chore(prices): sync Vertex AI prices: 14 models by berriai-litellm-provider-info-sync[bot] · Pull Request #40955 · BerriAI/litellm

berriai-litellm-provider-info-sync · 2026-09-13T04:55:41Z

Updates 14 models, each read from its provider's own published prices.

OpenAI

No price changes; listed for what its tick could not apply.

Skipped by the parser (7)

gpt-6-astra: long-context prices present but the row states no threshold
gpt-5.6-sol: long-context prices present but the row states no threshold
gpt-5.6-terra: long-context prices present but the row states no threshold
gpt-5.6-luna: long-context prices present but the row states no threshold
sora-2-pro 1024p: size variant has no litellm key stated on the page
sora-2-pro 1080p: size variant has no litellm key stated on the page
ft:o4-mini-2025-04-16: data-sharing discount has no litellm key

Together AI

No price changes; listed for what its tick could not apply.

Skipped by the parser (98)

Prism-ML/Ternary-Bonsai-27B: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/meta/llama-3.2-11b-vision-instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/meta/llama-3.2-90b-vision-instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/mistralai/mixtral-8x22b-instruct-v01: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/meta/llama-3.3-70b-instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/nvidia/llama-3.1-nemotron-70b-instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/meta/llama-3.1-8b-instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/meta/llama-3.1-70b-instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/nv-mistralai/mistral-nemo-12b-instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/mistralai/mixtral-8x7b-instruct-v01: no serverless token price (pricing.input and pricing.output are 0 or absent)
nim/nvidia/llama-3.3-nemotron-super-49b-v1: no serverless token price (pricing.input and pricing.output are 0 or absent)
google/gemma-3-27b-it: no serverless token price (pricing.input and pricing.output are 0 or absent)
meta-llama/Llama-2-7b-chat-hf: no serverless token price (pricing.input and pricing.output are 0 or absent)
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B: no serverless token price (pricing.input and pricing.output are 0 or absent)
google/gemma-3-1b-it: no serverless token price (pricing.input and pricing.output are 0 or absent)
google/gemma-3-4b-it: no serverless token price (pricing.input and pricing.output are 0 or absent)
deepcogito/cogito-v1-preview-llama-8B: no serverless token price (pricing.input and pricing.output are 0 or absent)
deepcogito/cogito-v1-preview-qwen-32B: no serverless token price (pricing.input and pricing.output are 0 or absent)
deepcogito/cogito-v1-preview-qwen-14B: no serverless token price (pricing.input and pricing.output are 0 or absent)
deepcogito/cogito-v1-preview-llama-70B: no serverless token price (pricing.input and pricing.output are 0 or absent)
deepcogito/cogito-v1-preview-llama-70B-Turbo: no serverless token price (pricing.input and pricing.output are 0 or absent)
meta-llama/Llama-3.3-70B-Instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-32B: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-72B: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-3B-Instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-1.5B-Instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-14B: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-7B: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-1.5B: no serverless token price (pricing.input and pricing.output are 0 or absent)
meta-llama/Meta-Llama-3.1-70B: no serverless token price (pricing.input and pricing.output are 0 or absent)
meta-llama/Llama-3.2-1B: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-7B-Instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen2.5-32B-Instruct: no serverless token price (pricing.input and pricing.output are 0 or absent)
meta-llama/Llama-3.1-405B: no serverless token price (pricing.input and pricing.output are 0 or absent)
agentica-org/DeepCoder-14B-Preview: no serverless token price (pricing.input and pricing.output are 0 or absent)
mistralai/Mistral-7B-v0.1: no serverless token price (pricing.input and pricing.output are 0 or absent)
mistralai/Devstral-Small-2505: no serverless token price (pricing.input and pricing.output are 0 or absent)
mistralai/Mixtral-8x22B-Instruct-v0.1: no serverless token price (pricing.input and pricing.output are 0 or absent)
allenai/Molmo-7B-D-0924: no serverless token price (pricing.input and pricing.output are 0 or absent)
Qwen/Qwen3-8B: no serverless token price (pricing.input and pricing.output are 0 or absent)
…and 58 more

Vertex AI

Updates 14 models from the provider's pricing page (page c7bf48f187b9).

Changes

vertex_ai/deep-research-pro-preview-12-2025: cache_read_input_token_cost $0.2/1M, source https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-2.5-flash-image: input_cost_per_token_batches $0.15/1M, input_cost_per_token_flex $0.15/1M, input_cost_per_token_priority $0.54/1M, output_cost_per_token_batches $1.25/1M, output_cost_per_token_flex $1.25/1M, source https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3-flash-preview: cache_read_input_audio_token_cost $0.1/1M, cache_read_input_token_cost_flex $0.05/1M, input_cost_per_token_batches $0.25/1M, input_cost_per_token_flex $0.25/1M, output_cost_per_token_batches $1.5/1M, output_cost_per_token_flex $1.5/1M, source https://cloud.google.com/vertex-ai/generative-ai/pricing → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3-pro-image: cache_read_input_token_cost $0.2/1M, cache_read_input_token_cost_above_200k_tokens $0.4/1M, cache_read_input_token_cost_above_200k_tokens_priority $0.72/1M, cache_read_input_token_cost_flex $0.1/1M, cache_read_input_token_cost_priority $0.36/1M, input_cost_per_token_above_200k_tokens $4/1M, input_cost_per_token_above_200k_tokens_priority $7.2/1M, input_cost_per_token_flex $1/1M, input_cost_per_token_priority $3.6/1M, output_cost_per_token_above_200k_tokens $18/1M, output_cost_per_token_above_200k_tokens_priority $32.4/1M, output_cost_per_token_flex $6/1M, output_cost_per_token_priority $21.6/1M, source https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.1-flash-image: cache_read_input_token_cost $0.05/1M, cache_read_input_token_cost_flex $0.025/1M, input_cost_per_token_batches $0.25/1M, input_cost_per_token_flex $0.25/1M, output_cost_per_token_batches $1.5/1M, output_cost_per_token_flex $1.5/1M, source https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.1-flash-lite: cache_read_input_audio_token_cost $0.05/1M, source https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.1-flash-lite-image: cache_read_input_token_cost_flex $0.0125/1M, input_cost_per_token_flex $0.125/1M, output_cost_per_token_flex $0.75/1M
vertex_ai/gemini-3.1-pro-preview: cache_read_input_token_cost_flex $0.2/1M, input_cost_per_token_flex $1/1M, output_cost_per_token_flex $6/1M, source https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.5-flash: source https://cloud.google.com/vertex-ai/generative-ai/pricing → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.5-flash-lite: cache_read_input_token_cost_priority $0.05/1M → $0.054/1M, source https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.6-flash: source https://cloud.google.com/vertex-ai/generative-ai/pricing → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.7-flash: source https://cloud.google.com/vertex-ai/generative-ai/pricing → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-3.8-flash: source https://cloud.google.com/vertex-ai/generative-ai/pricing → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
vertex_ai/gemini-embedding-2: source https://cloud.google.com/vertex-ai/generative-ai/pricing → https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing

Skipped by the parser (3)

gemini-2.5-flash: "Audio Input" above 200K is $0.30, not the base price; litellm has no field for it
Gemini 2.0 Flash Image Generation: litellm keys only the free experimental model (gemini-2.0-flash-exp-image-generation)
Gemini 2.0 Flash Live API: litellm has no vertex_ai/ key for the 2.0 Live API

Opened by the litellm-providers price sync. Every price is read from the provider's own published source and gated before it is applied; the audit trail for each value is in the portal's sync history.

fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/deepseek-v4-flash-0731: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp: fireworks_ai/deepseek-v4-flash-vision-exp: fireworks_ai/accounts/fireworks/models/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/deepseek-v4p1-flash: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/glm-5p2: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/glm-5p2: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/glm-5p3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/glm-5p3-flash: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/gpt-oss-120b: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/gpt-oss-120b: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/kimi-k2p6: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/kimi-k2p6: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/kimi-k2p7-code: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/kimi-k2p7-code: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/kimi-k3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/kimi-k3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/minimax-m2p7: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/minimax-m2p7: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/minimax-m3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/minimax-m3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/muse-glimmer-30b: fireworks_ai/muse-glimmer-30b: fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4: fireworks_ai/nemotron-3-ultra-nvfp4: fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b: fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b: input_cost_per_token fireworks_ai/accounts/fireworks/models/qwen3p7-plus: fireworks_ai/qwen3p7-plus: fireworks_ai/accounts/fireworks/models/qwen3p8-max: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/qwen3p8-max: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/routers/glm-5p2-fast: fireworks_ai/accounts/fireworks/routers/glm-5p3-fast: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost fireworks_ai/accounts/fireworks/routers/kimi-k3-fast: together_ai/arcee-ai/trinity-mini: input_cost_per_token, output_cost_per_token together_ai/arize-ai/qwen-2-1.5b-instruct: babbage-002: input_cost_per_token_batches, output_cost_per_token_batches chat-latest: chatgpt-image-latest: output_cost_per_token, input_cost_per_image_token, output_cost_per_image_token, input_cost_per_token_batches, output_cost_per_token_batches claude-fable-5: claude-fable-5-1: claude-haiku-4-5: claude-mythos-5: claude-mythos-5-1: claude-opus-4-5: claude-opus-4-6: claude-opus-4-7: claude-opus-4-8: claude-opus-5: claude-sonnet-4-5: claude-sonnet-4-6: claude-sonnet-5: davinci-002: input_cost_per_token_batches, output_cost_per_token_batches deep-research-pro-preview-12-2025: cache_read_input_token_cost together_ai/deepseek-ai/deepseek-coder-33b-instruct: input_cost_per_token, output_cost_per_token together_ai/deepseek-ai/DeepSeek-R1-0528:

CLAassistant · 2026-09-13T04:55:49Z

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
0 out of 3 committers have signed the CLA.

❌ berriai-litellm-provider-info-sync[bot]
❌ kerry-berri
❌ devin-ai-integration[bot]
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

codspeed · 2026-09-13T04:57:50Z

Merging this PR will not alter performance

✅ 31 untouched benchmarks

_{Comparing litellm-providers/price-sync (b25b6eb) with main (7fd541e)}

codecov · 2026-09-13T04:59:08Z

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

greptile-apps · 2026-09-13T05:18:37Z

Greptile Summary

This PR synchronizes provider pricing metadata in both copies of LiteLLM’s model-price catalog.

Adds Vertex AI flex, batch, priority, cache-read, and modality-specific rates.
Updates pricing-source URLs and selected rates across the broader catalog.
Keeps the primary and backup pricing maps identical.

Confidence Score: 5/5

The PR appears safe to merge because no outstanding or newly introduced actionable failure remains.

The newly added pricing fields match supported metadata keys and existing service-tier accounting behavior, both pricing-map copies remain synchronized, and the only previous root finding was manually resolved without explanation.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Updates model pricing fields and source URLs; no new actionable issue was identified in the changes since the previous review.
litellm/model_prices_and_context_window_backup.json	Mirrors the primary pricing-map updates and remains byte-for-byte consistent with it.

_{Reviews (4): Last reviewed commit: "chore(prices): sync Vertex AI prices: 14..." | Re-trigger Greptile}

…ce-sync

gemini-2.5-flash: cache_read_input_audio_token_cost gemini-2.5-flash-lite: cache_read_input_audio_token_cost gemini-3-flash-preview: cache_read_input_audio_token_cost gemini-3.1-flash-lite: cache_read_input_audio_token_cost

cursor

Stale Bugbot comment from a previous run.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

…embedding-2 alias Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

cursor

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit e4ebeae. Configure here.}

vertex_ai/deep-research-pro-preview-12-2025: cache_read_input_token_cost vertex_ai/gemini-2.5-flash-image: input_cost_per_token_flex, output_cost_per_token_flex, input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches vertex_ai/gemini-3-flash-preview: input_cost_per_token_flex, output_cost_per_token_flex, input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_flex, cache_read_input_audio_token_cost vertex_ai/gemini-3-pro-image: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost, input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_flex, cache_read_input_token_cost_priority, input_cost_per_token_above_200k_tokens, output_cost_per_token_above_200k_tokens, cache_read_input_token_cost_above_200k_tokens, input_cost_per_token_above_200k_tokens_priority, output_cost_per_token_above_200k_tokens_priority, cache_read_input_token_cost_above_200k_tokens_priority vertex_ai/gemini-3.1-flash-image: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost, input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_flex vertex_ai/gemini-3.1-flash-lite: cache_read_input_audio_token_cost vertex_ai/gemini-3.1-flash-lite-image: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost_flex vertex_ai/gemini-3.1-pro-preview: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost_flex vertex_ai/gemini-3.5-flash: vertex_ai/gemini-3.5-flash-lite: cache_read_input_token_cost_priority vertex_ai/gemini-3.6-flash: vertex_ai/gemini-3.7-flash: vertex_ai/gemini-3.8-flash: vertex_ai/gemini-embedding-2:

mateo-berri · 2026-09-14T22:04:28Z

@greptileai

devin-ai-integration · 2026-09-14T22:04:41Z

Price check for head c3f8c07: 48 models changed, 9 mismatch against models.dev or OpenRouter, mostly OpenRouter router-level prices. Details in #litellm-provider-info-sync.

mateo-berri

LGTM. Thanks!

…eads at the published 5.4e-08 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

devin-ai-integration · 2026-09-14T22:53:26Z

Price check for head b25b6eb: 48 models changed, 17 mismatch against models.dev or OpenRouter, mostly missing context limits and OpenRouter router-level prices. Details in #litellm-provider-info-sync.

