scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108
53005 commits 3347 branches 1448 tags 5 GiB
Commit graph

2458 commits

Author SHA1 Message Date
devin-ai-integration[bot]
793627ce83
fix(cost-map): add supports_reasoning to azure/eu/gpt-6-astra (#42989) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 09:57:52 -07:00
devin-ai-integration[bot]
de314f8271
fix(cost-map): take the later azure deprecation date for gpt-4.1-nano, gpt-4o-transcribe and gpt-realtime-2.1 (#42986) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 09:57:05 -07:00
devin-ai-integration[bot]
1ceb8fb08e
fix(cost-map): align openrouter deepseek-v4-pro cache hit price with cache read (#42985) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 09:45:09 -07:00
devin-ai-integration[bot]
7a9bfb4f1c
feat(azure): add gpt-audio and gpt-realtime alias rows from the Azure model list (#42981) 
* feat(azure): add gpt-audio and gpt-realtime alias rows from the Azure model list

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

* fix(azure): keep existing catalog formatting untouched

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 09:44:33 -07:00
devin-ai-integration[bot]
bd55afc0f8
fix(cost-map): add vertex ai priority audio input prices for gemini flash rows (#42980) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 09:30:37 -07:00
devin-ai-integration[bot]
cc7aaae748
fix(cost-map): sync openrouter deepseek-v4-pro prices (#42978) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 09:27:11 -07:00
devin-ai-integration[bot]
991c339946
fix(cost-map): sync openrouter deepseek v4 flash, v4 pro and v4.1 flash prices (#42974) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 08:53:31 -07:00
devin-ai-integration[bot]
cfa2830bde
fix(bedrock): extrapolate global cris pricing for gpt-5.4 and gpt-5.5 (#42971) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 08:30:48 -07:00
devin-ai-integration[bot]
553f0b6ee7
feat(cost-map): sync azure models, add MAI-Image-2.6, deepseek-v4.1-flash, muse-spark-1.3 (#42970) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 08:27:42 -07:00
devin-ai-integration[bot]
58d7cafb97
fix(cost-map): sync openrouter deepseek-v4-pro prices (#42969) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 08:24:27 -07:00
devin-ai-integration[bot]
b8f3ba03b3
fix(cost-map): sync openrouter deepseek-v4-pro prices (#42964) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 07:57:26 -07:00
devin-ai-integration[bot]
11ed3335c8
fix(cost-map): sync openrouter deepseek-v4-pro prices (#42956) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 07:18:08 -07:00
devin-ai-integration[bot]
77c7a870d5
fix(cost-map): add azure realtime, audio and partner model rows (#42954) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 06:55:14 -07:00
devin-ai-integration[bot]
3acdfda19c
fix(cost-map): add batch prices for vertex gemini-3.8-flash-cyber (#42953) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 06:52:06 -07:00
devin-ai-integration[bot]
785d4974ba
fix(cost-map): sync openrouter prices for deepseek v4 and glm-5.3 (#42952) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 06:49:17 -07:00
devin-ai-integration[bot]
c4b56b6ada
fix(cost-map): update azure gpt-4.1-nano and gpt-4o-2024-05-13 retirement dates (#42947) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 06:15:55 -07:00
devin-ai-integration[bot]
ddc7ee6838
feat(bedrock): add gpt-5.4 and gpt-5.5 us and global inference profile pricing (#42941) 
* feat(bedrock): add gpt-5.4 and gpt-5.5 us and global inference profile pricing

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

* fix(bedrock): drop supports_max_reasoning_effort from gpt-5.4 and gpt-5.5 rows

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 04:54:10 -07:00
devin-ai-integration[bot]
2eeb16266b
fix(cost-map): sync vertex-ai rows (gemma 4 maas cache price, chirp_2) (#42942) 
* fix(cost-map): sync vertex-ai rows (gemma 4 maas cache price, chirp_2)

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

* test(vertex-ai): expect chirp_2 as speech-to-text model now that catalog row exists

