Litellm

What's Changed
* [Fix] OTEL - Unsupported | type annotations in python3.9 by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5548
* Update Hugging Face Doc by gary149 in https://github.com/BerriAI/litellm/pull/5411
* [Fix-Datdog Logger] Log exceptions when callbacks faces an error by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5570
* fix(navbar.tsx): only show 'get enterprise license' if user is not already a premium user by krrishdholakia in https://github.com/BerriAI/litellm/pull/5568
* LiteLLM Minor Fixes and Improvements (08/06/2024) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5567
* [Feat-Proxy] Use DB Views to Get spend per Tag (Usage endpoints) by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5574
* [Feat] Allow setting duration time when regenerating key by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5566
* [Feat] Add cost tracking for cohere rerank by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5573
* Allow client-side credentials to be sent to proxy (accept only if complete credentials are given) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5575

New Contributors
* gary149 made their first contribution in https://github.com/BerriAI/litellm/pull/5411

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.19...v1.44.21



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.21



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 130.0 | 166.20606541064828 | 6.339987548576783 | 0.0 | 1897 | 0 | 112.93849100002262 | 2116.0177159999876 |
| Aggregated | Passed ✅ | 130.0 | 166.20606541064828 | 6.339987548576783 | 0.0 | 1897 | 0 | 112.93849100002262 | 2116.0177159999876 |

v1.44.19-stable
Excited to Launch the ability for LiteLLM Gateway (Proxy) Users to - Create Virtual Keys for 100+ LLMs and track their own Usage Start here: https://github.com/BerriAI/litellm/releases/tag/v1.44.19-stable

✨ [UI] Show when a virtual key expires

✨ UI - show expired virtual keys on Admin UI



What's Changed
* fix KeyError when call deepseek api by wolf-joe in https://github.com/BerriAI/litellm/pull/5530
* [UI] Show when a virtual key expires by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5541
* [Fix-Proxy] allow internal user and internal viewer to view usage by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5536
* LiteLLM Merged PR's by krrishdholakia in https://github.com/BerriAI/litellm/pull/5538
* Update lago.py to accomodate API change (5495) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5543
* LiteLLM Minor Fixes and Improvements by krrishdholakia in https://github.com/BerriAI/litellm/pull/5537
* [Fix] transcription/atranscription file parameter should accept correct types by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5534

New Contributors
* wolf-joe made their first contribution in https://github.com/BerriAI/litellm/pull/5530

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.18...v1.44.19-stable



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.19-stable



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 84 | 98.93160195485267 | 6.438868020860198 | 0.0 | 1927 | 0 | 68.17092200003572 | 1581.8675439999765 |
| Aggregated | Passed ✅ | 84 | 98.93160195485267 | 6.438868020860198 | 0.0 | 1927 | 0 | 68.17092200003572 | 1581.8675439999765 |

What's Changed
* fix KeyError when call deepseek api by wolf-joe in https://github.com/BerriAI/litellm/pull/5530
* [UI] Show when a virtual key expires by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5541
* [Fix-Proxy] allow internal user and internal viewer to view usage by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5536
* LiteLLM Merged PR's by krrishdholakia in https://github.com/BerriAI/litellm/pull/5538
* Update lago.py to accomodate API change (5495) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5543
* LiteLLM Minor Fixes and Improvements by krrishdholakia in https://github.com/BerriAI/litellm/pull/5537
* [Fix] transcription/atranscription file parameter should accept correct types by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5534

New Contributors
* wolf-joe made their first contribution in https://github.com/BerriAI/litellm/pull/5530

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.18...v1.44.19



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.19



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 140.0 | 169.38227208086795 | 6.321167248443861 | 0.0 | 1892 | 0 | 114.4958109999834 | 2909.539383999999 |
| Aggregated | Passed ✅ | 140.0 | 169.38227208086795 | 6.321167248443861 | 0.0 | 1892 | 0 | 114.4958109999834 | 2909.539383999999 |

v1.44.18-stable
What's Changed
* LiteLLM Minor fixes + improvements (08/04/2024) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5505
* fix(pass_through_endpoints): support bedrock agents via pass through by krrishdholakia in https://github.com/BerriAI/litellm/pull/5527


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.17...v1.44.18-stable



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.18-stable



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 150.0 | 170.81621034830297 | 6.398015939395273 | 0.0 | 1915 | 0 | 116.37449199997718 | 2974.9741289999747 |
| Aggregated | Passed ✅ | 150.0 | 170.81621034830297 | 6.398015939395273 | 0.0 | 1915 | 0 | 116.37449199997718 | 2974.9741289999747 |

What's Changed
* LiteLLM Minor fixes + improvements (08/04/2024) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5505
* fix(pass_through_endpoints): support bedrock agents via pass through by krrishdholakia in https://github.com/BerriAI/litellm/pull/5527