…103.0) (#290) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/berriai/litellm](https://images.chainguard.dev/directory/image/wolfi-base/overview) ([source](https://github.com/BerriAI/litellm)) | minor | `v1.102.1` → `v1.103.0` | --- ### Release Notes <details> <summary>BerriAI/litellm (ghcr.io/berriai/litellm)</summary> ### [`v1.103.0`](https://github.com/BerriAI/litellm/releases/tag/v1.103.0) [Compare Source](https://github.com/BerriAI/litellm/compare/v1.102.1...v1.103.0) #### 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:v1.103.0 ``` **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/v1.103.0/cosign.pub \ ghcr.io/berriai/litellm:v1.103.0 ``` 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(responses): translate the reasoning object into a chat-completion reasoning effort by [@joshgarnett](https://github.com/joshgarnett) in [#36363](https://github.com/BerriAI/litellm/pull/36363) - fix(proxy): bound tool and guardrail index create\_many by the spend-log statement budgets by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40561](https://github.com/BerriAI/litellm/pull/40561) - fix(mcp): require admission for delegated OAuth by [@joshua-berri](https://github.com/joshua-berri) in [#40923](https://github.com/BerriAI/litellm/pull/40923) - fix(logging): log one bounded summary for a burst of timed-out LoggingWorker callbacks by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40912](https://github.com/BerriAI/litellm/pull/40912) - fix(fireworks): resolve short model names to long cost map keys by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40929](https://github.com/BerriAI/litellm/pull/40929) - ci: remove main branch source guard by [@yuneng-berri](https://github.com/yuneng-berri) in [#40172](https://github.com/BerriAI/litellm/pull/40172) - chore(ci): promote internal staging to main by [@yuneng-berri](https://github.com/yuneng-berri) in [#40942](https://github.com/BerriAI/litellm/pull/40942) - fix(spend\_logs): store litellm\_call\_id and match it in request\_id lookups by [@mateo-berri](https://github.com/mateo-berri) in [#39068](https://github.com/BerriAI/litellm/pull/39068) - fix(auth): refresh lite login session token grants from the live user and team rows by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#40657](https://github.com/BerriAI/litellm/pull/40657) - feat(bedrock): support file delete and list for S3-backed managed files by [@mateo-berri](https://github.com/mateo-berri) in [#39836](https://github.com/BerriAI/litellm/pull/39836) - fix(proxy): gate the webhook test alert on proxy admins by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#40814](https://github.com/BerriAI/litellm/pull/40814) - fix(ui): hide admin write-form tabs on the models page from view-only admins by [@mateo-berri](https://github.com/mateo-berri) in [#38867](https://github.com/BerriAI/litellm/pull/38867) - fix(anthropic-adapter): surface mid-stream provider errors as Anthropic error events by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#33352](https://github.com/BerriAI/litellm/pull/33352) - docs(github): add an Affected release section to the PR template by [@mateo-berri](https://github.com/mateo-berri) in [#40618](https://github.com/BerriAI/litellm/pull/40618) - docs(e2e): ban unit tests under tests/e2e by [@yassin-berriai](https://github.com/yassin-berriai) in [#33852](https://github.com/BerriAI/litellm/pull/33852) - fix(router): preserve Azure Entra ID params in reusable credentials by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40889](https://github.com/BerriAI/litellm/pull/40889) - docs(user endpoints): remove unsupported soft\_budget param from user docstrings by [@shivamrawat1](https://github.com/shivamrawat1) in [#36585](https://github.com/BerriAI/litellm/pull/36585) - feat(friendli): auto-sync Friendli model metadata into price registry by [@Lee-Si-Yoon](https://github.com/Lee-Si-Yoon) in [#35918](https://github.com/BerriAI/litellm/pull/35918) - build(deps): bump smol-toml to 1.8.0 to clear GHSA-7w5x-hrqm-74c2 in osv-scan by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40478](https://github.com/BerriAI/litellm/pull/40478) - fix(bedrock\_mantle): price GovCloud regions from the regional cost row and accept region-prefixed model names by [@mateo-berri](https://github.com/mateo-berri) in [#39846](https://github.com/BerriAI/litellm/pull/39846) - chore(ci): remerge internal staging by [@yuneng-berri](https://github.com/yuneng-berri) in [#40943](https://github.com/BerriAI/litellm/pull/40943) - test(auth): freeze the cache clock in auth prefetch tests by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40996](https://github.com/BerriAI/litellm/pull/40996) - feat(jwt): allow virtual\_key\_claim\_field per issuer by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40927](https://github.com/BerriAI/litellm/pull/40927) - fix(cost): bill cached realtime audio tokens at the audio cache-read rate by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40627](https://github.com/BerriAI/litellm/pull/40627) - perf(logging): skip correlation contextvar stamping when request\_correlation\_in\_logs is off by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41054](https://github.com/BerriAI/litellm/pull/41054) - feat(pricing): add azure gpt-chat-latest rates and drop retired friendliai llama-3.1 entries by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40976](https://github.com/BerriAI/litellm/pull/40976) - build(deps): re-suppress GHSA-h7x2-h6g9-p789 in osv-scan on main, mlflow still has no fixed release by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41104](https://github.com/BerriAI/litellm/pull/41104) - fix(otel): cap per-index OpenInference message attributes span-wide by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40562](https://github.com/BerriAI/litellm/pull/40562) - feat(proxy): add general\_settings.allowed\_file\_extensions for /v1/files uploads by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41106](https://github.com/BerriAI/litellm/pull/41106) - fix(proxy): forward provider request id headers on mapped error responses by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40925](https://github.com/BerriAI/litellm/pull/40925) - fix(router): name the all-deployments-in-cooldown error on 429 responses by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40995](https://github.com/BerriAI/litellm/pull/40995) - fix(ui): show the team alias on the model info page and in its raw JSON by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40992](https://github.com/BerriAI/litellm/pull/40992) - feat(proxy): honor LITELLM\_DISABLE\_ACCESS\_LOG\_PATHS to drop noisy uvicorn access log lines by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41096](https://github.com/BerriAI/litellm/pull/41096) - fix(prometheus): label pre-call rate limit failures with the resolved api\_provider by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41059](https://github.com/BerriAI/litellm/pull/41059) - perf(proxy): serialize /model/info listing once with orjson by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41114](https://github.com/BerriAI/litellm/pull/41114) - fix(utils): stop wrapper\_async submitting the sync success handler twice by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41115](https://github.com/BerriAI/litellm/pull/41115) - fix(redis): log a timeout streak once per interval instead of one line per cache call by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40817](https://github.com/BerriAI/litellm/pull/40817) - fix(router): record flat retry attempts and cap retries from attempted\_retries by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40930](https://github.com/BerriAI/litellm/pull/40930) - refactor(prometheus): source PROXY\_LLM\_PROVIDER\_FALLBACK from litellm.constants by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41118](https://github.com/BerriAI/litellm/pull/41118) - fix(proxy): hide default credentials login hint when UI\_PASSWORD is set by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41107](https://github.com/BerriAI/litellm/pull/41107) - fix(cli): show routed models and session stats for LLM API keys by [@tin-berri](https://github.com/tin-berri) in [#41116](https://github.com/BerriAI/litellm/pull/41116) - fix(bedrock/realtime): propagate deferred Nova Sonic stream failures to the router by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41064](https://github.com/BerriAI/litellm/pull/41064) - fix(proxy): keep org admins' own team memberships in other orgs visible on team list by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41086](https://github.com/BerriAI/litellm/pull/41086) - feat(model\_info): provider-scoped fill\_missing\_for\_providers backfill from fallback generalization rules by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41093](https://github.com/BerriAI/litellm/pull/41093) - fix(auth): load team membership once per request and skip prisma on an L1 hit by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41102](https://github.com/BerriAI/litellm/pull/41102) - refactor(harness): expand independent trace coverage by [@yujonglee-berri](https://github.com/yujonglee-berri) in [#41120](https://github.com/BerriAI/litellm/pull/41120) - fix(proxy): release max\_parallel\_requests slot when a realtime session ends without LLM callbacks by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41113](https://github.com/BerriAI/litellm/pull/41113) - fix(router): cool down team deployments on 429 when a sibling serves the same public model by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40991](https://github.com/BerriAI/litellm/pull/40991) - fix(ui): move tags typed into key metadata JSON into the Tags field by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41023](https://github.com/BerriAI/litellm/pull/41023) - fix(ui): let team admins grant a team all proxy models by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#40196](https://github.com/BerriAI/litellm/pull/40196) - chore(lint): graduate 12 rules from the strict-gate ratchet by [@HUAHAODIA](https://github.com/HUAHAODIA) in [#41048](https://github.com/BerriAI/litellm/pull/41048) - test: add dedicated CircleCI integration contract foundation by [@yuneng-berri](https://github.com/yuneng-berri) in [#41066](https://github.com/BerriAI/litellm/pull/41066) - fix(utils): keep litellm params out of provider request bodies by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41018](https://github.com/BerriAI/litellm/pull/41018) - fix(openai): keep extra\_headers out of the chat request body on the httpx handler path by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41141](https://github.com/BerriAI/litellm/pull/41141) - test: cover persisted updates and warmed authorization policies by [@yuneng-berri](https://github.com/yuneng-berri) in [#41070](https://github.com/BerriAI/litellm/pull/41070) - fix(proxy): resolve x-litellm-call-id from response metadata when routes omit call\_id by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41056](https://github.com/BerriAI/litellm/pull/41056) - chore(prices): sync