forked from phoenix/litellm-mirror
LiteLLM Minor Fixes & Improvements (11/26/2024) (#6913)
* docs(config_settings.md): document all router_settings * ci(config.yml): add router_settings doc test to ci/cd * test: debug test on ci/cd * test: debug ci/cd test * test: fix test * fix(team_endpoints.py): skip invalid team object. don't fail `/team/list` call Causes downstream errors if ui just fails to load team list * test(base_llm_unit_tests.py): add 'response_format={"type": "text"}' test to base_llm_unit_tests adds complete coverage for all 'response_format' values to ci/cd * feat(router.py): support wildcard routes in `get_router_model_info()` Addresses https://github.com/BerriAI/litellm/issues/6914 * build(model_prices_and_context_window.json): add tpm/rpm limits for all gemini models Allows for ratelimit tracking for gemini models even with wildcard routing enabled Addresses https://github.com/BerriAI/litellm/issues/6914 * feat(router.py): add tpm/rpm tracking on success/failure to global_router Addresses https://github.com/BerriAI/litellm/issues/6914 * feat(router.py): support wildcard routes on router.get_model_group_usage() * fix(router.py): fix linting error * fix(router.py): implement get_remaining_tokens_and_requests Addresses https://github.com/BerriAI/litellm/issues/6914 * fix(router.py): fix linting errors * test: fix test * test: fix tests * docs(config_settings.md): add missing dd env vars to docs * fix(router.py): check if hidden params is dict
This commit is contained in:
parent
5d13302e6b
commit
2d2931a215
22 changed files with 878 additions and 131 deletions
|
@ -3383,6 +3383,8 @@
|
|||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_prompt_caching": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 2000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-flash-001": {
|
||||
|
@ -3406,6 +3408,8 @@
|
|||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_prompt_caching": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 2000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-flash": {
|
||||
|
@ -3428,6 +3432,8 @@
|
|||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 2000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-flash-latest": {
|
||||
|
@ -3450,6 +3456,32 @@
|
|||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 2000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-flash-8b": {
|
||||
"max_tokens": 8192,
|
||||
"max_input_tokens": 1048576,
|
||||
"max_output_tokens": 8192,
|
||||
"max_images_per_prompt": 3000,
|
||||
"max_videos_per_prompt": 10,
|
||||
"max_video_length": 1,
|
||||
"max_audio_length_hours": 8.4,
|
||||
"max_audio_per_prompt": 1,
|
||||
"max_pdf_size_mb": 30,
|
||||
"input_cost_per_token": 0,
|
||||
"input_cost_per_token_above_128k_tokens": 0,
|
||||
"output_cost_per_token": 0,
|
||||
"output_cost_per_token_above_128k_tokens": 0,
|
||||
"litellm_provider": "gemini",
|
||||
"mode": "chat",
|
||||
"supports_system_messages": true,
|
||||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 4000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-flash-8b-exp-0924": {
|
||||
|
@ -3472,6 +3504,8 @@
|
|||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 4000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-exp-1114": {
|
||||
|
@ -3494,7 +3528,12 @@
|
|||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
"tpm": 4000000,
|
||||
"rpm": 1000,
|
||||
"source": "https://ai.google.dev/pricing",
|
||||
"metadata": {
|
||||
"notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro."
|
||||
}
|
||||
},
|
||||
"gemini/gemini-1.5-flash-exp-0827": {
|
||||
"max_tokens": 8192,
|
||||
|
@ -3516,6 +3555,8 @@
|
|||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 2000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-flash-8b-exp-0827": {
|
||||
|
@ -3537,6 +3578,9 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 4000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-pro": {
|
||||
|
@ -3550,7 +3594,10 @@
|
|||
"litellm_provider": "gemini",
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
|
||||
"rpd": 30000,
|
||||
"tpm": 120000,
|
||||
"rpm": 360,
|
||||
"source": "https://ai.google.dev/gemini-api/docs/models/gemini"
|
||||
},
|
||||
"gemini/gemini-1.5-pro": {
|
||||
"max_tokens": 8192,
|
||||
|
@ -3567,6 +3614,8 @@
|
|||
"supports_vision": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 1000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-pro-002": {
|
||||
|
@ -3585,6 +3634,8 @@
|
|||
"supports_tool_choice": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_prompt_caching": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 1000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-pro-001": {
|
||||
|
@ -3603,6 +3654,8 @@
|
|||
"supports_tool_choice": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_prompt_caching": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 1000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-pro-exp-0801": {
|
||||
|
@ -3620,6 +3673,8 @@
|
|||
"supports_vision": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 1000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-pro-exp-0827": {
|
||||
|
@ -3637,6 +3692,8 @@
|
|||
"supports_vision": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 1000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-1.5-pro-latest": {
|
||||
|
@ -3654,6 +3711,8 @@
|
|||
"supports_vision": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_response_schema": true,
|
||||
"tpm": 4000000,
|
||||
"rpm": 1000,
|
||||
"source": "https://ai.google.dev/pricing"
|
||||
},
|
||||
"gemini/gemini-pro-vision": {
|
||||
|
@ -3668,6 +3727,9 @@
|
|||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_vision": true,
|
||||
"rpd": 30000,
|
||||
"tpm": 120000,
|
||||
"rpm": 360,
|
||||
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
|
||||
},
|
||||
"gemini/gemini-gemma-2-27b-it": {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue