# LiteLLM v1.100.0-dev.2

- Product: LiteLLM (https://whatsnew.fyi/product/litellm)
- Vendor: BerriAI
- Date: 2026-08-28
- Version: v1.100.0-dev.2
- Original notes: https://github.com/BerriAI/litellm/releases/tag/v1.100.0-dev.2
- Permalink: https://whatsnew.fyi/product/litellm/releases/v1.100.0-dev.2
- Labels: Pre-release

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Configure deployment caller identity in Prometheus
- **fixed** — Map /v1/messages provider errors before failure logging in OTEL
- **fixed** — Map upstream status codes for providers with no exception_type branch
- **fixed** — Record ownership of streamed responses under managed ids in passthrough
- **fixed** — Encrypt streamed responses ids on /openai/v1/responses and /responses aliases in proxy
- **fixed** — Fail open on response_format instead of dropping it for unregistered models in together_ai
- **fixed** — Honor DATABASE_DISABLE_PREPARED_STATEMENTS in componentized entrypoints in proxy
- **fixed** — Preserve structured output strictness in anthropic-responses
- **fixed** — Resolve hidden aliases for explicit lookup in router
- **fixed** — Keep focus in the add model public name input while typing in UI
- **fixed** — Price 1-hour cache writes on claude-3-haiku and claude-3-opus at 2x input in model_prices
- **fixed** — Keep the caller's Google token on credential-less Vertex passthrough under custom auth in proxy
- **fixed** — Preserve provider access token lifetime in MCP
- **fixed** — Raise bedrock_mantle gpt-5.5 and gpt-5.4 max_input_tokens to 1050000 in model_prices
- **fixed** — Authenticate realtime websocket with Azure AD token when no api-key in azure/realtime
- **fixed** — Map reasoning_effort to reasoning.effort for OpenAI GPT-5.x on Converse in bedrock
- **fixed** — Support credential providers across clients in redis
- **fixed** — Support mode: image_edit in health checks
- **fixed** — Add US data residency uplift to claude-sonnet-4-6 and mythos entries in cost-map
- **fixed** — Raise missing-credential error on /v1/messages passthrough in anthropic

##### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).

**Verify using the pinned commit hash (recommended):**

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.100.0-dev.2
```

**Verify using the release tag (convenience):**

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.100.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.100.0-dev.2
```

Expected output:

```
The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key
```

---
##### What's Changed
* refactor(ui): install the shadcn alert primitive by @yuneng-berri in https://github.com/BerriAI/litellm/pull/38300
* refactor(ui): re-pull label, textarea, separator and skeleton from the registry by @yuneng-berri in https://github.com/BerriAI/litellm/pull/38302
* feat(prometheus): configure deployment caller identity by @mphilippnv in https://github.com/BerriAI/litellm/pull/38221
* test(e2e): let the Together replayed-reasoning case survive a single provider miss by @mateo-berri in https://github.com/BerriAI/litellm/pull/38314
* fix(otel): map /v1/messages provider errors before failure logging by @mateo-berri in https://github.com/BerriAI/litellm/pull/38310
* fix(exceptions): map upstream status codes for providers with no exception_type branch by @mateo-berri in https://github.com/BerriAI/litellm/pull/38318
* fix(passthrough): record ownership of streamed responses under managed ids by @mateo-berri in https://github.com/BerriAI/litellm/pull/38320
* fix(proxy): encrypt streamed responses ids on /openai/v1/responses and /responses aliases by @mateo-berri in https://github.com/BerriAI/litellm/pull/38325
* test(cost-calc): pin the rate fallbacks inside a tiered-pricing tier by @yuneng-berri in https://github.com/BerriAI/litellm/pull/38327
* test(e2e): cover the Bedrock provider-feature cells customers run by @mateo-berri in https://github.com/BerriAI/litellm/pull/38232
* fix(together_ai): fail open on response_format instead of dropping it for unregistered models by @mateo-berri in https://github.com/BerriAI/litellm/pull/38269
* fix(proxy): honor DATABASE_DISABLE_PREPARED_STATEMENTS in componentized entrypoints by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/38363
* fix(anthropic-responses): preserve structured output strictness by @eugene-yao-zocdoc in https://github.com/BerriAI/litellm/pull/38211
* chore(typing): roll up the daily tech debt cleanups from Aug 20 to Aug 26 by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37922
* fix(router): resolve hidden aliases for explicit lookup by @daniel-meismer-zocdoc in https://github.com/BerriAI/litellm/pull/38272
* fix(ui): keep focus in the add model public name input while typing by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/38366
* fix(model_prices): price 1-hour cache writes on claude-3-haiku and claude-3-opus at 2x input by @mateo-berri in https://github.com/BerriAI/litellm/pull/38371
* fix(proxy): keep the caller's Google token on credential-less Vertex passthrough under custom auth by @mateo-berri in https://github.com/BerriAI/litellm/pull/38299
* fix(mcp): preserve provider access token lifetime by @daniel-meismer-zocdoc in https://github.com/BerriAI/litellm/pull/38271
* chore(ui): remove stale "New" badge

_[Truncated at 4000 characters — full notes: https://github.com/BerriAI/litellm/releases/tag/v1.100.0-dev.2]_