Vertex AI prices: 14 models by [@berriai-litellm-provider-info-sync](https://github.com/berriai-litellm-provider-info-sync)\[bot] in [#40955](https://github.com/BerriAI/litellm/pull/40955) - ci(codeql): exclude noisy Python quality queries by [@yuneng-berri](https://github.com/yuneng-berri) in [#41142](https://github.com/BerriAI/litellm/pull/41142) - feat(proxy): predict prompt-cache costs across deployments by [@tin-berri](https://github.com/tin-berri) in [#40877](https://github.com/BerriAI/litellm/pull/40877) - fix(prompt\_security): keep polling file sanitization through non-terminal statuses by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41131](https://github.com/BerriAI/litellm/pull/41131) - fix(health): skip background health check DB writes when the latest-row read fails by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41145](https://github.com/BerriAI/litellm/pull/41145) - feat(model\_armor): logging\_only mode scans completed streams after delivery by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40702](https://github.com/BerriAI/litellm/pull/40702) - fix(bedrock guardrails): derive contextual grounding source and query from plain messages by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41132](https://github.com/BerriAI/litellm/pull/41132) - fix(cli): drop enum.StrEnum so the CLI imports on Python 3.10 by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41046](https://github.com/BerriAI/litellm/pull/41046) - fix(responses): route mid-stream error events through exception\_type so content\_policy\_fallbacks fire by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40988](https://github.com/BerriAI/litellm/pull/40988) - fix(cost): bill gemini-embedding-2 per token and stop double charging audio by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41157](https://github.com/BerriAI/litellm/pull/41157) - test: bind management E2E callers and isolate JWT actors by [@yuneng-berri](https://github.com/yuneng-berri) in [#40892](https://github.com/BerriAI/litellm/pull/40892) - fix(headroom): protect cache\_control-marked rows anywhere in history by [@rad-p44](https://github.com/rad-p44) in [#40315](https://github.com/BerriAI/litellm/pull/40315) - test: add strict stateless provider replay identity by [@yuneng-berri](https://github.com/yuneng-berri) in [#41149](https://github.com/BerriAI/litellm/pull/41149) - fix(ci): test checked-out model pricing in unit jobs by [@yuneng-berri](https://github.com/yuneng-berri) in [#41181](https://github.com/BerriAI/litellm/pull/41181) - fix(guardrails): write per-message guardrail rewrites back onto Responses input items by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40939](https://github.com/BerriAI/litellm/pull/40939) - fix(proxy): log the provider usage on deferred /v1/messages calls and price cache writes without a creation rate by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41172](https://github.com/BerriAI/litellm/pull/41172) - fix(guardrails): record not\_run evaluation when scoping leaves nothing to scan by [@yucheng-berri](https://github.com/yucheng-berri) in [#39050](https://github.com/BerriAI/litellm/pull/39050) - fix(responses): preserve provider affinity by [@AaronHowell](https://github.com/AaronHowell) in [#40228](https://github.com/BerriAI/litellm/pull/40228) - fix(sdk): keep body and proxy headers on BadRequestError mapped from a litellm\_proxy 400 by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40994](https://github.com/BerriAI/litellm/pull/40994) - fix(responses): hoist Codex additional\_tools input items into the chat bridge tools by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40989](https://github.com/BerriAI/litellm/pull/40989) - fix(router): honor team and key provider weights by [@tin-berri](https://github.com/tin-berri) in [#41072](https://github.com/BerriAI/litellm/pull/41072) - test(e2e): verify streamed answers and tool continuation by [@yuneng-berri](https://github.com/yuneng-berri) in [#41194](https://github.com/BerriAI/litellm/pull/41194) - fix(cli): label router costs and simplify the routed-model header by [@tin-berri](https://github.com/tin-berri) in [#41186](https://github.com/BerriAI/litellm/pull/41186) - test(spend): reconcile concurrent requests and daily activity by [@yuneng-berri](https://github.com/yuneng-berri) in [#41188](https://github.com/BerriAI/litellm/pull/41188) - fix(guardrails): scan the Anthropic top-level system prompt and tool\_use arguments by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40984](https://github.com/BerriAI/litellm/pull/40984) - fix(router): count num\_retries\_per\_request across fallback hops by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41191](https://github.com/BerriAI/litellm/pull/41191) - fix(bedrock): grant rerank, retrieve, agent, and agentcore actions in the web identity session policy by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41168](https://github.com/BerriAI/litellm/pull/41168) - fix(vertex-live): bill Gemini Live sessions end to end (internal copy of [#37075](https://github.com/BerriAI/litellm/issues/37075)) by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40915](https://github.com/BerriAI/litellm/pull/40915) - fix(health): resolve litellm\_credential\_name in realtime health checks by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41173](https://github.com/BerriAI/litellm/pull/41173) - feat(proxy): unified custom\_key\_policy hook for key generate, update and regenerate by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40921](https://github.com/BerriAI/litellm/pull/40921) - fix(proxy): enforce custom\_key\_update policy on /key/regenerate by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40695](https://github.com/BerriAI/litellm/pull/40695) - fix(router): preserve session model choice within each complexity tier by [@tin-berri](https://github.com/tin-berri) in [#41174](https://github.com/BerriAI/litellm/pull/41174) - test(pricing): let synced GovCloud Bedrock rows cite the AWS price list by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41263](https://github.com/BerriAI/litellm/pull/41263) - docs(github): ask for interactive coding-tool proof in the PR template by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41257](https://github.com/BerriAI/litellm/pull/41257) - feat(proxy): add POST /management/v1/users/bulk for batched user and team membership creation by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41028](https://github.com/BerriAI/litellm/pull/41028) - fix(credentials): answer 409 on a credential name collision, make Terraform adoption opt-in by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#40917](https://github.com/BerriAI/litellm/pull/40917) - feat(proxy): add POST /management/v1/users/bulk\_delete and POST /management/v1/teams/{team\_id}/members/bulk\_delete by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41039](https://github.com/BerriAI/litellm/pull/41039) - fix(proxy): list directly assigned team models in model access errors by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41256](https://github.com/BerriAI/litellm/pull/41256) - feat(auto-router): allow opted-in team members to manage their routers by [@tin-berri](https://github.com/tin-berri) in [#41175](https://github.com/BerriAI/litellm/pull/41175) - build(rust-bridge): add typed \_native stub and validate it with mypy.stubtest by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41180](https://github.com/BerriAI/litellm/pull/41180) - feat(guardrails): add new upstream presidio pii entities including german set by [@MvdB](https://github.com/MvdB) in [#36775](https://github.com/BerriAI/litellm/pull/36775) - fix(responses): filter bridged kwargs like the native Responses path by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41144](https://github.com/BerriAI/litellm/pull/41144) - test(e2e): cover the reliability retry, cooldown, fallback, and routing-strategy cells by [@mateo-berri](https://github.com/mateo-berri) in [#39857](https://github.com/BerriAI/litellm/pull/39857) - fix(anthropic): add the per-turn-control beta when a message carries output\_config by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41189](https://github.com/BerriAI/litellm/pull/41189) - fix(router): bind per-request routing\_strategy override selectors to the request's callbacks by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41178](https://github.com/BerriAI/litellm/pull/41178) - feat(proxy): bind JWT claims to registered agents via agent\_id\_jwt\_field by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40904](https://github.com/BerriAI/litellm/pull/40904) - fix(proxy): enforce organization budgets when max\_budget is 0 by [@yassin-berriai](https://github.com/yassin-berriai) in [#41271](https://github.com/BerriAI/litellm/pull/41271) - fix(alerting): send llm\_exceptions Slack alert for 5xx HTTPException and ProxyException by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41125](https://github.com/BerriAI/litellm/pull/41125) - fix(headroom): protect the cached prefix through the last cache\_control breakpoint by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41161](https://github.com/BerriAI/litellm/pull/41161) - fix(utils): cache custom HuggingFace tokenizers across /utils/token\_counter requests by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41216](https://github.com/BerriAI/litellm/pull/41216) - fix(router): keep weighted routing when a deployment id equals a model\_name by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41156](https://github.com/BerriAI/litellm/pull/41156) - feat(router): add capability classifier as Fuse foundation by [@tin-berri](https://github.com/tin-berri) in [#41270](https://github.com/BerriAI/litellm/pull/41270) - fix(proxy): keep access-group raw SQL writes on the writer while writer\_unavailable is stale by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41283](https://github.com/BerriAI/litellm/pull/41283) - fix(prometheus): count 401 auth failures in litellm\_proxy\_failed\_requests\_metric by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41170](https://github.com/BerriAI/litellm/pull/41170) - test: drop tests that pin vendor facts and add the CLAUDE.md rule by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41269](https://github.com/BerriAI/litellm/pull/41269) - fix(proxy): run the remaining inline token counts off the event loop by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40262](https://github.com/BerriAI/litellm/pull/40262) - fix(proxy): log blocked streaming guardrail responses as failures, not success by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40191](https://github.com/BerriAI/litellm/pull/40191) - feat(proxy): add tpd\_limit (tokens per day) for batch submissions by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40997](https://github.com/BerriAI/litellm/pull/40997) - fix(proxy): reconcile budget reservation before enqueuing spend to the DB by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40310](https://github.com/BerriAI/litellm/pull/40310) - fix(xai): stop sending web\_search\_options