scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-16 23:41:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Merge pull request #41457 from BerriAI/litellm-providers/price-sync

Browse source 
chore(prices): sync Google Gemini prices: 22 models
This commit is contained in:
kerry-berri 2026-09-16 12:37:16 -07:00 • committed by GitHub
commit b6143b3711
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 170 additions and 182 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

124
litellm/model_prices_and_context_window_backup.json
View file

@ -11313,13 +11313,16 @@
},
"azure_ai/grok-4.3": {
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -11331,13 +11334,16 @@
},
"azure_ai/grok-4.6": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_200k_tokens": 1.2e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -26162,7 +26168,9 @@
"output_vector_size": 3072,
"rpm": 10000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supports_audio_input": true,
"supports_multimodal": true,
"supports_vision": true,
"tpm": 10000000
},
"gemini/gemini-1.5-flash": {
@ -26303,8 +26311,8 @@
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 2.5e-06,
"output_cost_per_token": 2.5e-06,
@ -26350,6 +26358,7 @@
"output_cost_per_token_batches": 1.25e-06,
"output_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_priority": 4.5e-06,
"supports_audio_input": true,
"supports_image_size": false
},
"gemini/gemini-2.5-flash-image": {
@ -26362,7 +26371,7 @@
"input_cost_per_token_priority": 5.4e-07,
"litellm_provider": "gemini",
"supports_reasoning": false,
"max_input_tokens": 32768,
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
@ -26388,22 +26397,23 @@
"image"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_function_calling": false,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_vision": true,
"supports_web_search": true,
"supports_web_search": false,
"tpm": 8000000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
},
"supports_audio_input": false,
"supports_image_size": false
},
"gemini/gemini-3-pro-image": {
@ -26441,7 +26451,7 @@
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
@ -26544,7 +26554,7 @@
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
@ -26571,7 +26581,7 @@
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_reasoning": false,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
@ -26653,12 +26663,13 @@
"text",
"image"
],
"supports_function_calling": true,
"supports_function_calling": false,
"supports_prompt_caching": false,
"supports_reasoning": false,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": false,
"tpm": 4000000
},
"gemini/deep-research-pro-preview-12-2025": {
@ -26711,8 +26722,8 @@
"input_cost_per_token": 1e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 4e-07,
"output_cost_per_token": 4e-07,
@ -26758,6 +26769,7 @@
"output_cost_per_token_batches": 2e-07,
"output_cost_per_token_flex": 2e-07,
"output_cost_per_token_priority": 7.2e-07,
"supports_audio_input": true,
"supports_image_size": false
},
"gemini/gemini-2.5-flash-lite-preview-09-2025": {
@ -27005,6 +27017,9 @@
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 1e-05,
"output_cost_per_token": 1e-05,
@ -27013,7 +27028,11 @@
"/v1/audio/speech"
],
"tpm": 4000000,
"rpm": 10
"rpm": 10,
"supports_audio_input": false,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false
},
"gemini/gemini-2.5-pro": {
"cache_read_input_token_cost": 1.25e-07,
@ -27027,8 +27046,8 @@
"input_cost_per_token_above_200k_tokens_priority": 4.5e-06,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
@ -27338,8 +27357,8 @@
