9495f4e941
* auth_with_role_name add region_name arg for cross-account sts * update tests to include case with aws_region_name for _auth_with_aws_role * Only pass region_name to STS client when aws_region_name is set * Add optional aws_sts_endpoint to _auth_with_aws_role * Parametrize ambient-credentials test for no opts, region_name, and aws_sts_endpoint * consistently passing region and endpoint args into explicit credentials irsa * fix env var leakage * fix: bedrock openai-compatible imported-model should also have model arn encoded * feat: show proxy url in ModelHub (#21660) * fix(bedrock): correct modelInput format for Converse API batch models (#21656) * fix(proxy): add model_ids param to access group endpoints for precise deployment tagging (#21655) POST /access_group/new and PUT /access_group/{name}/update now accept an optional model_ids list that targets specific deployments by their unique model_id, instead of tagging every deployment that shares a model_name. When model_ids is provided it takes priority over model_names, giving API callers the same single-deployment precision that the UI already has via PATCH /model/{model_id}/update. Backward compatible: model_names continues to work as before. Closes #21544 * feat(proxy): add custom favicon support\n\nAdd ability to configure a custom favicon for the litellm proxy UI.\n\n- Add favicon_url field to UIThemeConfig model\n- Add LITELLM_FAVICON_URL env var support\n- Add /get_favicon endpoint to serve custom favicons\n- Update ThemeContext to dynamically set favicon\n- Add favicon URL input to UI theme settings page\n- Add comprehensive tests\n\nCloses #8323 (#21653) * fix(bedrock): prevent double UUID in create_file S3 key (#21650) In create_file for Bedrock, get_complete_file_url is called twice: once in the sync handler (generating UUID-1 for api_base) and once inside transform_create_file_request (generating UUID-2 for the actual S3 upload). The Bedrock provider correctly writes UUID-2 into litellm_params["upload_url"], but the sync handler unconditionally overwrites it with api_base (UUID-1). This causes the returned file_id to point to a non-existent S3 key. Fix: only set upload_url to api_base when transform_create_file_request has not already set it, preserving the Bedrock provider's value. Closes #21546 * feat(semantic-cache): support configurable vector dimensions for Qdrant (#21649) Add vector_size parameter to QdrantSemanticCache and expose it through the Cache facade as qdrant_semantic_cache_vector_size. This allows users to use embedding models with dimensions other than the default 1536, enabling cheaper/stronger models like Stella (1024d), bge-en-icl (4096d), voyage, cohere, etc. The parameter defaults to QDRANT_VECTOR_SIZE (env var or 1536) for backward compatibility. When creating new collections, the configured vector_size is used instead of the hardcoded constant. Closes #9377 * fix(utils): normalize camelCase thinking param keys to snake_case (#21762) Clients like OpenCode's @ai-sdk/openai-compatible send budgetTokens (camelCase) instead of budget_tokens in the thinking parameter, causing validation errors. Add early normalization in completion(). * feat: add optional digest mode for Slack alert types (#21683) Adds per-alert-type digest mode that aggregates duplicate alerts within a configurable time window and emits a single summary message with count, start/end timestamps. Configuration via general_settings.alert_type_config: alert_type_config: llm_requests_hanging: digest: true digest_interval: 86400 Digest key: (alert_type, request_model, api_base) Default interval: 24 hours Window type: fixed interval Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add blog_posts.json and local backup * feat: add GetBlogPosts utility with GitHub fetch and local fallback Adds GetBlogPosts class that fetches blog posts from GitHub with a 1-hour in-process TTL cache, validates the response, and falls back to the bundled