to xAI's retired Live Search path by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#38278](https://github.com/BerriAI/litellm/pull/38278) - feat(terraform): add tpm\_limit, rpm\_limit, budget\_duration, allowed\_models to litellm\_team\_member\_add by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#38682](https://github.com/BerriAI/litellm/pull/38682) - fix(rerank): bill Vertex search\_units from input records and give every rerank response a unique id by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35180](https://github.com/BerriAI/litellm/pull/35180) - fix(router): stop counting caller-set timeout 408s toward deployment cooldown by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41230](https://github.com/BerriAI/litellm/pull/41230) - feat(router): add Fuse V2 classifier after capability forecasting by [@tin-berri](https://github.com/tin-berri) in [#41272](https://github.com/BerriAI/litellm/pull/41272) - fix(proxy): keep client User-Agent on auth failure spend logs by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41291](https://github.com/BerriAI/litellm/pull/41291) - fix(proxy): reset budgets by decrementing pre-reset spend instead of zeroing rows by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41279](https://github.com/BerriAI/litellm/pull/41279) - fix(xai): honor nested web\_search filters on the xAI Responses API by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#38268](https://github.com/BerriAI/litellm/pull/38268) - fix(router): stop registering a caller-supplied credential as a router deployment by [@yassin-berriai](https://github.com/yassin-berriai) in [#41289](https://github.com/BerriAI/litellm/pull/41289) - fix(router): accept custom\_provider\_map providers before the first completion call by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41300](https://github.com/BerriAI/litellm/pull/41300) - fix(proxy): return 400 instead of 500 for lone surrogate escapes in request body by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41297](https://github.com/BerriAI/litellm/pull/41297) - fix(langsmith): keep events appended during an in-flight flush instead of clearing them by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41288](https://github.com/BerriAI/litellm/pull/41288) - fix(logging): track spend for streams a deployment hook converted to non-streaming by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41171](https://github.com/BerriAI/litellm/pull/41171) - fix(bedrock): sanitize client tool\_call ids to Bedrock toolUseId constraints by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40872](https://github.com/BerriAI/litellm/pull/40872) - fix(passthrough): attribute Vertex passthrough successes to the resolved router deployment by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41307](https://github.com/BerriAI/litellm/pull/41307) - feat(ui): persist Models table search, filters, sort and page in the URL by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41296](https://github.com/BerriAI/litellm/pull/41296) - fix(jwt-auth): scope JWT key mappings by issuer to prevent cross-issuer collisions by [@yassin-berriai](https://github.com/yassin-berriai) in [#41281](https://github.com/BerriAI/litellm/pull/41281) - feat(openai): add openai\_system\_messages\_first to put system messages first for prompt caching by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41304](https://github.com/BerriAI/litellm/pull/41304) - feat(ui): add custom request headers to the API Playground by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41309](https://github.com/BerriAI/litellm/pull/41309) - feat(cli): sync Codex /model picker from proxy /v1/models in lite codex by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40476](https://github.com/BerriAI/litellm/pull/40476) - chore: bump litellm-enterprise 0.1.67 -> 0.1.68, litellm-proxy-extras 0.4.97 -> 0.4.98, litellm 1.102.0 -> 1.103.0 by [@yuneng-berri](https://github.com/yuneng-berri) in [#41321](https://github.com/BerriAI/litellm/pull/41321) - feat: add aihubmix provider pricing entries by [@IToSSc](https://github.com/IToSSc) in [#41179](https://github.com/BerriAI/litellm/pull/41179) - feat(auto-router): add per-model Fast mode toggle by [@tin-berri](https://github.com/tin-berri) in [#41282](https://github.com/BerriAI/litellm/pull/41282) - fix(proxy): include litellm\_call\_id in LLM API exception logs by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41205](https://github.com/BerriAI/litellm/pull/41205) - fix(proxy): keep yaml pass-through endpoints visible to auth after db overlay by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41303](https://github.com/BerriAI/litellm/pull/41303) - fix(proxy): resolve router\_settings.model\_group\_alias before key/team model auth by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41308](https://github.com/BerriAI/litellm/pull/41308) - fix(ui): block usage export and flag the range when a spend page fails by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#41294](https://github.com/BerriAI/litellm/pull/41294) - fix(vertex\_ai): bill Gemini Omni Interactions usage and Veo sampleCount on passthrough by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41322](https://github.com/BerriAI/litellm/pull/41322) - fix(proxy): honor LITELLM\_LOG for uvicorn and proxy extras loggers by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41306](https://github.com/BerriAI/litellm/pull/41306) - fix(cost): price native Responses WebSocket turns at their returned service\_tier by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41318](https://github.com/BerriAI/litellm/pull/41318) - fix(proxy): key model rpm/tpm override takes precedence over team model limit by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41302](https://github.com/BerriAI/litellm/pull/41302) - fix(proxy): track per-member organization spend by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41255](https://github.com/BerriAI/litellm/pull/41255) - feat(proxy): add /nvidia\_nim passthrough route for NIM object detection and OCR /v1/infer by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41316](https://github.com/BerriAI/litellm/pull/41316) - feat(model\_info): add provider-neutral Gemini 2.5+ chat baseline fallback generalization by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41320](https://github.com/BerriAI/litellm/pull/41320) - fix(spend): sum multi-round session duration in logs UI by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35388](https://github.com/BerriAI/litellm/pull/35388) - feat(router): limit unlicensed Capability and Fuse v2 routers to one each by [@tin-berri](https://github.com/tin-berri) in [#41326](https://github.com/BerriAI/litellm/pull/41326) - fix(guardrails): resolve caller identity from metadata buckets in custom code guardrail by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41126](https://github.com/BerriAI/litellm/pull/41126) - fix(e2e): onboard dashboard users through invitations by [@yuneng-berri](https://github.com/yuneng-berri) in [#41319](https://github.com/BerriAI/litellm/pull/41319) - feat(guardrails): add Microsoft Agent 365 MCP tool-call guardrail by [@yucheng-berri](https://github.com/yucheng-berri) in [#38241](https://github.com/BerriAI/litellm/pull/38241) - test: drop remaining tests that pin cost-map vendor facts by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41298](https://github.com/BerriAI/litellm/pull/41298) - feat(ui): show average response time per model in usage model activity by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41313](https://github.com/BerriAI/litellm/pull/41313) - fix(proxy): preserve Anthropic pricing modifiers in router savings by [@tin-berri](https://github.com/tin-berri) in [#41341](https://github.com/BerriAI/litellm/pull/41341) - feat(guardrails): support pre\_call and during\_call modes for llm\_as\_a\_judge by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41128](https://github.com/BerriAI/litellm/pull/41128) - fix(gemini): propagate the provider's modelVersion to the response model by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41338](https://github.com/BerriAI/litellm/pull/41338) - fix(fireworks-ai): bill cache-write, reasoning and audio tokens via the shared cost calculator by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41339](https://github.com/BerriAI/litellm/pull/41339) - feat(guardrails): singulr v2 API contract with logging\_only, pre\_mcp\_call and post\_mcp\_call by [@yucheng-berri](https://github.com/yucheng-berri) in [#41329](https://github.com/BerriAI/litellm/pull/41329) - ci(image-scan): ignore zlib CVE-2026-85091 until Wolfi ships the fix by [@yuneng-berri](https://github.com/yuneng-berri) in [#41353](https://github.com/BerriAI/litellm/pull/41353) - feat(e2e): reuse exact provider responses for 24 hours by [@yuneng-berri](https://github.com/yuneng-berri) in [#41346](https://github.com/BerriAI/litellm/pull/41346) - fix(xai): keep 'instructions' on the xAI Responses API so system messages survive web search by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#38254](https://github.com/BerriAI/litellm/pull/38254) - feat(ui): configure capability and Fuse v2 classifiers by [@tin-berri](https://github.com/tin-berri) in [#41315](https://github.com/BerriAI/litellm/pull/41315) - fix(anthropic): tolerate message\_delta events without usage when streaming by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41336](https://github.com/BerriAI/litellm/pull/41336) - test(router): ignore deployment-selection logs in the fallback log assertion by [@yuneng-berri](https://github.com/yuneng-berri) in [#41358](https://github.com/BerriAI/litellm/pull/41358) - test(proxy): assert budget resets decrement the cleared spend by [@yuneng-berri](https://github.com/yuneng-berri) in [#41359](https://github.com/BerriAI/litellm/pull/41359) - fix(e2e): expect models filters to persist after reload by [@yuneng-berri](https://github.com/yuneng-berri) in [#41348](https://github.com/BerriAI/litellm/pull/41348) - fix(e2e): record cookie-setting provider responses and keep prompt-caching tests live by [@yuneng-berri](https://github.com/yuneng-berri) in [#41366](https://github.com/BerriAI/litellm/pull/41366) - fix(responses): recount tokens when a streamed response completes without usage by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41337](https://github.com/BerriAI/litellm/pull/41337) - fix(ui): simplify Capability and Fuse advanced routing options by [@tin-berri](https://github.com/tin-berri) in [#41371](https://github.com/BerriAI/litellm/pull/41371) - fix(mcp): authorize JWT OAuth credential persistence by [@joshua-berri](https://github.com/joshua-berri) in [#41314](https://github.com/BerriAI/litellm/pull/41314) - feat(router): stream shadow traffic and fan out silent\_model to multiple targets by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41368](https://github.com/BerriAI/litellm/pull/41368) - perf(content\_filter): scan a bounded window per streamed chunk by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41407](https://github.com/BerriAI/litellm/pull/41407) - fix(proxy): hide