# LiteLLM v1.99.0-dev.2

- Product: LiteLLM (https://whatsnew.fyi/product/litellm)
- Vendor: BerriAI
- Date: 2026-08-21
- Version: v1.99.0-dev.2
- Original notes: https://github.com/BerriAI/litellm/releases/tag/v1.99.0-dev.2
- Permalink: https://whatsnew.fyi/product/litellm/releases/v1.99.0-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'.

---

- **fixed** — Log spend for OpenAI passthrough embeddings with unmapped models
- **fixed** — Keep acreate_file fallbacks inside the requested model group
- **fixed** — Record estimated input tokens in spend logs for failed dispatched requests
- **fixed** — Accept bool thinking param instead of crashing with AttributeError
- **changed** — Migrate the teams form graph off antd Form onto react-hook-form
- **fixed** — Restore the cache control Role and Index field hints
- **added** — Add mounted-field projections for the MCP server form graph
- **changed** — Extract the MCP server edit save payload into a pure builder
- **changed** — Port the create key form off antd Form onto react-hook-form
- **changed** — Port the add model form off antd Form onto react-hook-form
- **changed** — Port the KeyLifecycleSettings tests onto react-hook-form
- **fixed** — Rebuild nested and list paths in the mounted-field projection
- **fixed** — Gate the pass-through guardrail field inputs when the section is disabled
- **fixed** — Read through to the DB on registry misses so just-created models, guardrails, and agents resolve on sibling replicas
- **fixed** — Forward the per-server auth header on OpenAPI tool calls
- **added** — Add lifecycle timestamps to spend logs
- **changed** — Migrate the antd Button call sites onto the shadcn Button
- **changed** — Give the rollup a source-agnostic deployment record
- **changed** — Scope shadow eval jobs to multiple keys

##### 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:v1.99.0-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/v1.99.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.99.0-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
* fix(proxy): log spend for OpenAI passthrough embeddings with unmapped models by @mateo-berri in https://github.com/BerriAI/litellm/pull/37425
* fix(router): keep acreate_file fallbacks inside the requested model group by @mateo-berri in https://github.com/BerriAI/litellm/pull/37424
* fix(proxy): record estimated input tokens in spend logs for failed dispatched requests by @mateo-berri in https://github.com/BerriAI/litellm/pull/37365
* fix: accept bool thinking param instead of crashing with AttributeError by @mateo-berri in https://github.com/BerriAI/litellm/pull/37423
* refactor(ui): migrate the teams form graph off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37417
* fix(ui): restore the cache control Role and Index field hints by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37437
* feat(ui): add mounted-field projections for the MCP server form graph by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37440
* refactor(ui): extract the MCP server edit save payload into a pure builder by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37436
* test: derive vertex batch cost expectation from the cost map by @mateo-berri in https://github.com/BerriAI/litellm/pull/37444
* refactor(ui): port the create key form off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37442
* refactor(ui): port the add model form off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37446
* refactor(ui): host KeyLifecycleSettings tests in react-hook-form instead of antd Form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37449
* fix(ui): rebuild nested and list paths in the mounted-field projection by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37450
* fix(ui): gate the pass-through guardrail field inputs when the section is disabled by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37435
* fix(tests): keep a host PROXY_BASE_URL out of request-derived URL tests by @mateo-berri in https://github.com/BerriAI/litellm/pull/37451
* refactor(ui): port the MCP server forms off antd Form onto react-hook-form by @yuneng-berri in https://github.com/BerriAI/litellm/pull/37483
* test(e2e): pin the tag-routing denial to its actual cause by @mateo-berri in https://github.com/BerriAI/litellm/pull/37432
* fix(proxy): read through to the DB on registry misses so just-created models, guardrails, and agents resolve on sibling replicas by @mateo-berri in https://github.com/BerriAI/litellm/pull/36263
* fix(mcp): forward the per-server auth header on OpenAPI tool calls by @tin-berri in https://github.com/BerriAI/litellm/pull/37410
* chore(typing): drop 1.3k basedpyright errors across 42 Any

_[Truncated at 4000 characters — full notes: https://github.com/BerriAI/litellm/releases/tag/v1.99.0-dev.2]_