blog_posts_backup.json on any network or validation failure. * test: add cache reset fixture and LITELLM_LOCAL_BLOG_POSTS test Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat: add GET /public/litellm_blog_posts endpoint Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: log fallback warning in blog posts endpoint and tighten test * feat: add disable_show_blog to UISettings Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat: add useUISettings and useDisableShowBlog hooks * fix: rename useUISettings to useUISettingsFlags to avoid naming collision * fix: use existing useUISettings hook in useDisableShowBlog to avoid cache duplication Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat: add BlogDropdown component with react-query and error/retry state Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: enforce 5-post limit in BlogDropdown and add cap test * fix: add retry, stable post key, enabled guard in BlogDropdown Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat: add BlogDropdown to navbar after Docs link * feat: add network_mock transport for benchmarking proxy overhead without real API calls Intercepts at httpx transport layer so the full proxy path (auth, routing, OpenAI SDK, response transformation) is exercised with zero-latency responses. Activated via `litellm_settings: { network_mock: true }` in proxy config. * Litellm dev 02 19 2026 p2 (#21871) * feat(ui/): new guardrails monitor 'demo mock representation of what guardrails monitor looks like * fix: ui updates * style(ui/): fix styling * feat: enable running ai monitor on individual guardrails * feat: add backend logic for guardrail monitoring * fix(guardrails/usage_endpoints.py): fix usage dashboard * fix(budget): fix timezone config lookup and replace hardcoded timezone map with ZoneInfo (#21754) * fix(budget): fix timezone config lookup and replace hardcoded timezone map with ZoneInfo * fix(budget): update stale docstring on get_budget_reset_time * fix: add missing return type annotations to iterator protocol methods in streaming_handler (#21750) * fix: add return type annotations to iterator protocol methods in streaming_handler Add missing return type annotations to __iter__, __aiter__, __next__, and __anext__ methods in CustomStreamWrapper and related classes. - __iter__(self) -> Iterator["ModelResponseStream"] - __aiter__(self) -> AsyncIterator["ModelResponseStream"] - __next__(self) -> "ModelResponseStream" - __anext__(self) -> "ModelResponseStream" Also adds AsyncIterator and Iterator to typing imports. Fixes issue with PLR0915 noqa comments and ensures proper type checking support. Related to: BerriAI/litellm#8304 * fix: add ruff PLR0915 noqa for files with too many statements * Add gollem Go agent framework cookbook example (#21747) Show how to use gollem, a production Go agent framework, with LiteLLM proxy for multi-provider LLM access including tool use and streaming. * fix: avoid mutating caller-owned dicts in SpendUpdateQueue aggregation (#21742) * fix(vertex_ai): enable context-1m-2025-08-07 beta header (#21870) * server root path regression doc * fixing syntax * fix: replace Zapier webhook with Google Form for survey submission (#21621) * Replace Zapier webhook with Google Form for survey submission * Add back error logging for survey submission debugging --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> * Revert "Merge pull request #21140 from BerriAI/litellm_perf_user_api_key_auth" This reverts commit |
||
|---|---|---|
| .. | ||
| eval_suites_mlflow_autoevals | ||
| benchmark.py | ||
| readme.md | ||
LLM-Bench
Benchmark LLMs response, cost and response time
LLM vs Cost per input + output token ($)
| Model | Provider | Cost per input + output token ($) |
|---|---|---|
| openrouter/mistralai/mistral-7b-instruct | openrouter | 0.0 |
| ollama/llama2 | ollama | 0.0 |
| ollama/llama2:13b | ollama | 0.0 |
| ollama/llama2:70b | ollama | 0.0 |
| ollama/llama2-uncensored | ollama | 0.0 |
