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[bot] · Pull Request #41154 · BerriAI/litellm

berriai-litellm-provider-info-sync · 2026-09-15T00:36:09Z

TLDR

Problem this solves:

Catalog prices for Azure, Azure AI, Gemini, OpenAI and Bedrock drifted from provider pages
Together AI, Fireworks and Vertex Imagen models carry no or stale deprecation dates
Azure eu and us data-zone tiers are missing for 28 OpenAI models

How it solves it:

Rereads each provider's published price page and rewrites the changed fields
Adds 57 azure/eu/* and azure/us/* rows priced from the Azure retail API
Adds gemini/gemini-3.8-live and gemini/gemini-3.8-live-extended-thinking
Sets deprecation_date on 30 Together AI, Fireworks and Vertex Imagen rows
Stamps a source URL on 228 rows so every value is traceable
Deletes four tests that pinned vendor prices and broke on this sync

User Flow

Before: a proxy admin routing azure/gpt-5.6-sol sees spend logged at the old, higher price

They send POST https://litellm-domain/v1/chat/completions with "model": "azure/gpt-5.6-sol"
The response comes back fine, but https://litellm-domain/ui/?page=logs bills input at $5.00 and output at $30.00 per 1M tokens
They send POST https://litellm-domain/v1/chat/completions with "model": "azure/eu/gpt-5.2" and get a 400 because the model is not in the catalog

After: the same requests are billed at the current Azure price and the eu tier resolves

They send POST https://litellm-domain/v1/chat/completions with "model": "azure/gpt-5.6-sol"
https://litellm-domain/ui/?page=logs bills input at $4.00 and output at $20.00 per 1M tokens, matching Azure's page
They send POST https://litellm-domain/v1/chat/completions with "model": "azure/eu/gpt-5.2" and it is priced at the eu data-zone rate

Relevant issues

Affected release

Linear ticket

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

I have added meaningful tests
The handful of test files covering my change pass locally, e.g. uv run pytest tests/test_litellm/<your_test_file>.py -v. Leave the suites (make test-unit-*, make test-unit) to CI: it finishes in ~15 minutes where a laptop takes an hour or more
My PR passes all required CI/CD checks (e.g., lint, schema.d.ts sync check, etc.)
My PR's scope is as isolated as possible; it only solves 1 specific problem
I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Delays in PR merge?

If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).

Screenshots / Proof of Fix

Live proxy proof does not apply to an automated price sync. Each value was read from the provider's own price page, and the source field on every touched row points at that page. The price-check bot compared every changed row against models.dev and OpenRouter on each push; the two remaining differences are listed under Caveats and were reviewed and accepted. Per-provider sync reports are in the bot comments on this PR

Type

Chore

What changed

59 new rows, 278 changed rows, nothing removed, in both model_prices_and_context_window.json and the backup copy

Price fields that move on existing rows:

azure/gpt-5.6-sol and its eu/us tiers: input 5.00 -> 4.00, output 30.00 -> 20.00, cache read 0.50 -> 0.40, cache write 6.25 -> 5.00 per 1M
azure/gpt-4o-2024-11-20, azure/gpt-4o-mini-2024-07-18, azure/o1-mini: drop the 10% premium that had been applied to the base row
azure/eu|us/gpt-5.1*, gpt-5.4*, gpt-5.1-codex-mini: rounding fixes on input and cache read (1.38 -> 1.375 per 1M and the like)
azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8: input 1.41 -> 0.25, output 0.35 -> 1.00 per 1M per the Azure retail API
azure_ai/FW-GLM-5.2-Fast, FW-Inkling, FW-Nemotron-3-Ultra-NVFP4: up 10%
azure_ai/Phi-4-mini-reasoning: input 0.08 -> 0.075, output 0.32 -> 0.30 per 1M
gemini/gemini-robotics-er-2-preview: halved to 1.00 / 5.00 per 1M
Gemini TTS and live previews gain output_cost_per_audio_token and input_cost_per_second
OpenAI, Azure and Bedrock rows gain or correct batch, flex and priority tier prices