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 04:39:09 -07:00
devin-ai-integration[bot]
8bbe7edb71
fix(cost-map): add azure deprecation dates for regional gpt-6 rows (#42933) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 03:03:53 -07:00
devin-ai-integration[bot]
b550db1b4f
fix(cost-map): update openrouter kimi-k2.7-code input price (#42932) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 02:58:44 -07:00
devin-ai-integration[bot]
04f3ade124
feat(cost-map): add wandb DeepSeek-V4.1-Flash and gemma-4-26B-A4B-it (#42924) 
* feat(cost-map): add wandb DeepSeek-V4.1-Flash and gemma-4-26B-A4B-it

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

* fix(cost-map): mark wandb gemma-4-26B-A4B-it as reasoning capable

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 02:07:12 -07:00
devin-ai-integration[bot]
1c8a0ff602
fix(cost-map): add azure deprecation dates for gpt-6 and gpt-realtime-whisper (#42897) 
* fix(cost-map): add azure deprecation dates for gpt-6 and gpt-realtime-whisper

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

* fix(cost-map): add azure deprecation dates to dated gpt-6 keys

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 01:06:54 -07:00
devin-ai-integration[bot]
d11705a24d
fix(cost-map): source for bedrock mantle gpt-5.6 luna, sol, terra and grok-4.6 (#42898) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-24 01:04:31 -07:00
devin-ai-integration[bot]
a5b9b6da4d
feat(cost-map): add vertex_ai/gemini-3.8-live (#42891) 
* feat(cost-map): add vertex_ai/gemini-3.8-live

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

* fix(cost-map): price vertex_ai/gemini-3.8-live video tokens

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 23:41:10 -07:00
devin-ai-integration[bot]
42d8d08815
fix(cost-map): source and chat completions endpoint for bedrock mantle gpt-5.4 and gpt-5.5 (#42890) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 23:25:24 -07:00
devin-ai-integration[bot]
8f7cea5fcd
fix(cost-map): sync openrouter prices and add fireworks ember-1 (#42889) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 23:21:59 -07:00
devin-ai-integration[bot]
0094cff47a
fix(cost-map): add azure gpt-realtime-mini-2025-10-06 deprecation date (#42885) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 22:38:31 -07:00
devin-ai-integration[bot]
6b1ec4cd3a
fix(models): correct fireworks kimi k3 us pricing to the published rate (#42884) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 22:26:59 -07:00
devin-ai-integration[bot]
dfb61e9b48
fix(cost-map): add azure gpt-realtime-mini deprecation date (#42883) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 22:24:37 -07:00
devin-ai-integration[bot]
001179a636
fix(cost-map): sync vertex-ai deprecation dates from Vertex model lifecycle pages (#42882) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 22:21:05 -07:00
devin-ai-integration[bot]
0fb999b613
fix(cost-map): halve openrouter deepseek-v4-flash-0731 output price (#42881) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 22:18:28 -07:00
devin-ai-integration[bot]
b21b20ed13
feat(vertex_ai): add gemini-3.8-flash-cyber pricing (#42879)
Some checks failed
LiteLLM Rust / rust-lint (push) Waiting to run
Details
LiteLLM Rust / rust-test (push) Waiting to run
Details
LiteLLM Rust / rust-wheel (push) Waiting to run
Details
Terraform Provider / gofmt, vet, build, test (push) Waiting to run
Details
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Waiting to run
Details
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Details
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled
Details 
* feat(vertex_ai): add gemini-3.8-flash-cyber pricing