| ollama/mistral | ollama | 0.0 |
| ollama/codellama | ollama | 0.0 |
| ollama/orca-mini | ollama | 0.0 |
| ollama/vicuna | ollama | 0.0 |
| perplexity/codellama-34b-instruct | perplexity | 0.0 |
| perplexity/llama-2-13b-chat | perplexity | 0.0 |
| perplexity/llama-2-70b-chat | perplexity | 0.0 |
| perplexity/mistral-7b-instruct | perplexity | 0.0 |
| perplexity/replit-code-v1.5-3b | perplexity | 0.0 |
| text-bison | vertex_ai-text-models | 0.00000025 |
| text-bison@001 | vertex_ai-text-models | 0.00000025 |
| chat-bison | vertex_ai-chat-models | 0.00000025 |
| chat-bison@001 | vertex_ai-chat-models | 0.00000025 |
| chat-bison-32k | vertex_ai-chat-models | 0.00000025 |
| code-bison | vertex_ai-code-text-models | 0.00000025 |
| code-bison@001 | vertex_ai-code-text-models | 0.00000025 |
| code-gecko@001 | vertex_ai-chat-models | 0.00000025 |
| code-gecko@latest | vertex_ai-chat-models | 0.00000025 |
| codechat-bison | vertex_ai-code-chat-models | 0.00000025 |
| codechat-bison@001 | vertex_ai-code-chat-models | 0.00000025 |
| codechat-bison-32k | vertex_ai-code-chat-models | 0.00000025 |
| palm/chat-bison | palm | 0.00000025 |
| palm/chat-bison-001 | palm | 0.00000025 |
| palm/text-bison | palm | 0.00000025 |
| palm/text-bison-001 | palm | 0.00000025 |
| palm/text-bison-safety-off | palm | 0.00000025 |
| palm/text-bison-safety-recitation-off | palm | 0.00000025 |
| anyscale/meta-llama/Llama-2-7b-chat-hf | anyscale | 0.0000003 |
| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | anyscale | 0.0000003 |
| openrouter/meta-llama/llama-2-13b-chat | openrouter | 0.0000004 |
| openrouter/nousresearch/nous-hermes-llama2-13b | openrouter | 0.0000004 |
| deepinfra/meta-llama/Llama-2-7b-chat-hf | deepinfra | 0.0000004 |
| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | deepinfra | 0.0000004 |
| anyscale/meta-llama/Llama-2-13b-chat-hf | anyscale | 0.0000005 |
| amazon.titan-text-lite-v1 | bedrock | 0.0000007 |
| deepinfra/meta-llama/Llama-2-13b-chat-hf | deepinfra | 0.0000007 |
| text-babbage-001 | text-completion-openai | 0.0000008 |
| text-ada-001 | text-completion-openai | 0.0000008 |
| babbage-002 | text-completion-openai | 0.0000008 |
| openrouter/google/palm-2-chat-bison | openrouter | 0.000001 |
| openrouter/google/palm-2-codechat-bison | openrouter | 0.000001 |
| openrouter/meta-llama/codellama-34b-instruct | openrouter | 0.000001 |
| deepinfra/codellama/CodeLlama-34b-Instruct-hf | deepinfra | 0.0000012 |
| deepinfra/meta-llama/Llama-2-70b-chat-hf | deepinfra | 0.0000016499999999999999 |
| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | deepinfra | 0.0000016499999999999999 |
| anyscale/meta-llama/Llama-2-70b-chat-hf | anyscale | 0.000002 |
| anyscale/codellama/CodeLlama-34b-Instruct-hf | anyscale | 0.000002 |
| gpt-3.5-turbo-1106 | openai | 0.000003 |
| openrouter/meta-llama/llama-2-70b-chat | openrouter | 0.000003 |
| amazon.titan-text-express-v1 | bedrock | 0.000003 |
| gpt-3.5-turbo | openai | 0.0000035 |
| gpt-3.5-turbo-0301 | openai | 0.0000035 |
| gpt-3.5-turbo-0613 | openai | 0.0000035 |
| gpt-3.5-turbo-instruct | text-completion-openai | 0.0000035 |
| openrouter/openai/gpt-3.5-turbo | openrouter | 0.0000035 |
| cohere.command-text-v14 | bedrock | 0.0000035 |
| gpt-3.5-turbo-0613 | openai | 0.0000035 |
| claude-instant-1 | anthropic | 0.00000714 |
| claude-instant-1.2 | anthropic | 0.00000714 |
| openrouter/anthropic/claude-instant-v1 | openrouter | 0.00000714 |
| anthropic.claude-instant-v1 | bedrock | 0.00000714 |
| openrouter/mancer/weaver | openrouter | 0.00001125 |
| j2-mid | ai21 | 0.00002 |
| ai21.j2-mid-v1 | bedrock | 0.000025 |
| openrouter/jondurbin/airoboros-l2-70b-2.1 | openrouter | 0.00002775 |
| command-nightly | cohere | 0.00003 |
| command | cohere | 0.00003 |
| command-light | cohere | 0.00003 |
| command-medium-beta | cohere | 0.00003 |
| command-xlarge-beta | cohere | 0.00003 |
| command-r-plus | cohere | 0.000018 |
| j2-ultra | ai21 | 0.00003 |