Deprecation dates:

18 Together AI rows (14 newly dated, 4 moved 2026-09-14 -> 2026-09-15)
4 Fireworks rows set to 2026-08-27
8 Vertex Imagen rows set to 2026-06-30 (imagegeneration@006 to 2025-09-24)

130 of the 278 changed rows change only the source field

The two new gemini/gemini-3.8-live* rows carry tpm: 250000 and rpm: 10, copied from the sibling gemini/gemini-3.1-flash-live-preview row, so every gemini/ chat row keeps rate limits

Tests removed because they pinned catalog prices and failed once the catalog moved to the provider's current numbers:

test_azure_ai_fw_cost_per_token (Azure AI Foundry FW-* per-token prices)
test_sub_input_cache_write_price_is_an_extra_saving (azure/eu/gpt-4o-2024-11-20 cache write price)
test_azure_gpt_5_6_cache_write_tokens_are_billed (azure/gpt-5.6-luna literal rates)
test_azure_gpt_5_6_rates_match_azure_price_page (1.25x cache write and 1.1x data zone ratios from a dated price page)

A follow up PR replaces the wider set of price pinning tests with catalog independent ones

Caveats (if any)

Medium

azure/gpt-5.6-sol cache read 0.40 and cache write 5.00 per 1M; models.dev lists 0.50 and 6.25 for Azure. Azure's page states the lower values, so the PR keeps them
azure_ai/Phi-4-mini-reasoning context stays 131072; models.dev says 128000. Not changed by this PR
Azure o1, eu/o1, us/o1: parser found no input price, left as is
Four OpenAI long-context rows skipped: no threshold stated on the page
gemini-robotics-er-2-streaming-preview: no pricing table on page, left as is

Low

75 azure/eu/* and azure/us/* tiers have no third-party comparison; models.dev and OpenRouter do not list data-zone tiers
9 keys are in neither models.dev nor OpenRouter and rest on the provider page alone
Rows without a serverless token price were not read

QA runbook

Only test deletions, no e2e files are touched. Run uv run pytest tests/test_litellm/test_cost_calculator.py tests/test_litellm/test_utils.py -k "gemini or azure" -q to confirm the remaining cost and model info tests still pass against the new catalog

Final Attestation

The tests check the right things, including the edge cases, and regressions in the respective real-world customer use-cases are not possible after this PR

Link to Devin session: https://app.devin.ai/sessions/de5c4a28cf3f4b64a6a4b56dc4b46429
Open in Devin Desktop: https://app.devin.ai/desktop/session/de5c4a28cf3f4b64a6a4b56dc4b46429?variant=devin

Note

Medium Risk
Large catalog edits directly change how LiteLLM bills and reports spend for many deployments; wrong values would misstate costs, though runtime billing logic is unchanged.

Overview
Refreshes the built-in model cost map (model_prices_and_context_window.json and its backup) so proxy spend logs and completion_cost match current vendor pricing across Azure, Azure AI, Gemini, OpenAI, Bedrock, Together AI, Fireworks, and Vertex (~278 updated rows, ~59 new).

Catalog additions and corrections: Adds Azure EU/US data-zone keys (e.g. azure/eu/*, azure/us/*) and new Gemini live models; updates token, cache, batch/flex/priority, and modality-specific rates (notably lower azure/gpt-5.6-sol input/output/cache prices, Azure AI Foundry fixes, Gemini TTS/live audio fields). Sets deprecation_date on ~30 Together AI, Fireworks, and Vertex Imagen entries. Stamps a traceable source URL on many rows.

Tests: Removes four unit tests that asserted fixed catalog numbers (Azure AI FW-* pricing, Azure EU cache write, GPT-5.6 cache/ratio checks) so CI does not break on routine price syncs; remaining cost-calculator tests still exercise behavior without pinning vendor list prices.