"input_cost_per_token": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
@ -27388,7 +27407,8 @@
"input_cost_per_token_batches": 2.5e-07,
"input_cost_per_token_flex": 2.5e-07,
"output_cost_per_token_batches": 1.5e-06,
"output_cost_per_token_flex": 1.5e-06
"output_cost_per_token_flex": 1.5e-06,
"supports_audio_input": true
},
"gemini/gemini-3.5-flash": {
"prompt_cache_min_tokens": 4096,
@ -27397,8 +27417,8 @@
"input_cost_per_token": 1.5e-06,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
@ -28112,9 +28132,9 @@
"input_cost_per_token": 1e-06,
"input_cost_per_token_batches": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_audio_token": 2e-05,
"output_cost_per_token": 2e-05,
@ -28127,19 +28147,20 @@
"audio"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_vision": false,
"supports_web_search": false,
"tpm": 10000000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
}
},
"supports_audio_input": false
},
"gemini/gemini-exp-1114": {
"input_cost_per_token": 0,
@ -55917,7 +55938,7 @@
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "realtime",
@ -55937,7 +55958,11 @@
],
"supports_audio_input": true,
"supports_audio_output": true,
"gemini_native_audio": true
"gemini_native_audio": true,
"supports_function_calling": true,
"supports_response_schema": false,
"supports_vision": true,
"supports_web_search": true
},
"gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 3e-06,
@ -55971,7 +55996,8 @@
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true,
"input_cost_per_second": 8.33333333333e-05
"input_cost_per_second": 8.33333333333e-05,
"supports_response_schema": false
},
"gemini/gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 3e-06,
@ -56033,7 +56059,7 @@
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "realtime",
@ -56055,7 +56081,11 @@
"supports_audio_output": true,
"tpm": 250000,
"rpm": 10,
"gemini_native_audio": true
"gemini_native_audio": true,
"supports_function_calling": true,
"supports_response_schema": false,
"supports_vision": true,
"supports_web_search": true
},
"gemini/gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 3e-06,
@ -56091,7 +56121,8 @@
"tpm": 250000,
"rpm": 10,
"gemini_audio_only_live": true,
"input_cost_per_second": 8.33333333333e-05
"input_cost_per_second": 8.33333333333e-05,
"supports_response_schema": false
},
"gemini/gemini-3.1-flash-tts-preview": {
"input_cost_per_token": 1e-06,
@ -56108,19 +56139,29 @@
"/v1/audio/speech"
],
"tpm": 4000000,
"rpm": 10
"rpm": 10,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false
},
"gemini-2.5-flash-preview-tts": {
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 1e-05,
"output_cost_per_token": 1e-05,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/audio/speech"
]
],
"supports_audio_input": false,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false
},
"gemini-flash-latest": {
"cache_read_input_token_cost": 3e-08,
@ -58694,6 +58735,9 @@
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false,
"tpm": 250000
},
"gemini/gemini-3.5-transcribe": {
@ -58715,7 +58759,8 @@
],
"supports_audio_input": true,
"tpm": 800000,
"rpm": 2000
"rpm": 2000,
"supports_function_calling": false
},
"gemini/gemini-3.5-transcribe-live": {
"input_cost_per_audio_token": 3.5e-06,
@ -58735,7 +58780,8 @@
],
"supports_audio_input": true,
"tpm": 250000,
"rpm": 10
"rpm": 10,
"supports_function_calling": false
},
"vertex_ai/gemini-3.5-transcribe-preview": {
"input_cost_per_audio_token": 2e-06,
@ -61374,7 +61420,7 @@
"input_cost_per_audio_token": 1.5e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",