model allowlist from client-facing model access denied errors by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41310](https://github.com/BerriAI/litellm/pull/41310) - feat(http): opt-in outbound HTTP/2 for httpx clients by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41268](https://github.com/BerriAI/litellm/pull/41268) - refactor(rust): remove gateway, config, router, realtime, and Rust trace-parity instrumentation by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41432](https://github.com/BerriAI/litellm/pull/41432) - fix(guardrails): don't add post\_call output scan for MCP-only Presidio modes by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40571](https://github.com/BerriAI/litellm/pull/40571) - chore(prices): sync Azure, Azure AI, Gemini, OpenAI, Bedrock, Together AI, Fireworks and Vertex prices: 278 models, 59 new, 30 deprecated by [@berriai-litellm-provider-info-sync](https://github.com/berriai-litellm-provider-info-sync)\[bot] in [#41154](https://github.com/BerriAI/litellm/pull/41154) - fix(rag): forward retrieval\_filter from retrieval\_config to vector store search by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34427](https://github.com/BerriAI/litellm/pull/34427) - refactor(rust): extract auth and cache crates by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41464](https://github.com/BerriAI/litellm/pull/41464) - fix(proxy): default litellm\_trace\_id to the OTel server span trace id by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41386](https://github.com/BerriAI/litellm/pull/41386) - chore(codeowners): add ryan and kerry as owners of the cost map by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41333](https://github.com/BerriAI/litellm/pull/41333) - fix(responses): guard empty-choices chunks in the Responses API streaming bridge by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#34455](https://github.com/BerriAI/litellm/pull/34455) - chore(prices): sync Google Gemini prices: 22 models by [@berriai-litellm-provider-info-sync](https://github.com/berriai-litellm-provider-info-sync)\[bot] in [#41457](https://github.com/BerriAI/litellm/pull/41457) - fix(bedrock): forward userContext in Knowledge Base Retrieve requests by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41475](https://github.com/BerriAI/litellm/pull/41475) - ci(rust): split rust jobs, use nextest and Swatinem/rust-cache by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41480](https://github.com/BerriAI/litellm/pull/41480) - fix(fireworks\_ai): flatten dict-form reasoning\_effort to its effort string by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41335](https://github.com/BerriAI/litellm/pull/41335) - fix(proxy): never forward the LiteLLM virtual key to Anthropic on the /anthropic passthrough by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41340](https://github.com/BerriAI/litellm/pull/41340) - fix(proxy): rename AWS Secrets Manager secret when key alias changes by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41468](https://github.com/BerriAI/litellm/pull/41468) - feat(otel): promote nested request metadata keys to litellm.metadata.\* span attributes by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41462](https://github.com/BerriAI/litellm/pull/41462) - fix(proxy): sync AWS Secrets Manager on body-less key regenerate and key alias changes by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41458](https://github.com/BerriAI/litellm/pull/41458) - fix(http\_handler): keep a handler alive while a response it issued is still reading by [@max-sixty](https://github.com/max-sixty) in [#34829](https://github.com/BerriAI/litellm/pull/34829) - fix(bedrock): make prompt caching work on the Nova InvokeModel route by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41343](https://github.com/BerriAI/litellm/pull/41343) - ci(migrations): flag defaulted ADD COLUMN on request-log tables by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41460](https://github.com/BerriAI/litellm/pull/41460) - feat(prometheus): add customer (end\_user) budget gauges by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41472](https://github.com/BerriAI/litellm/pull/41472) - fix(otel): drop None metric and event attributes before OTLP export by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#36815](https://github.com/BerriAI/litellm/pull/36815) - fix(anthropic): carry the served model from message\_start onto stream chunks by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41446](https://github.com/BerriAI/litellm/pull/41446) - fix(models): rolling registry audit: Gemini latest aliases, Nova cache pricing, OpenRouter/Together sync, Mistral GLM 5.3, Azure snapshots, Grok caching by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41112](https://github.com/BerriAI/litellm/pull/41112) - fix(router): count TPM/RPM usage before building rate-limit headers by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41474](https://github.com/BerriAI/litellm/pull/41474) - feat(guardrails): release buffered stream chunks after each passing scan by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41425](https://github.com/BerriAI/litellm/pull/41425) - fix!: re-check budget on router fallback targets by [@runjivu](https://github.com/runjivu) in [#41379](https://github.com/BerriAI/litellm/pull/41379) - refactor(ocr): move file preparation from the python bridge into litellm-core by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41489](https://github.com/BerriAI/litellm/pull/41489) - feat(s3): add s3\_log\_prompts\_only option to log prompts without responses by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41327](https://github.com/BerriAI/litellm/pull/41327) - feat(team): team-level model\_max\_budget with key-level overrides by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41330](https://github.com/BerriAI/litellm/pull/41330) - feat(keys): filter /key/list by active, expired, revoked or deleted status and serve deleted keys from /key/info by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41311](https://github.com/BerriAI/litellm/pull/41311) - feat(proxy): expose lifetime total\_spend on virtual keys by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41403](https://github.com/BerriAI/litellm/pull/41403) - fix(proxy): release completed max-parallel slots promptly by [@elifozdamar](https://github.com/elifozdamar) in [#40843](https://github.com/BerriAI/litellm/pull/40843) - feat(ui): accept ssh clone urls when registering a skill by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#35418](https://github.com/BerriAI/litellm/pull/35418) - fix(prices): dedupe Nova cache\_read\_input\_token\_cost keys left by a text merge by [@yuneng-berri](https://github.com/yuneng-berri) in [#41496](https://github.com/BerriAI/litellm/pull/41496) - fix(otel): propagate W3C trace context on HTTP and WebSocket passthrough by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40669](https://github.com/BerriAI/litellm/pull/40669) - fix(proxy): remove duplicate user budget hook that 429'd zero-cost models by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41345](https://github.com/BerriAI/litellm/pull/41345) - test(logging): pick this test's own records out of the shared log batch by [@yuneng-berri](https://github.com/yuneng-berri) in [#41487](https://github.com/BerriAI/litellm/pull/41487) - test(together\_ai): move request-shape checks to the mapped file, drop the live ones by [@yuneng-berri](https://github.com/yuneng-berri) in [#41360](https://github.com/BerriAI/litellm/pull/41360) - feat(ui): shared URL-state layer for tables and tabs by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#41331](https://github.com/BerriAI/litellm/pull/41331) - feat(e2e): make the provider cache reusable across builds and mount Bedrock behind it by [@yuneng-berri](https://github.com/yuneng-berri) in [#41402](https://github.com/BerriAI/litellm/pull/41402) - fix(mcp): fail closed on missing upstream credentials by [@joshua-berri](https://github.com/joshua-berri) in [#41364](https://github.com/BerriAI/litellm/pull/41364) - feat(rust): scaffold Redis cache crate by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41501](https://github.com/BerriAI/litellm/pull/41501) - fix(dashscope): forward reasoning\_effort to the provider by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#37506](https://github.com/BerriAI/litellm/pull/37506) - fix(proxy): carry litellm\_call\_id through endpoint specific error logs and failure responses by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41356](https://github.com/BerriAI/litellm/pull/41356) - fix(proxy): retry rate-limit fallbacks from a pristine request snapshot by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40596](https://github.com/BerriAI/litellm/pull/40596) - fix(gemini): map minimal thinking to low for Gemini 3.7 and 3.8 Flash by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41201](https://github.com/BerriAI/litellm/pull/41201) - fix(proxy): stop forwarding LiteLLM credential headers on Bedrock agent-runtime passthrough by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41504](https://github.com/BerriAI/litellm/pull/41504) - fix(streaming): estimate interrupted Anthropic stream usage from reasoning\_content by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41503](https://github.com/BerriAI/litellm/pull/41503) - fix(azure\_ai): route Responses API to native /openai/v1/responses for Foundry Models by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#33856](https://github.com/BerriAI/litellm/pull/33856) - fix(proxy): show all model groups to proxy admins in /model\_group/info by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41094](https://github.com/BerriAI/litellm/pull/41094) - feat(proxy): let proxy admins choose which team fields team admins may edit by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#39996](https://github.com/BerriAI/litellm/pull/39996) - fix(bedrock): neutralize orphaned tool blocks instead of raising or injecting a dummy tool (internal copy of [#31400](https://github.com/BerriAI/litellm/issues/31400)) by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41513](https://github.com/BerriAI/litellm/pull/41513) - feat(ui): persist organizations and projects list, detail tab and key table state in the URL by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#41445](https://github.com/BerriAI/litellm/pull/41445) - fix(bedrock\_mantle): accept and forward verbosity on gpt-5.x chat completions by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41509](https://github.com/BerriAI/litellm/pull/41509) - test: cover database transactions and persisted accounting by [@yuneng-berri](https://github.com/yuneng-berri) in [#41073](https://github.com/BerriAI/litellm/pull/41073) - test: provider wire contracts, streaming and recovery by [@yuneng-berri](https://github.com/yuneng-berri) in [#41075](https://github.com/BerriAI/litellm/pull/41075) - fix(mcp): count admin static headers as api\_key credential slots