^{Reviewed by Cursor Bugbot for commit b9ab362. Bugbot is set up for automated code reviews on this repo. Configure here.}

CLAassistant · 2026-09-15T00:36:29Z

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 2 committers have signed the CLA.

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

devin-ai-integration · 2026-09-15T00:37:22Z

Price check at 5dc31fa: 4 models changed, 0 mismatches against models.dev; none listed on OpenRouter. Details in #litellm-provider-info-sync.

codspeed · 2026-09-15T00:38:25Z

Merging this PR will not alter performance

✅ 31 untouched benchmarks

_{Comparing litellm-providers/price-sync (b9ab362) with main (f0474bb)}

greptile-apps · 2026-09-15T00:38:40Z

Greptile Summary

This PR synchronizes provider pricing, model metadata, regional Azure entries, and deprecation dates across the primary and backup model catalogs.

Adds Gemini 3.8 live model rate-limit metadata in the changes since the previous review.
Removes Azure GPT-5.6 tests that pinned vendor-specific prices.
Keeps the primary and backup catalogs synchronized.

Confidence Score: 5/5

The PR appears safe to merge, with no outstanding blocking findings.

No new actionable defect was established. The earlier incorrect Gemini per-second billing finding was withdrawn and resolved. devin-ai-integration[bot] accepted the temporary pricing-test coverage gap because the removed assertions pinned changing vendor prices and stated that catalog-independent replacements are planned; that thread was subsequently resolved.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Updates provider pricing and metadata, including adding rate limits to the new Gemini 3.8 live rows.
litellm/model_prices_and_context_window_backup.json	Mirrors the pricing and metadata updates from the primary model catalog.
tests/test_litellm/test_cost_calculator.py	Removes Azure GPT-5.6 vendor-price assertions, preserving the previously acknowledged temporary coverage gap.
tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py	Removes Azure AI Foundry tests that pinned synchronized catalog prices.
tests/test_litellm/proxy/spend_tracking/test_savings.py	Removes the vendor-coupled cache-write savings assertion covered by the previous review discussion.

_{Reviews (4): Last reviewed commit: "fix(prices): add tpm and rpm to gemini 3..." | Re-trigger Greptile}

codecov · 2026-09-15T00:43:36Z

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

devin-ai-integration · 2026-09-15T01:37:30Z

Price check at 956b211: 25 Bedrock entries only gained a source field, 4 Gemini models changed, 0 mismatches. Details in #litellm-provider-info-sync.

devin-ai-integration · 2026-09-15T16:29:52Z

Price check at a6bcc44: 25 Bedrock entries only gained a source field, 4 Gemini entries changed secondary fields, 0 mismatches. Details in #litellm-provider-info-sync.

devin-ai-integration · 2026-09-15T16:32:39Z

Price check at 3986ea1: 18 entries changed only batch or audio fields, 0 mismatches against models.dev and OpenRouter. Details in #litellm-provider-info-sync

devin-ai-integration · 2026-09-15T16:47:44Z

Price check at 8c1300b: 18 entries changed only batch, audio or image fields, 0 mismatches against models.dev and OpenRouter. Details in #litellm-provider-info-sync

devin-ai-integration · 2026-09-15T16:52:51Z

Price check at 77812c6: 43 entries changed only source, batch, audio, image or per-second fields, 0 mismatches against models.dev and OpenRouter. Details in #litellm-provider-info-sync

cursor

Stale Bugbot comment from a previous run.

