decider are in the Add Model provider list, and Swagger UI describes `/v1/decisions` and `/v1/systemone` #### New Model Support (1 new model) | Provider | Model | Context Window | Input ($/1M tokens) | Output ($/1M tokens) | | --- | --- | --- | --- | --- | | Azure AI | `azure_ai/Microsoft-Decision-1` | - | $0.042 | $0.00 | ### What's Changed - Dispatch Decisions through per-provider configs and the shared HTTP handler - [PR #45129](https://github.com/BerriAI/litellm/pull/45129), [PR #45130](https://github.com/BerriAI/litellm/pull/45130), [PR #45442](https://github.com/BerriAI/litellm/pull/45442) - Add the hosted vLLM Decisions provider - [PR #45501](https://github.com/BerriAI/litellm/pull/45501) - Add `azure_ai/Microsoft-Decision-1` and support it on the Decisions API - [PR #45639](https://github.com/BerriAI/litellm/pull/45639), [PR #45673](https://github.com/BerriAI/litellm/pull/45673), [PR #45717](https://github.com/BerriAI/litellm/pull/45717) - Call a Strands Decider on an AgentCore runtime ARN - [PR #45678](https://github.com/BerriAI/litellm/pull/45678) - Add `litellm.systemone()` and keep `litellm.decisions()` to the OpenAI format - [PR #45846](https://github.com/BerriAI/litellm/pull/45846) - Refuse `safety_identifier` on providers that cannot take it unless `drop_params` drops it - [PR #44955](https://github.com/BerriAI/litellm/pull/44955) - Bill OpenRouter Decisions and the Decisions pass-through from `usage.cost` (the Decisions and pass-through billing parts only) - [PR #45640](https://github.com/BerriAI/litellm/pull/45640) - Add TypeSafe and Strands Decider to the Add Model provider list, and describe both Decisions routes in Swagger UI - [PR #45335](https://github.com/BerriAI/litellm/pull/45335), [PR #45838](https://github.com/BerriAI/litellm/pull/45838) - Add the decision model guardrail with an Admin UI flow - [PR #45663](https://github.com/BerriAI/litellm/pull/45663), backported in [PR #45900](https://github.com/BerriAI/litellm/pull/45900), with the Add Guardrail provider list fixed after both backports landed in [PR #45936](https://github.com/BerriAI/litellm/pull/45936) - Pick an onboarded decision model as the Auto Router classifier - [PR #45913](https://github.com/BerriAI/litellm/pull/45913), backported in [PR #45914](https://github.com/BerriAI/litellm/pull/45914) - Rebuild the Admin UI bundle - [PR #45924](https://github.com/BerriAI/litellm/pull/45924) The Decisions follow-ups and the version bump are backported together in [PR #45906](https://github.com/BerriAI/litellm/pull/45906) ## Full Changelog https://github.com/BerriAI/litellm/compare/v1.104.2...v1.104.3 ## Related pages - [v1.105.0](https://docs.litellm.ai/release_notes/v1.105.0/v1-105-0.md) - [v1.104.2](https://docs.litellm.ai/release_notes/v1.104.2/v1-104-2.md)