# LiteLLM v1.98.0-dev.2

- Product: LiteLLM (https://whatsnew.fyi/product/litellm)
- Vendor: BerriAI
- Date: 2026-08-13
- Version: v1.98.0-dev.2
- Original notes: https://github.com/BerriAI/litellm/releases/tag/v1.98.0-dev.2
- Permalink: https://whatsnew.fyi/product/litellm/releases/v1.98.0-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** — Attribute Vertex passthrough batch cost to key/team/tags
- **fixed** — Scope file list pagination cursors to the caller in proxy
- **fixed** — Skip prisma-dependent hooks when no database is attached in proxy
- **fixed** — Report has_more false on caller-scoped file list pages in proxy
- **fixed** — Restore management_v1 query-param validation under fastapi>=0.140.7 in proxy
- **fixed** — Stop /{provider}/v1/files from capturing /openai_passthrough in proxy
- **fixed** — Keep batch fallbacks inside the model group that owns the file in router
- **added** — Configure provisioned-throughput flat cost on a model deployment
- **fixed** — Enable native structured output for GLM 5 and DeepSeek V3.2 in bedrock
- **added** — Daily rollup writes per-model PTU flat cost by active hour
- **added** — Add opt-in session_id and trace_id correlation to JSON log records via contextvars
- **added** — Surface PTU flat cost on the daily activity read path
- **added** — Add per-deployment allowed_fails_policy and cooldown_time override support in router
- **added** — Add PTU inputs to the model form and flat cost to the Usage page
- **fixed** — Price dict-shaped image input token details at the image rate in cost
- **fixed** — Refresh deprecation dates, correct xAI pricing and add missing provider models
- **added** — Gate PTU flat-cost attribution behind an opt-in env var
- **added** — Configurable estimated output tokens per key, team and model in rate limiting
- **fixed** — Hide admin-only Logs tabs from roles that cannot call their endpoints in UI
- **fixed** — Gate policy and prompt lookups on an admin capability in UI

##### 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:v1.98.0-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/v1.98.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.98.0-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(batches): attribute Vertex passthrough batch cost to key/team/tags by @yucheng-berri in https://github.com/BerriAI/litellm/pull/34456
* docs: rewrite the CLAUDE.md comment rule with explicit exceptions by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36301
* fix(proxy): scope file list pagination cursors to the caller by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36093
* fix(proxy): skip prisma-dependent hooks when no database is attached by @mateo-berri in https://github.com/BerriAI/litellm/pull/36273
* fix(proxy): report has_more false on caller-scoped file list pages by @mateo-berri in https://github.com/BerriAI/litellm/pull/36326
* fix(proxy): restore management_v1 query-param validation under fastapi>=0.140.7 by @HuanQian571 in https://github.com/BerriAI/litellm/pull/35773
* fix(proxy): stop /{provider}/v1/files from capturing /openai_passthrough by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36092
* chore(typing): remove 914 basedpyright Any errors across 16 hotspot files by @mateo-berri in https://github.com/BerriAI/litellm/pull/36386
* fix(router): keep batch fallbacks inside the model group that owns the file by @mateo-berri in https://github.com/BerriAI/litellm/pull/36181
* feat(ptu): configure provisioned-throughput flat cost on a model deployment by @yucheng-berri in https://github.com/BerriAI/litellm/pull/35341
* docs: clarify the CLAUDE.md comment exceptions are any-of by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36421
* docs: replace the Changes PR template section with Caveats by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36423
* fix(bedrock): enable native structured output for GLM 5 and DeepSeek V3.2 by @alexshtf in https://github.com/BerriAI/litellm/pull/35669
* feat(ptu): daily rollup writes per-model PTU flat cost by active hour by @yucheng-berri in https://github.com/BerriAI/litellm/pull/35343
* feat(logging): add opt-in session_id and trace_id correlation to JSON log records via contextvars by @deepanshululla in https://github.com/BerriAI/litellm/pull/34418
* feat(ptu): surface PTU flat cost on the daily activity read path by @yucheng-berri in https://github.com/BerriAI/litellm/pull/35391
* feat(router): add per-deployment allowed_fails_policy and cooldown_time override support by @deepanshululla in https://github.com/BerriAI/litellm/pull/34416
* feat(ptu): add PTU inputs to the model form and flat cost to the Usage page by @yucheng-berri in https://github.com/BerriAI/litellm/pull/35393
* fix(cost): price dict-shaped image input token details at the image rate by @vairodp in https://github.com/BerriAI/litellm/pull/33490
* fix(model_prices): refresh deprecation dates, correct xAI

_[Truncated at 4000 characters — full notes: https://github.com/BerriAI/litellm/releases/tag/v1.98.0-dev.2]_