devin-ai-integration · 2026-09-15T17:06:02Z

Price check at 8e2effb: 39 entries changed only source, batch, audio, image or per-second fields, 0 mismatches on fields this PR changes. Details in #litellm-provider-info-sync

devin-ai-integration · 2026-09-15T17:08:25Z

Price check at 6ce0144: 43 entries changed only source, batch, audio, image or per-second fields, 0 mismatches on fields this PR changes. Details in #litellm-provider-info-sync

gemini-2.5-flash-preview-tts: output_cost_per_audio_token, input_cost_per_token_batches gemini/gemini-2.5-flash-preview-tts: output_cost_per_audio_token, input_cost_per_token_batches gemini-3.1-flash-live-preview: input_cost_per_second gemini/gemini-3.1-flash-live-preview: input_cost_per_second

anthropic.claude-fable-5: anthropic.claude-fable-5-1: anthropic.claude-opus-4-7: anthropic.claude-opus-4-8: anthropic.claude-opus-5: anthropic.claude-sonnet-4-6: anthropic.claude-sonnet-5: global.anthropic.claude-fable-5: global.anthropic.claude-fable-5-1: global.anthropic.claude-opus-4-7: global.anthropic.claude-opus-4-8: global.anthropic.claude-opus-5: global.anthropic.claude-sonnet-4-6: global.anthropic.claude-sonnet-5: us-gov.anthropic.claude-fable-5-1: us-gov.anthropic.claude-opus-4-8: us-gov.anthropic.claude-opus-5: us-gov.anthropic.claude-sonnet-5: us.anthropic.claude-fable-5: us.anthropic.claude-fable-5-1: us.anthropic.claude-opus-4-7: us.anthropic.claude-opus-4-8: us.anthropic.claude-opus-5: us.anthropic.claude-sonnet-4-6: us.anthropic.claude-sonnet-5:

chatgpt-image-latest: input_cost_per_image_token_batches gemini-2.0-flash: input_cost_per_audio_token_batches gemini-2.0-flash-lite: input_cost_per_audio_token_batches gemini-2.5-flash: input_cost_per_audio_token_batches gemini-2.5-flash-lite: input_cost_per_audio_token_batches gemini-3-flash-preview: input_cost_per_audio_token_batches vertex_ai/gemini-3-flash-preview: input_cost_per_audio_token_batches gemini-3.1-flash-lite: input_cost_per_audio_token_batches vertex_ai/gemini-3.1-flash-lite: input_cost_per_audio_token_batches gpt-image-1: input_cost_per_image_token_batches gpt-image-1-mini: input_cost_per_image_token_batches gpt-image-1.5: input_cost_per_image_token_batches gpt-image-1.5-2025-12-16: input_cost_per_image_token_batches gpt-image-2: input_cost_per_image_token_batches

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

us-gov.anthropic.claude-fable-5-1: us-gov.anthropic.claude-opus-4-8: us-gov.anthropic.claude-opus-5: us-gov.anthropic.claude-sonnet-5:

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

devin-ai-integration · 2026-09-16T01:38:47Z

Price check at 91c8d1c: 86 models changed, 2 mismatches against models.dev and OpenRouter (azure/gpt-5.6-sol cache prices, Llama-4-Maverick OpenRouter only); 75 Azure eu/us tiers have no direct comparison. Details in #litellm-provider-info-sync.

… Google Gemini, sync failed: AWS Bedrock, 6 held] gemini/gemini-3.1-pro-preview-customtools: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost_flex

devin-ai-integration · 2026-09-16T01:48:02Z

Price check at c5a388a: 86 keys with price changes, 75 regional tiers with no direct comparison, 1 mismatch (azure/gpt-5.6-sol cache fields). Details in #litellm-provider-info-sync

gemini/gemini-robotics-er-2-preview: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, input_cost_per_token_batches, output_cost_per_token_batches

devin-ai-integration · 2026-09-16T03:48:33Z

Price check at 641dcd5: 87 keys changed, 75 regional tiers with no direct comparison, 2 mismatches (azure/gpt-5.6-sol cache fields, Phi-4-mini-reasoning context). Details in #litellm-provider-info-sync