by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41514](https://github.com/BerriAI/litellm/pull/41514) - ci: auto-merge provider-info-sync PRs when CI, Greptile and Bugbot are clean by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41494](https://github.com/BerriAI/litellm/pull/41494) - feat(rust): add standalone framing crate by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41500](https://github.com/BerriAI/litellm/pull/41500) - fix(proxy): enforce tag budgets for tags added by guardrails by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40842](https://github.com/BerriAI/litellm/pull/40842) - fix(utils): run post-call deployment hook on converted chat streams by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41495](https://github.com/BerriAI/litellm/pull/41495) - fix(e2e): bind provider-cache recordings to the deployment's test, not the serving process by [@yuneng-berri](https://github.com/yuneng-berri) in [#41520](https://github.com/BerriAI/litellm/pull/41520) - test: add extension and browser integration contracts by [@yuneng-berri](https://github.com/yuneng-berri) in [#41078](https://github.com/BerriAI/litellm/pull/41078) - fix(logging): scan each log record once and collapse base64 payloads before the secret regex by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40934](https://github.com/BerriAI/litellm/pull/40934) - fix(spend\_tracking): attribute router-rejected requests to the model group provider by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41507](https://github.com/BerriAI/litellm/pull/41507) - feat(router): discover token limits for hosted OpenAI-compatible models by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41508](https://github.com/BerriAI/litellm/pull/41508) - feat(proxy): let team admins edit rpm\_limit and max\_budget when enabled by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#41525](https://github.com/BerriAI/litellm/pull/41525) - fix(otel): fit per-index OpenInference messages to the span's remaining attribute budget by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41498](https://github.com/BerriAI/litellm/pull/41498) - test(aws): verify rotated secret value by [@yuneng-berri](https://github.com/yuneng-berri) in [#41524](https://github.com/BerriAI/litellm/pull/41524) - test(e2e): read a deleted key back as deleted, not as a 404 by [@yuneng-berri](https://github.com/yuneng-berri) in [#41551](https://github.com/BerriAI/litellm/pull/41551) - fix(otel v2): map the caller's Langfuse user, session and tags onto the root and generation spans by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41140](https://github.com/BerriAI/litellm/pull/41140) - test: fix seven tests left stale by [#41311](https://github.com/BerriAI/litellm/issues/41311), [#41337](https://github.com/BerriAI/litellm/issues/41337), [#39996](https://github.com/BerriAI/litellm/issues/39996), [#41310](https://github.com/BerriAI/litellm/issues/41310), [#41289](https://github.com/BerriAI/litellm/issues/41289) and [#41315](https://github.com/BerriAI/litellm/issues/41315) by [@yuneng-berri](https://github.com/yuneng-berri) in [#41527](https://github.com/BerriAI/litellm/pull/41527) - test(budgets): cover management null handling by [@yuneng-berri](https://github.com/yuneng-berri) in [#41563](https://github.com/BerriAI/litellm/pull/41563) - test(e2e): drop the auto-router select "opens below" spec by [@yuneng-berri](https://github.com/yuneng-berri) in [#41568](https://github.com/BerriAI/litellm/pull/41568) - fix(guardrails): stream Prompt Security post\_call redactions in incremental\_diff mode by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41558](https://github.com/BerriAI/litellm/pull/41558) - fix(guardrails): give post-call scans the scoped request conversation and tools by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41220](https://github.com/BerriAI/litellm/pull/41220) - feat(openrouter): add stealth/union-alpha to the model cost map by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41576](https://github.com/BerriAI/litellm/pull/41576) - test(management): cover project authorization lifecycle by [@yuneng-berri](https://github.com/yuneng-berri) in [#41573](https://github.com/BerriAI/litellm/pull/41573) - feat(rust): map Anthropic Messages transformations by [@yujonglee-berri](https://github.com/yujonglee-berri) in [#41531](https://github.com/BerriAI/litellm/pull/41531) - fix(e2e): clear the three standing errors in the scheduled Buildkite suite by [@yuneng-berri](https://github.com/yuneng-berri) in [#41616](https://github.com/BerriAI/litellm/pull/41616) - refactor(rust\_bridge): declarative route catalog and shared runtime selection by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41479](https://github.com/BerriAI/litellm/pull/41479) - fix(mock\_completion): keep the resolved provider so router custom pricing resolves for azure\_ai deployments by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41623](https://github.com/BerriAI/litellm/pull/41623) - fix(mcp): restrict health discovery to virtual key grants by [@joshua-berri](https://github.com/joshua-berri) in [#41609](https://github.com/BerriAI/litellm/pull/41609) - fix(mcp): preserve request-selected guardrails during tool execution by [@joshua-berri](https://github.com/joshua-berri) in [#41619](https://github.com/BerriAI/litellm/pull/41619) - refactor(ocr): mirror Python provider layout and preserve tests by [@yujonglee-berri](https://github.com/yujonglee-berri) in [#41550](https://github.com/BerriAI/litellm/pull/41550) - test(fireworks\_ai): stop pinning vision support on minimax-m3 by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41627](https://github.com/BerriAI/litellm/pull/41627) - perf(spend\_tracking): index LiteLLM\_SpendLogs by (api\_key, startTime) by [@etiennechabert](https://github.com/etiennechabert) in [#37983](https://github.com/BerriAI/litellm/pull/37983) - fix(proxy): reject non-string model with 400 and log its spend as unknown-model by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41633](https://github.com/BerriAI/litellm/pull/41633) - test(together\_ai): stop pinning successor deprecation status by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41635](https://github.com/BerriAI/litellm/pull/41635) - chore(prices): sync Together AI prices: 6 models, 6 deprecated \[sync failed: Google Gemini] by [@berriai-litellm-provider-info-sync](https://github.com/berriai-litellm-provider-info-sync)\[bot] in [#41570](https://github.com/BerriAI/litellm/pull/41570) - fix(budgets): page end-user cache invalidation after a budget reset by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#41488](https://github.com/BerriAI/litellm/pull/41488) - chore: bump litellm-proxy-extras 0.4.98 -> 0.4.99 by [@yuneng-berri](https://github.com/yuneng-berri) in [#41659](https://github.com/BerriAI/litellm/pull/41659) - fix(tests): resolve the integration support package without run.py's PYTHONPATH by [@yuneng-berri](https://github.com/yuneng-berri) in [#41373](https://github.com/BerriAI/litellm/pull/41373) - fix(ui): keep untimed guardrail entries on the request lifecycle by [@yuneng-berri](https://github.com/yuneng-berri) in [#41374](https://github.com/BerriAI/litellm/pull/41374) - fix(anthropic-bridge): convert mid-conversation system turns to user turns on /v1/messages to chat completions by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41493](https://github.com/BerriAI/litellm/pull/41493) - fix(bedrock): support aws-sdk-bedrock-runtime 0.10/0.11 in Bedrock Realtime by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41542](https://github.com/BerriAI/litellm/pull/41542) - feat(cli): deprecate the litellm-proxy entrypoint in favour of lite by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41673](https://github.com/BerriAI/litellm/pull/41673) - fix(scim): align pagination `count` validation with RFC 7644 by [@zachbernstein-sdx](https://github.com/zachbernstein-sdx) in [#41444](https://github.com/BerriAI/litellm/pull/41444) - fix(bedrock): never emit Converse cachePoint for OpenAI-family models by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41419](https://github.com/BerriAI/litellm/pull/41419) - fix(images): stop forwarding the raw image\[] and mask\[] form keys by [@mateo-berri](https://github.com/mateo-berri) in [#39512](https://github.com/BerriAI/litellm/pull/39512) - feat(management\_v1): bulk update team member budgets by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#41632](https://github.com/BerriAI/litellm/pull/41632) - refactor(rust): extract provider translations by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41690](https://github.com/BerriAI/litellm/pull/41690) - feat(cli): rename lite autoroute up/down to start/stop, keeping the old names as deprecated aliases by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41672](https://github.com/BerriAI/litellm/pull/41672) - fix(responses): keep the addressed response id off bridged provider requests by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41689](https://github.com/BerriAI/litellm/pull/41689) - fix(license): let a wildcard allowed\_features license grant the auto\_router feature by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41684](https://github.com/BerriAI/litellm/pull/41684) - fix(ui): list every provider in the cache leakage by-model table by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#40875](https://github.com/BerriAI/litellm/pull/40875) - fix(team): keep a forked member budget's reset window and audit bulk member budget writes by [@ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#41686](https://github.com/BerriAI/litellm/pull/41686) - feat(proxy): add TypeSafe AI Jev evaluate passthrough with registry-priced spend tracking by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41607](https://github.com/BerriAI/litellm/pull/41607) - test(e2e): cover bedrock batch file upload and create in the us-gov-west-1 partition by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41536](https://github.com/BerriAI/litellm/pull/41536) - feat(grafana): add all-metrics dashboard and fix stale dashboard\_v2 gauges by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41578](https://github.com/BerriAI/litellm/pull/41578) - fix(cost): price Azure PTU spillover requests at standard token rates by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41569](https://github.com/BerriAI/litellm/pull/41569) - build(deps): bump soupsieve to 2.9.2 to clear the osv-scan advisories by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41703](https://github.com/BerriAI/litellm/pull/41703) - fix(fireworks\_ai): restore supports\_vision on minimax-m3 in the cost map by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41699](https://github.com/BerriAI/litellm/pull/41699) - feat(policy\_engine): explicit priority for policy attachment execution order by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41571](https://github.com/BerriAI/litellm/pull/41571) - feat(router): add TypeSafe Jev as a complexity router classifier by [@devin-ai-integration](https://github.com/devin-ai-integration)\[bot] in [#41615](https://github.com…