124
model_prices_and_context_window.json
View file

@ -11313,13 +11313,16 @@
},
"azure_ai/grok-4.3": {
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -11331,13 +11334,16 @@
},
"azure_ai/grok-4.6": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_200k_tokens": 1.2e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -26162,7 +26168,9 @@
"output_vector_size": 3072,
"rpm": 10000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supports_audio_input": true,
"supports_multimodal": true,
"supports_vision": true,
"tpm": 10000000
},
"gemini/gemini-1.5-flash": {
@ -26303,8 +26311,8 @@
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 2.5e-06,
"output_cost_per_token": 2.5e-06,
@ -26350,6 +26358,7 @@
"output_cost_per_token_batches": 1.25e-06,
"output_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_priority": 4.5e-06,
"supports_audio_input": true,
"supports_image_size": false
},
"gemini/gemini-2.5-flash-image": {
@ -26362,7 +26371,7 @@
"input_cost_per_token_priority": 5.4e-07,
"litellm_provider": "gemini",
"supports_reasoning": false,
"max_input_tokens": 32768,
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
@ -26388,22 +26397,23 @@
"image"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_function_calling": false,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_vision": true,
"supports_web_search": true,
"supports_web_search": false,
"tpm": 8000000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
},
"supports_audio_input": false,
"supports_image_size": false
},
"gemini/gemini-3-pro-image": {
@ -26441,7 +26451,7 @@
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
@ -26544,7 +26554,7 @@
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
@ -26571,7 +26581,7 @@
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_reasoning": false,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
@ -26653,12 +26663,13 @@
"text",
"image"
],
"supports_function_calling": true,
"supports_function_calling": false,
"supports_prompt_caching": false,
"supports_reasoning": false,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": false,
"tpm": 4000000
},
"gemini/deep-research-pro-preview-12-2025": {
@ -26711,8 +26722,8 @@
"input_cost_per_token": 1e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 4e-07,
"output_cost_per_token": 4e-07,
@ -26758,6 +26769,7 @@
"output_cost_per_token_batches": 2e-07,
"output_cost_per_token_flex": 2e-07,
"output_cost_per_token_priority": 7.2e-07,
"supports_audio_input": true,
"supports_image_size": false
},
"gemini/gemini-2.5-flash-lite-preview-09-2025": {
@ -27005,6 +27017,9 @@
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 1e-05,
"output_cost_per_token": 1e-05,
@ -27013,7 +27028,11 @@
"/v1/audio/speech"
],
"tpm": 4000000,
"rpm": 10
"rpm": 10,
"supports_audio_input": false,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false
},
"gemini/gemini-2.5-pro": {
"cache_read_input_token_cost": 1.25e-07,
@ -27027,8 +27046,8 @@
"input_cost_per_token_above_200k_tokens_priority": 4.5e-06,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
@ -27338,8 +27357,8 @@
"input_cost_per_token": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3e-06,
"output_cost_per_token": 3e-06,
@ -27388,7 +27407,8 @@
"input_cost_per_token_batches": 2.5e-07,
"input_cost_per_token_flex": 2.5e-07,
"output_cost_per_token_batches": 1.5e-06,
"output_cost_per_token_flex": 1.5e-06
"output_cost_per_token_flex": 1.5e-06,
"supports_audio_input": true
},
"gemini/gemini-3.5-flash": {
"prompt_cache_min_tokens": 4096,
@ -27397,8 +27417,8 @@
"input_cost_per_token": 1.5e-06,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 9e-06,
"output_cost_per_token": 9e-06,
@ -28112,9 +28132,9 @@
"input_cost_per_token": 1e-06,
"input_cost_per_token_batches": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_audio_token": 2e-05,
"output_cost_per_token": 2e-05,
@ -28127,19 +28147,20 @@
"audio"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_vision": false,
"supports_web_search": false,
"tpm": 10000000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
}
},
"supports_audio_input": false
},
"gemini/gemini-exp-1114": {
"input_cost_per_token": 0,
@ -55917,7 +55938,7 @@
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "realtime",
@ -55937,7 +55958,11 @@
],
"supports_audio_input": true,
"supports_audio_output": true,
"gemini_native_audio": true
"gemini_native_audio": true,
"supports_function_calling": true,
"supports_response_schema": false,
"supports_vision": true,
"supports_web_search": true
},
"gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 3e-06,
@ -55971,7 +55996,8 @@
"supports_vision": true,
"supports_web_search": true,
"gemini_audio_only_live": true,
"input_cost_per_second": 8.33333333333e-05
"input_cost_per_second": 8.33333333333e-05,
"supports_response_schema": false
},
"gemini/gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 3e-06,
@ -56033,7 +56059,7 @@
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "realtime",
@ -56055,7 +56081,11 @@
"supports_audio_output": true,
"tpm": 250000,
"rpm": 10,
"gemini_native_audio": true
"gemini_native_audio": true,
"supports_function_calling": true,
"supports_response_schema": false,
"supports_vision": true,
"supports_web_search": true
},
"gemini/gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 3e-06,
@ -56091,7 +56121,8 @@
"tpm": 250000,
"rpm": 10,
"gemini_audio_only_live": true,
"input_cost_per_second": 8.33333333333e-05
"input_cost_per_second": 8.33333333333e-05,
"supports_response_schema": false
},
"gemini/gemini-3.1-flash-tts-preview": {
"input_cost_per_token": 1e-06,
@ -56108,19 +56139,29 @@
"/v1/audio/speech"
],
"tpm": 4000000,
"rpm": 10
"rpm": 10,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false
},
"gemini-2.5-flash-preview-tts": {
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 1e-05,
"output_cost_per_token": 1e-05,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/audio/speech"
]
],
"supports_audio_input": false,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false
},
"gemini-flash-latest": {
"cache_read_input_token_cost": 3e-08,
@ -58694,6 +58735,9 @@
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": false,
"supports_response_schema": false,
"supports_web_search": false,
"tpm": 250000
},
"gemini/gemini-3.5-transcribe": {
@ -58715,7 +58759,8 @@
],
"supports_audio_input": true,
"tpm": 800000,
"rpm": 2000
"rpm": 2000,
"supports_function_calling": false
},
"gemini/gemini-3.5-transcribe-live": {
"input_cost_per_audio_token": 3.5e-06,
@ -58735,7 +58780,8 @@
],
"supports_audio_input": true,
"tpm": 250000,
"rpm": 10
"rpm": 10,
"supports_function_calling": false
},
"vertex_ai/gemini-3.5-transcribe-preview": {
"input_cost_per_audio_token": 2e-06,
@ -61374,7 +61420,7 @@
"input_cost_per_audio_token": 1.5e-06,
"input_cost_per_token": 1.5e-06,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",