together_ai/google/gemma-4-31B-it: deprecation_date together_ai/intfloat/multilingual-e5-large-instruct: deprecation_date together_ai/openai/gpt-oss-20b: deprecation_date together_ai/thinkingmachines/Inkling-Small: deprecation_date

devin-ai-integration · 2026-09-16T13:18:24Z

Price check at 0443605: 87 keys changed, 75 regional tiers with no direct comparison, 2 mismatches (azure/gpt-5.6-sol cache fields, Phi-4-mini-reasoning context), details in #litellm-provider-info-sync

devin-ai-integration · 2026-09-16T16:21:38Z

Price check at d398c91: 87 keys changed, 75 regional tiers with no direct comparison, 1 mismatch (azure/gpt-5.6-sol cache fields), details in #litellm-provider-info-sync

azure_ai/Codestral-2501: azure_ai/cohere-command-a: azure_ai/deepseek-r1: azure_ai/deepseek-v3: azure_ai/deepseek-v3-0324: azure_ai/deepseek-v3.1: azure_ai/deepseek-v3.2: azure_ai/deepseek-v3.2-speciale: azure_ai/deepseek-v4-flash: azure_ai/DeepSeek-V4-Flash-0731: azure_ai/deepseek-v4-pro: azure_ai/embed-v-4-0: azure_ai/FW-DeepSeek-V3.2: azure_ai/FW-DeepSeek-V4-Pro: azure_ai/FW-GLM-5: azure_ai/FW-GLM-5.1: azure_ai/FW-GLM-5.2: azure_ai/FW-GLM-5.2-Fast: azure_ai/FW-Inkling: azure_ai/FW-Kimi-K2.5: azure_ai/FW-Kimi-K2.6: azure_ai/FW-Kimi-K2.7-Code: azure_ai/FW-Kimi-K3: azure_ai/FW-MiniMax-M2.5: azure_ai/FW-MiniMax-M3: azure_ai/FW-Nemotron-3-Ultra-NVFP4: azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B: azure_ai/gpt-oss-120b: azure_ai/grok-3: azure_ai/global/grok-3: azure_ai/grok-3-mini: azure_ai/global/grok-3-mini: azure_ai/grok-4: azure_ai/grok-4-1-fast-non-reasoning: azure_ai/grok-4-1-fast-reasoning: azure_ai/grok-4-20-non-reasoning: azure_ai/grok-4-20-reasoning: azure_ai/grok-4-fast-non-reasoning: azure_ai/grok-4-fast-reasoning: azure_ai/grok-4.3: azure_ai/grok-4.6: azure_ai/grok-code-fast-1: azure_ai/kimi-k2.5: azure_ai/kimi-k2.6: azure_ai/kimi-k2.7-code: azure_ai/Llama-3.3-70B-Instruct: azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8: azure_ai/MAI-DS-R1: azure_ai/MAI-Image-2.5: azure_ai/MAI-Image-2.5-Flash: azure_ai/MAI-Image-2e: azure_ai/MAI-Thinking-1: azure_ai/mistral-large-3: azure_ai/Phi-3-medium-128k-instruct: azure_ai/Phi-3-medium-4k-instruct: azure_ai/Phi-3-mini-128k-instruct: azure_ai/Phi-3-mini-4k-instruct: azure_ai/Phi-3-small-128k-instruct: azure_ai/Phi-3-small-8k-instruct: azure_ai/Phi-3.5-mini-instruct:

devin-ai-integration · 2026-09-16T16:28:10Z

Price check at 8096856: 87 keys changed, 75 regional tiers with no direct comparison, 2 mismatches (azure/gpt-5.6-sol cache fields, Phi-4-mini-reasoning context), details in #litellm-provider-info-sync

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

devin-ai-integration · 2026-09-16T16:34:33Z

Price check at cab6732: 87 keys changed, 75 regional tiers with no direct comparison, 2 mismatches (azure/gpt-5.6-sol cache fields, Phi-4-mini-reasoning context), details in #litellm-provider-info-sync

cursor

Stale Bugbot comment from a previous run.