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

* fix(vertex_ai): mark gemini-3.8-flash-cyber minimal reasoning unsupported

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 21:55:55 -07:00
devin-ai-integration[bot]
9d12c217af
fix(models): correct gemini robotics er 2 preview audio input price (#42877) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 21:42:23 -07:00
devin-ai-integration[bot]
e99c5d30b6
feat(cost-map): add retired azure gpt-5 chat and o1-preview data zone rows (#42878) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 21:32:27 -07:00
devin-ai-integration[bot]
7370650d91
fix(model_prices): bedrock bare Claude ids priced at the Global SKU (aws-bedrock sync) (#42875) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 21:27:25 -07:00
devin-ai-integration[bot]
15a2bd8b28
fix(models): add fireworks 2026-09-25 deprecation dates for glm 5.2, kimi k2.6, kimi k2.7 code, deepseek v4 and muse glimmer serverless rows (#42874) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 21:07:44 -07:00
devin-ai-integration[bot]
871f562f72
fix(models): add openai deprecation date for gpt-5-chat-latest and gpt-5-chat (#42872) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 21:01:10 -07:00
devin-ai-integration[bot]
1f1817ed39
fix(models): add azure gpt-4o-mini-transcribe and gpt-4o-mini-tts deprecation dates (#42873) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 21:00:33 -07:00
devin-ai-integration[bot]
58e41e697b
chore(vertex_ai): add deprecation dates for retired claude 3 and jamba 1.5 partner models (#42867) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 20:37:43 -07:00
devin-ai-integration[bot]
184969df37
fix(models): add fireworks deprecation date for glm 5.2 fast serverless rows (#42866) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 20:28:04 -07:00
devin-ai-integration[bot]
a4f69e058c
fix(model_prices): registry audit 2026-09-23, in-region Bedrock Claude prices (#42779) 
* fix(model_prices): registry audit 2026-09-23, in-region Bedrock Claude and OpenRouter price fixes

Absorbs #42698

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

* fix(model_prices): keep registry formatting unchanged

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

* test: use eu.amazon.nova-pro for regional pricing probe after in-region parity

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

* test: lock in-region parity for bare Bedrock Claude ids

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

* test: compare every pricing field for bare Bedrock Claude parity

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

* fix(model-catalog): add above_32k cost fields to ModelInfo round-trip

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

* Revert "fix(model-catalog): add above_32k cost fields to ModelInfo round-trip"

This reverts commit c71d5a3de3.

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: coldStoneSoul <shekharpachlore@gmail.com>
 2026-09-24 02:47:29 +00:00
devin-ai-integration[bot]
153f13b913
fix(models): add fireworks deprecation dates for kimi k2.6 fast, kimi k2.7 code fast and glm 5.2 fast us (#42849) 
* fix(models): add fireworks deprecation dates for kimi k2.6 fast, kimi k2.7 code fast and glm 5.2 fast us

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

* fix(models): add the same fireworks deprecation dates to the router twin rows

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 19:35:22 -07:00
devin-ai-integration[bot]
660e6746e4
feat(bedrock): add 17 aws-bedrock cost map rows from provider sync (#42852) 
* feat(bedrock): add 22 aws-bedrock cost map rows from provider sync

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

* fix(bedrock): mark mythos-preview regional rows as supporting prompt caching

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

* fix(bedrock): drop bare openai.gpt-5.6-sol row shadowing the bedrock_mantle fallback

get_model_info checks the bare split_model before bedrock_mantle/<model>, so the new bare key made bedrock_mantle/us-east-2/openai.gpt-5.6-sol resolve to the bedrock_converse row instead of falling back to bedrock_mantle/openai.gpt-5.6-sol

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

* fix(bedrock): drop bare OpenAI and xAI keys already covered by bedrock_mantle rows

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 19:16:34 -07:00
devin-ai-integration[bot]
80c39a08c8
feat(models): add gemini lyria-realtime-exp row inherited from lyria-3.5 (#42848) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 19:00:47 -07:00
devin-ai-integration[bot]
545afadba5
feat(models): add openrouter/openai/gpt-oss-120b:batch from the OpenRouter models API (#42847) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 18:57:49 -07:00
devin-ai-integration[bot]
c21f782227
fix(models): add the sora-2-pro shutdown date to the sora-2-pro-high-res rows (#42846) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 18:54:09 -07:00
devin-ai-integration[bot]
d4b0a547b2
chore(models): add deprecation_date to claude-mythos-preview from the Anthropic deprecations page (#42845) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 18:51:13 -07:00
devin-ai-integration[bot]
a314fe858f
feat(models): add 39 together_ai chat rows priced by the Together models API (#42851) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 18:50:59 -07:00
devin-ai-integration[bot]
b431d12cf0
fix(models): add the June 1, 2026 retirement date to the vertex_ai gemini-2.0-flash rows (#42850) 
Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 18:49:20 -07:00
devin-ai-integration[bot]
61996e1837
feat(models): add openai chat-latest, codex and deep-research rows from the model docs (#42834) 
* feat(models): add openai chat-latest, codex and deep-research rows from the model docs

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

* fix(models): mark new openai vision models as supporting pdf input

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-23 18:27:01 -07:00