| ai21.j2-ultra-v1 | bedrock | 0.0000376 |
| gpt-4-1106-preview | openai | 0.00004 |
| gpt-4-vision-preview | openai | 0.00004 |
| claude-2 | anthropic | 0.0000437 |
| openrouter/anthropic/claude-2 | openrouter | 0.0000437 |
| anthropic.claude-v1 | bedrock | 0.0000437 |
| anthropic.claude-v2 | bedrock | 0.0000437 |
| gpt-4 | openai | 0.00009 |
| gpt-4-0314 | openai | 0.00009 |
| gpt-4-0613 | openai | 0.00009 |
| openrouter/openai/gpt-4 | openrouter | 0.00009 |
| gpt-4-32k | openai | 0.00018 |
| gpt-4-32k-0314 | openai | 0.00018 |
| gpt-4-32k-0613 | openai | 0.00018 |
Setup:
git clone https://github.com/BerriAI/litellm
cd to benchmark dir
cd litellm/cookbook/benchmark
Install Dependencies
pip install litellm click tqdm tabulate termcolor
Configuration
In benchmark/benchmark.py select your LLMs, LLM API Key and questions
Supported LLMs: https://docs.litellm.ai/docs/providers
# Define the list of models to benchmark
models = ['gpt-3.5-turbo', 'togethercomputer/llama-2-70b-chat', 'claude-2']
# Enter LLM API keys
os.environ['OPENAI_API_KEY'] = ""
os.environ['ANTHROPIC_API_KEY'] = ""
os.environ['TOGETHERAI_API_KEY'] = ""
# List of questions to benchmark (replace with your questions)
questions = [
"When will BerriAI IPO?",
"When will LiteLLM hit $100M ARR?"
]
Run LLM-Bench
python3 benchmark.py
Expected Output
Running question: When will BerriAI IPO? for model: claude-2: 100%|████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:13<00:00, 4.41s/it]
Benchmark Results for 'When will BerriAI IPO?':
+-----------------+----------------------------------------------------------------------------------+---------------------------+------------+
| Model | Response | Response Time (seconds) | Cost ($) |
+=================+==================================================================================+===========================+============+
| gpt-3.5-turbo | As an AI language model, I cannot provide up-to-date information or predict | 1.55 seconds | $0.000122 |
| | future events. It is best to consult a reliable financial source or contact | | |
| | BerriAI directly for information regarding their IPO plans. | | |
+-----------------+----------------------------------------------------------------------------------+---------------------------+------------+
| togethercompute | I'm not able to provide information about future IPO plans or dates for BerriAI | 8.52 seconds | $0.000531 |
| r/llama-2-70b-c | or any other company. IPO (Initial Public Offering) plans and timelines are | | |
| hat | typically kept private by companies until they are ready to make a public | | |
| | announcement. It's important to note that IPO plans can change and are subject | | |
| | to various factors, such as market conditions, financial performance, and | | |
| | regulatory approvals. Therefore, it's difficult to predict with certainty when | | |
| | BerriAI or any other company will go public. If you're interested in staying | | |
| | up-to-date with BerriAI's latest news and developments, you may want to follow | | |
| | their official social media accounts, subscribe to their newsletter, or visit | | |
| | their website periodically for updates. | | |
+-----------------+----------------------------------------------------------------------------------+---------------------------+------------+
| claude-2 | I do not have any information about when or if BerriAI will have an initial | 3.17 seconds | $0.002084 |
| | public offering (IPO). As an AI assistant created by Anthropic to be helpful, | | |
| | harmless, and honest, I do not have insider knowledge about Anthropic's business | | |
| | plans or strategies. | | |
+-----------------+----------------------------------------------------------------------------------+---------------------------+------------+
Support
🤝 Schedule a 1-on-1 Session: Book a 1-on-1 session with Krrish and Ishaan, the founders, to discuss any issues, provide feedback, or explore how we can improve LiteLLM for you.