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

devin-ai-integration · 2026-09-16T16:51:14Z

Price check at b9ab362: 87 keys changed, 75 regional tiers with no direct comparison, 1 mismatch (azure/gpt-5.6-sol cache fields), details in #litellm-provider-info-sync

mateo-berri · 2026-09-16T17:25:44Z

@greptileai

mateo-berri · 2026-09-16T17:36:58Z

bugbot run

mateo-berri

LGTM. Thanks!

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 b9ab362. Configure here.}

berriai-litellm-provider-info-sync Bot requested a review from a team September 15, 2026 00:36

berriai-litellm-provider-info-sync Bot requested a review from mateo-berri as a code owner September 15, 2026 00:36

greptile-apps Bot reviewed Sep 15, 2026

View reviewed changes

Comment thread model_prices_and_context_window.json

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

fix(cost): bill audio input once when both per-token and per-second rates exist #41158

Closed

4 of 6 tasks

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync Vertex AI prices: 4 models~~ chore(prices): sync AWS Bedrock prices: 25 models Sep 15, 2026

This was referenced Sep 15, 2026

chore(prices): drop unused input_cost_per_second from gemini-3.1-flash-live-preview #41165

Closed

test(pricing): allow a source link on Bedrock GovCloud rows the AWS offer file prices #41167

Open

devin-ai-integration Bot force-pushed the litellm-providers/price-sync branch from 956b211 to a6bcc44 Compare September 15, 2026 16:28

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync AWS Bedrock prices: 25 models~~ chore(prices): sync prices for 2 providers: 14 models Sep 15, 2026

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync prices for 2 providers: 14 models~~ chore(prices): sync AWS Bedrock prices: 4 models Sep 15, 2026

cursor Bot reviewed Sep 15, 2026

View reviewed changes

Comment thread model_prices_and_context_window.json

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

test(pricing): let synced GovCloud Bedrock rows cite the AWS price list #41263

Merged

3 of 5 tasks

berriai-litellm-provider-info-sync Bot and others added 6 commits September 15, 2026 17:42

chore(prices): drop source from us-gov rows to match usgov pricing test

68f9732

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

chore(prices): sync AWS Bedrock prices: 4 models

1b69cfc

us-gov.anthropic.claude-fable-5-1: us-gov.anthropic.claude-opus-4-8: us-gov.anthropic.claude-opus-5: us-gov.anthropic.claude-sonnet-5:

chore(prices): drop source from us-gov rows again

a8dd139

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

chore(prices): sync Google Gemini prices: 1 model [enrichment failed:…

c5a388a

… Google Gemini, sync failed: AWS Bedrock, 6 held] gemini/gemini-3.1-pro-preview-customtools: input_cost_per_token_flex, output_cost_per_token_flex, cache_read_input_token_cost_flex

chore(prices): sync Google Gemini prices: 1 model

641dcd5

gemini/gemini-robotics-er-2-preview: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, input_cost_per_token_batches, output_cost_per_token_batches

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync Google Gemini prices: 1 model [enrichment failed: Google Gemini, sync failed: AWS Bedrock, 6 held]~~ chore(prices): sync Google Gemini prices: 1 model Sep 16, 2026

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync Google Gemini prices: 1 model~~ chore(prices): sync Together AI prices: 4 models, 4 deprecated Sep 16, 2026