104
tests/test_litellm/test_gemini_3_1_flash_lite_image_pricing.py
View file

@ -3,14 +3,7 @@ from pathlib import Path
import pytest
import litellm
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
from litellm.types.utils import (
ImageObject,
ImageResponse,
ImageUsage,
ImageUsageInputTokensDetails,
)
REPO_ROOT = Path(__file__).parents[2]
MAIN_PATH = REPO_ROOT / "model_prices_and_context_window.json"
@ -21,94 +14,12 @@ GEMINI = "gemini/gemini-3.1-flash-lite-image"
VERTEX = "vertex_ai/gemini-3.1-flash-lite-image"
ALL_KEYS = (UNPREFIXED, GEMINI, VERTEX)
INPUT_COST = 2.5e-07
INPUT_COST_BATCHES = 1.25e-07
OUTPUT_TEXT_COST = 1.5e-06
OUTPUT_TEXT_COST_BATCHES = 7.5e-07
OUTPUT_IMAGE_TOKEN_COST = 3e-05
OUTPUT_COST_PER_1K_IMAGE = 0.0336
INPUT_COST_PER_IMAGE = 0.00028
CACHE_READ_COST = 2.5e-08
MAX_INPUT_TOKENS = 65536
MAX_OUTPUT_TOKENS = 4096
TOKENS_PER_1K_IMAGE = 1120
SHARED_FIELDS = {
"mode": "image_generation",
"input_cost_per_token": INPUT_COST,
"input_cost_per_token_batches": INPUT_COST_BATCHES,
"input_cost_per_image": INPUT_COST_PER_IMAGE,
"output_cost_per_token": OUTPUT_TEXT_COST,
"output_cost_per_token_batches": OUTPUT_TEXT_COST_BATCHES,
"output_cost_per_image": OUTPUT_COST_PER_1K_IMAGE,
"output_cost_per_image_token": OUTPUT_IMAGE_TOKEN_COST,
"max_input_tokens": MAX_INPUT_TOKENS,
"max_output_tokens": MAX_OUTPUT_TOKENS,
"max_tokens": MAX_OUTPUT_TOKENS,
"supported_endpoints": ["/v1/chat/completions", "/v1/completions", "/v1/batch"],
"supported_output_modalities": ["text", "image"],
"supports_reasoning": False,
"supports_response_schema": False,
"supports_system_messages": True,
"supports_vision": True,
}
VERTEX_ROUTE_FIELDS = {
"litellm_provider": "vertex_ai-language-models",
"cache_read_input_token_cost": CACHE_READ_COST,
"supported_modalities": ["text", "image", "video"],
"supports_function_calling": False,
"supports_pdf_input": True,
"supports_prompt_caching": True,
"supports_video_input": True,
}
PER_ROUTE_FIELDS = {
UNPREFIXED: VERTEX_ROUTE_FIELDS,
VERTEX: VERTEX_ROUTE_FIELDS,
GEMINI: {
"litellm_provider": "gemini",
"supported_modalities": ["text", "image"],
"supports_function_calling": True,
"supports_prompt_caching": False,
"rpm": 1000,
"tpm": 4000000,
},
}
GROUNDING_FIELDS = (
"supports_web_search",
"search_context_cost_per_query",
"web_search_billing_unit",
)
def _load(path: Path) -> dict:
with open(path, encoding="utf-8") as f:
return json.load(f)
@pytest.fixture
def local_model_cost_map(monkeypatch):
original_model_cost = litellm.model_cost
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
litellm.model_cost = litellm.get_model_cost_map(url="")
litellm.get_model_info.cache_clear()
try:
yield
finally:
litellm.model_cost = original_model_cost
litellm.get_model_info.cache_clear()
@pytest.mark.parametrize("model", ALL_KEYS)
@pytest.mark.parametrize("path", (MAIN_PATH, BACKUP_PATH), ids=("main", "backup"))
def test_per_route_capabilities_match_model_cards(model: str, path: Path):
info = _load(path)[model]
for field, value in PER_ROUTE_FIELDS[model].items():
assert info[field] == value, f"{model} {field} in {path.name}: {info.get(field)} != {value}"
@pytest.mark.parametrize("model", ALL_KEYS)
def test_backup_matches_main(model: str):
assert _load(BACKUP_PATH).get(model) == _load(MAIN_PATH).get(model)
@ -124,18 +35,3 @@ def test_vertex_prefix_routes_to_vertex():
routed_model, provider, _, _ = get_llm_provider(model=VERTEX)
assert routed_model == UNPREFIXED
assert provider == "vertex_ai"
def _one_k_image_response() -> ImageResponse:
return ImageResponse(
data=[ImageObject(b64_json="img1")],
usage=ImageUsage(
input_tokens=50 + TOKENS_PER_1K_IMAGE,
input_tokens_details=ImageUsageInputTokensDetails(
text_tokens=50,
image_tokens=TOKENS_PER_1K_IMAGE,
),
output_tokens=TOKENS_PER_1K_IMAGE,
total_tokens=50 + TOKENS_PER_1K_IMAGE + TOKENS_PER_1K_IMAGE,
),
)