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.17...v1.44.18



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.18



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 110.0 | 123.78989845407648 | 6.4836946715014685 | 0.0 | 1938 | 0 | 82.95310500000141 | 2277.6017620000175 |
| Aggregated | Passed ✅ | 110.0 | 123.78989845407648 | 6.4836946715014685 | 0.0 | 1938 | 0 | 82.95310500000141 | 2277.6017620000175 |

v1.44.17-stable
What's Changed
* Add azure/gpt-4o-2024-08-06 pricing. by Manouchehri in https://github.com/BerriAI/litellm/pull/5510
* [Fix] get_llm_provider, return provider as `cohere_chat` for cohere chat models by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5511
* fix proxy server - always read redis for rate limiting logic by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5484
* Helicone stream response logging by maamalama in https://github.com/BerriAI/litellm/pull/5516
* security - Prevent sql injection in `/team/update` query by krrishdholakia in https://github.com/BerriAI/litellm/pull/5513
* [Fix-Refactor] support presidio on new guardrails config by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5514
* [Fix - Proxy] show error from /spend/tags and /spend/logs on client side by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5520
* [Feat] log request / response on pass through endpoints by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5518
* [Fix-Proxy] show more descriptive error messages on /health checks by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5521


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.16...v1.44.17-stable



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.17-stable



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 150.0 | 168.624452710735 | 6.331403580740946 | 0.0 | 1891 | 0 | 110.9297180000226 | 815.6032489999916 |
| Aggregated | Passed ✅ | 150.0 | 168.624452710735 | 6.331403580740946 | 0.0 | 1891 | 0 | 110.9297180000226 | 815.6032489999916 |

What's Changed
* Add azure/gpt-4o-2024-08-06 pricing. by Manouchehri in https://github.com/BerriAI/litellm/pull/5510
* [Fix] get_llm_provider, return provider as `cohere_chat` for cohere chat models by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5511
* fix proxy server - always read redis for rate limiting logic by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5484
* Helicone stream response logging by maamalama in https://github.com/BerriAI/litellm/pull/5516
* security - Prevent sql injection in `/team/update` query by krrishdholakia in https://github.com/BerriAI/litellm/pull/5513
* [Fix-Refactor] support presidio on new guardrails config by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5514
* [Fix - Proxy] show error from /spend/tags and /spend/logs on client side by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5520
* [Feat] log request / response on pass through endpoints by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5518
* [Fix-Proxy] show more descriptive error messages on /health checks by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5521


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.16...v1.44.17



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.17



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 110.0 | 144.75345275454978 | 6.424739460241986 | 0.0 | 1923 | 0 | 86.76964199997883 | 3621.227346000012 |
| Aggregated | Passed ✅ | 110.0 | 144.75345275454978 | 6.424739460241986 | 0.0 | 1923 | 0 | 86.76964199997883 | 3621.227346000012 |

v1.44.16-stable
What's Changed
* update canary by yujonglee in https://github.com/BerriAI/litellm/pull/5459
* Bump pagefind from 1.1.0 to 1.1.1 in /docs/my-website by dependabot in https://github.com/BerriAI/litellm/pull/5491
* [Feat] Add Google Secret Manager Support by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5489
* [Feat-Proxy] Enterprise - allow controlling allowed private, public, admin only routes by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5494
* [Feat-Proxy] bump langfuse sdk version on docker by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5497
* LiteLLM Minor fixes + improvements (08/03/2024) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5488


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.15...v1.44.16-stable



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.16-stable



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 140.0 | 168.79004244876447 | 6.3642503777567425 | 0.0 | 1903 | 0 | 113.65976999996974 | 2153.1978849999405 |
| Aggregated | Passed ✅ | 140.0 | 168.79004244876447 | 6.3642503777567425 | 0.0 | 1903 | 0 | 113.65976999996974 | 2153.1978849999405 |

What's Changed
* update canary by yujonglee in https://github.com/BerriAI/litellm/pull/5459
* Bump pagefind from 1.1.0 to 1.1.1 in /docs/my-website by dependabot in https://github.com/BerriAI/litellm/pull/5491
* [Feat] Add Google Secret Manager Support by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5489
* [Feat-Proxy] Enterprise - allow controlling allowed private, public, admin only routes by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5494
* [Feat-Proxy] bump langfuse sdk version on docker by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5497
* LiteLLM Minor fixes + improvements (08/03/2024) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5488