Merge remote-tracking branch 'origin/main' into HEAD

d398c91

devin-ai-integration Bot changed the title ~~chore(prices): sync Together AI prices: 4 models, 4 deprecated~~ chore(prices): sync Azure, Azure AI, Gemini, OpenAI, Bedrock, Together AI, Fireworks and Vertex prices: 278 models, 59 new, 30 deprecated Sep 16, 2026

berriai-litellm-provider-info-sync Bot changed the title ~~chore(prices): sync Azure, Azure AI, Gemini, OpenAI, Bedrock, Together AI, Fireworks and Vertex prices: 278 models, 59 new, 30 deprecated~~ chore(prices): sync Azure prices: 247 models Sep 16, 2026

test: drop price-pinning tests that break on catalog updates

cab6732

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

greptile-apps Bot reviewed Sep 16, 2026

View reviewed changes

Comment thread tests/test_litellm/llms/azure_ai/test_azure_ai_fw_models_metadata.py

cursor Bot reviewed Sep 16, 2026

View reviewed changes

Comment thread model_prices_and_context_window.json

kerry and others added 2 commits September 16, 2026 16:49

test: drop azure gpt-5.6 rate tests pinned to a dated price page

eed760a

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

fix(prices): add tpm and rpm to gemini 3.8 live rows

b9ab362

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

devin-ai-integration Bot changed the title ~~chore(prices): sync Azure prices: 247 models~~ chore(prices): sync Azure, Azure AI, Gemini, OpenAI, Bedrock, Together AI, Fireworks and Vertex prices: 278 models, 59 new, 30 deprecated Sep 16, 2026

devin-ai-integration Bot mentioned this pull request Sep 16, 2026

test: delete unit-test assertions that pin cost-map prices, limits and deprecation dates #41443

Merged

3 of 6 tasks

mateo-berri approved these changes Sep 16, 2026

View reviewed changes

kerry-berri merged commit 4e99640 into main Sep 16, 2026
88 checks passed

cursor Bot reviewed Sep 16, 2026

View reviewed changes

Conversation

berriai-litellm-provider-info-sync Bot commented Sep 15, 2026 • edited by cursor Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

TLDR

User Flow

Relevant issues

Affected release

Linear ticket

Pre-Submission checklist

Delays in PR merge?

Screenshots / Proof of Fix

Type

What changed

Caveats (if any)

Medium

Low

QA runbook

Final Attestation

Uh oh!

CLAassistant commented Sep 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

devin-ai-integration Bot commented Sep 15, 2026

Uh oh!

codspeed Bot commented Sep 15, 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!

greptile-apps Bot commented Sep 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Greptile Summary

Confidence Score: 5/5

Uh oh!

Uh oh!

codecov Bot commented Sep 15, 2026

Codecov Report

Uh oh!

devin-ai-integration Bot commented Sep 15, 2026

Uh oh!

devin-ai-integration Bot commented Sep 15, 2026

Uh oh!

devin-ai-integration Bot commented Sep 15, 2026

Uh oh!

devin-ai-integration Bot commented Sep 15, 2026

Uh oh!

devin-ai-integration Bot commented Sep 15, 2026

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!

devin-ai-integration Bot commented Sep 15, 2026

Uh oh!

devin-ai-integration Bot commented Sep 15, 2026

Uh oh!

devin-ai-integration Bot commented Sep 16, 2026

Uh oh!

devin-ai-integration Bot commented Sep 16, 2026

Uh oh!

devin-ai-integration Bot commented Sep 16, 2026

Uh oh!

devin-ai-integration Bot commented Sep 16, 2026

Uh oh!

devin-ai-integration Bot commented Sep 16, 2026

Uh oh!

devin-ai-integration Bot commented Sep 16, 2026

Uh oh!

devin-ai-integration Bot commented Sep 16, 2026

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!

devin-ai-integration Bot commented Sep 16, 2026

Uh oh!

mateo-berri commented Sep 16, 2026

Uh oh!

berriai-litellm-provider-info-sync Bot commented Sep 15, 2026 •

edited by cursor Bot

Loading

CLAassistant commented Sep 15, 2026 •

edited

Loading

codspeed Bot commented Sep 15, 2026 •

edited

Loading

greptile-apps Bot commented Sep 15, 2026 •

edited

Loading

cursor Bot left a comment •

edited

Loading

cursor Bot left a comment •

edited

Loading