berriai-litellm-provider-info-sync Bot requested a review from a team September 13, 2026 04:55

berriai-litellm-provider-info-sync Bot requested a review from mateo-berri as a code owner September 13, 2026 04:55

greptile-apps Bot reviewed Sep 13, 2026

View reviewed changes

Comment thread model_prices_and_context_window.json Outdated

kerry and others added 2 commits September 14, 2026 21:21

Merge remote-tracking branch 'origin/main' into litellm-providers/pri…

ddf13e9

…ce-sync

chore(prices): sync Vertex AI prices: 4 models

93e6599

gemini-2.5-flash: cache_read_input_audio_token_cost gemini-2.5-flash-lite: cache_read_input_audio_token_cost gemini-3-flash-preview: cache_read_input_audio_token_cost gemini-3.1-flash-lite: cache_read_input_audio_token_cost

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync prices for 5 providers: 278 models, 34 new~~ chore(prices): sync Vertex AI prices: 4 models Sep 14, 2026

cursor Bot reviewed Sep 14, 2026

View reviewed changes

Comment thread model_prices_and_context_window.json

Comment thread model_prices_and_context_window.json

Comment thread model_prices_and_context_window.json

Comment thread model_prices_and_context_window.json

kerry and others added 3 commits September 14, 2026 21:41

chore(prices): flag gpt-5.5-cyber as a reasoning model

abbf5aa

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

fix(prices): mark Vertex Gemini TTS entries as audio_speech

f45e20e

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

fix(prices): add text output rate to Vertex TTS entries, sync gemini-…

e4ebeae

…embedding-2 alias Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

cursor Bot reviewed Sep 14, 2026

View reviewed changes

devin-ai-integration Bot changed the title ~~chore(prices): sync Vertex AI prices: 4 models~~ chore(prices): sync prices for 5 providers: 278 models, 34 new Sep 14, 2026

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync prices for 5 providers: 278 models, 34 new~~ chore(prices): sync Vertex AI prices: 14 models Sep 14, 2026

mateo-berri approved these changes Sep 14, 2026

View reviewed changes

devin-ai-integration Bot mentioned this pull request Sep 14, 2026

fix(cost_map): vertex gemini-3.5-flash-lite priority cache read is $0.054/M #41137

Closed

4 of 6 tasks

test(cost_calc): pin vertex_ai gemini-3.5-flash-lite priority cache r…

b25b6eb

…eads at the published 5.4e-08 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

kerry-berri merged commit 9481556 into main Sep 14, 2026
86 checks passed

tin-berri mentioned this pull request Sep 15, 2026

fix(cost): avoid double billing Gemini embedding modalities #41151

Closed

6 tasks done

devin-ai-integration Bot mentioned this pull request Sep 15, 2026

fix(cost): bill gemini-embedding-2 per token and stop double charging audio #41157

Merged

3 of 5 tasks

yuneng-berri mentioned this pull request Sep 15, 2026

fix(ci): test checked-out model pricing in unit jobs #41181

Merged

5 of 6 tasks

devin-ai-integration Bot mentioned this pull request Sep 17, 2026

fix(models): rolling registry audit: Azure retirement dates, Bedrock Mantle Grok 4.3 context window #41597

Merged

6 tasks done

Conversation

berriai-litellm-provider-info-sync Bot commented Sep 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

OpenAI

Skipped by the parser (7)

Together AI

Skipped by the parser (98)

Vertex AI

Changes

Skipped by the parser (3)

Uh oh!

CLAassistant commented Sep 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

codspeed Bot commented Sep 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merging this PR will not alter performance

Uh oh!

codecov Bot commented Sep 13, 2026

Codecov Report

Uh oh!

greptile-apps Bot commented Sep 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Greptile Summary

Confidence Score: 5/5

Important Files Changed

Uh oh!

Uh oh!

cursor Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

cursor Bot left a comment

Choose a reason for hiding this comment

Uh oh!

mateo-berri commented Sep 14, 2026

Uh oh!

devin-ai-integration Bot commented Sep 14, 2026

Uh oh!

mateo-berri left a comment

Choose a reason for hiding this comment

Uh oh!

devin-ai-integration Bot commented Sep 14, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

berriai-litellm-provider-info-sync Bot commented Sep 13, 2026 •

edited

Loading

CLAassistant commented Sep 13, 2026 •

edited

Loading

codspeed Bot commented Sep 13, 2026 •

edited

Loading

greptile-apps Bot commented Sep 13, 2026 •

edited

Loading

cursor Bot left a comment •

edited

Loading