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.15...v1.44.16



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.16



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 150.0 | 172.57036657744393 | 6.428433196552351 | 0.0033411814950895795 | 1924 | 1 | 111.12589300000764 | 1407.5345470000116 |
| Aggregated | Passed ✅ | 150.0 | 172.57036657744393 | 6.428433196552351 | 0.0033411814950895795 | 1924 | 1 | 111.12589300000764 | 1407.5345470000116 |

v1.44.15-stable
What's Changed
* Bedrock Embeddings refactor + model support by krrishdholakia in https://github.com/BerriAI/litellm/pull/5462
* Fix response_format={'type': 'json_object'} not working for Azure models by simonsanvil in https://github.com/BerriAI/litellm/pull/5468
* LiteLLM minor fixes + improvements (31/08/2024) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5464
* (gemini): Fix Cloudflare AI Gateway typo. by Manouchehri in https://github.com/BerriAI/litellm/pull/5429
* [PRICING] Add pricing for ft:gpt-3.5-turbo-* by kiriloman in https://github.com/BerriAI/litellm/pull/5471
* Azure Service Principal with Secret authentication workflow. (5131) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5437
* LiteLLM Minor Fixes + Improvements by krrishdholakia in https://github.com/BerriAI/litellm/pull/5474
* [Feat] Add AI21 /chat API by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5478
* [Feat] Track Usage for `/streamGenerateContent` endpoint by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5480
* [Feat-Proxy] track imagen /predict in LiteLLM spend logs by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5481
* [Feat] track embedding /predict in spend logs by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5482
* feat(router.py): Support Loadbalancing batch azure api endpoints by krrishdholakia in https://github.com/BerriAI/litellm/pull/5469
* fix(router.py): fix inherited type by krrishdholakia in https://github.com/BerriAI/litellm/pull/5485


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.14...v1.44.15-stable



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.15-stable



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 150.0 | 174.12666019390488 | 6.364398958388214 | 0.0 | 1903 | 0 | 113.97205899999108 | 1135.2586950000045 |
| Aggregated | Passed ✅ | 150.0 | 174.12666019390488 | 6.364398958388214 | 0.0 | 1903 | 0 | 113.97205899999108 | 1135.2586950000045 |

What's Changed
* Bedrock Embeddings refactor + model support by krrishdholakia in https://github.com/BerriAI/litellm/pull/5462
* Fix response_format={'type': 'json_object'} not working for Azure models by simonsanvil in https://github.com/BerriAI/litellm/pull/5468
* LiteLLM minor fixes + improvements (31/08/2024) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5464
* (gemini): Fix Cloudflare AI Gateway typo. by Manouchehri in https://github.com/BerriAI/litellm/pull/5429
* [PRICING] Add pricing for ft:gpt-3.5-turbo-* by kiriloman in https://github.com/BerriAI/litellm/pull/5471
* Azure Service Principal with Secret authentication workflow. (5131) by krrishdholakia in https://github.com/BerriAI/litellm/pull/5437
* LiteLLM Minor Fixes + Improvements by krrishdholakia in https://github.com/BerriAI/litellm/pull/5474
* [Feat] Add AI21 /chat API by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5478
* [Feat] Track Usage for `/streamGenerateContent` endpoint by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5480
* [Feat-Proxy] track imagen /predict in LiteLLM spend logs by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5481
* [Feat] track embedding /predict in spend logs by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5482
* feat(router.py): Support Loadbalancing batch azure api endpoints by krrishdholakia in https://github.com/BerriAI/litellm/pull/5469
* fix(router.py): fix inherited type by krrishdholakia in https://github.com/BerriAI/litellm/pull/5485


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.14...v1.44.15



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.15



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 150.0 | 172.03211431410688 | 6.371131108857087 | 0.0 | 1907 | 0 | 115.2671469999973 | 2482.183120000059 |
| Aggregated | Passed ✅ | 150.0 | 172.03211431410688 | 6.371131108857087 | 0.0 | 1907 | 0 | 115.2671469999973 | 2482.183120000059 |

v1.44.14-stable
What's Changed
* anthropic prompt caching cost tracking by krrishdholakia in https://github.com/BerriAI/litellm/pull/5453
* [Feat-Proxy] track spend logs for vertex pass through endpoints by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5457
* [Feat] New Provider - Add Cerebras AI API by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5461
* [Feat - Prometheus] - Track error_code, model metric by ishaan-jaff in https://github.com/BerriAI/litellm/pull/5463
* Minor LiteLLM Fixes and Improvements by krrishdholakia in https://github.com/BerriAI/litellm/pull/5456


**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.44.13...v1.44.14-stable



Docker Run LiteLLM Proxy


docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.44.14-stable



Don't want to maintain your internal proxy? get in touch 🎉
Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| /chat/completions | Passed ✅ | 140.0 | 164.65214474238385 | 6.252754675195834 | 0.0 | 1871 | 0 | 115.70125900004768 | 2147.0894060000205 |
| Aggregated | Passed ✅ | 140.0 | 164.65214474238385 | 6.252754675195834 | 0.0 | 1871 | 0 | 115.70125900004768 | 2147.0894060000205 |