scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-11 22:51:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 124

fix(model_prices): add provider-announced deprecation dates for OpenAI, Gemini, Vertex, Azure models

Browse source 
Adds missing deprecation_date values verified against provider retirement docs and flags native structured output support on Anthropic-direct Claude Fable/Mythos 5.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-08-17 20:48:00 +00:00
parent f1e1c89600
commit 0897b6deda
2 changed files with 172 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

87
litellm/model_prices_and_context_window_backup.json
View file

@ -2890,6 +2890,7 @@
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_1hr": 2e-06,
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2026-10-19",
"input_cost_per_token": 1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -2913,6 +2914,7 @@
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2026-10-19",
"max_input_tokens": 200000,
"max_output_tokens": 64000,
"max_tokens": 64000,
@ -2934,6 +2936,7 @@
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2.5e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-02-02",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -2963,6 +2966,7 @@
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2.5e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-04-06",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3086,6 +3090,7 @@
"cache_creation_input_token_cost": 1.875e-05,
"cache_creation_input_token_cost_above_1hr": 3e-05,
"cache_read_input_token_cost": 1.5e-06,
"deprecation_date": "2026-08-05",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -3107,6 +3112,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-19",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -3162,6 +3168,7 @@
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-02-10",
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
@ -3235,6 +3242,7 @@
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-10-26",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3327,6 +3335,7 @@
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-02",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3373,6 +3382,7 @@
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-02",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3419,6 +3429,7 @@
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 0.00012,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-07",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3464,6 +3475,7 @@
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 0.00012,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-07",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3505,6 +3517,7 @@
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3545,6 +3558,7 @@
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3585,6 +3599,7 @@
"input_cost_per_token": 2e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3625,6 +3640,7 @@
"input_cost_per_token": 2e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -4493,6 +4509,7 @@
},
"azure/gpt-4.1": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "azure",
@ -4560,6 +4577,7 @@
},
"azure/gpt-4.1-mini": {
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 4e-07,
"input_cost_per_token_batches": 2e-07,
"litellm_provider": "azure",
@ -4627,6 +4645,7 @@
},
"azure/gpt-4.1-nano": {
"cache_read_input_token_cost": 2.5e-08,
"deprecation_date": "2026-10-14",
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
"litellm_provider": "azure",
@ -4903,6 +4922,7 @@
},
"azure/gpt-4o-mini": {
"cache_read_input_token_cost": 7.5e-08,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 1.65e-07,
"litellm_provider": "azure",
"max_input_tokens": 128000,
@ -5345,6 +5365,7 @@
},
"azure/gpt-5": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2027-02-09",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5508,6 +5529,7 @@
},
"azure/gpt-5-mini": {
"cache_read_input_token_cost": 2.5e-08,
"deprecation_date": "2027-02-09",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5573,6 +5595,7 @@
},
"azure/gpt-5-nano": {
"cache_read_input_token_cost": 5e-09,
"deprecation_date": "2027-02-09",
"input_cost_per_token": 5e-08,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5670,6 +5693,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"deprecation_date": "2027-05-15",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -5737,6 +5761,7 @@
},
"azure/gpt-5.1-codex": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2027-05-15",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5798,6 +5823,7 @@
},
"azure/gpt-5.1-codex-mini": {
"cache_read_input_token_cost": 2.5e-08,
"deprecation_date": "2027-05-15",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5828,6 +5854,7 @@
},
"azure/gpt-5.2": {
"cache_read_input_token_cost": 1.75e-07,
"deprecation_date": "2027-06-08",
"input_cost_per_token": 1.75e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -6145,6 +6172,7 @@
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "azure",
"deprecation_date": "2027-09-02",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -6381,6 +6409,7 @@
"azure/gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"deprecation_date": "2027-09-07",
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"litellm_provider": "azure",
@ -7054,6 +7083,7 @@
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"deprecation_date": "2027-10-26",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -7411,6 +7441,7 @@
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 7.5e-07,
"litellm_provider": "azure",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -7492,6 +7523,7 @@
"cache_read_input_token_cost": 2e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "azure",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -7699,6 +7731,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
"litellm_provider": "azure",
"deprecation_date": "2027-06-16",
"mode": "image_generation",
"output_cost_per_image_token": 3.2e-05,
"supported_endpoints": [
@ -7724,6 +7757,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
"litellm_provider": "azure",
"deprecation_date": "2027-10-21",
"mode": "image_generation",
"output_cost_per_token": 1e-05,
"output_cost_per_image_token": 3e-05,
@ -7851,6 +7885,7 @@
},
"azure/o1": {
"cache_read_input_token_cost": 7.5e-06,
"deprecation_date": "2026-10-21",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -7945,6 +7980,7 @@
},
"azure/o3": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-10-21",
"input_cost_per_token": 2e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -8042,6 +8078,7 @@
},
"azure/o3-mini": {
"cache_read_input_token_cost": 5.5e-07,
"deprecation_date": "2026-10-01",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -8071,6 +8108,7 @@
"supports_vision": false
},
"azure/o3-pro": {
"deprecation_date": "2026-12-17",
"input_cost_per_token": 2e-05,
"input_cost_per_token_batches": 1e-05,
"litellm_provider": "azure",
@ -8133,6 +8171,7 @@
},
"azure/o4-mini": {
"cache_read_input_token_cost": 2.75e-07,
"deprecation_date": "2026-10-16",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -8877,6 +8916,7 @@
},
"azure_ai/FW-DeepSeek-V3.2": {
"cache_read_input_token_cost": 3.1e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 6.2e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 163840,
@ -8907,6 +8947,7 @@
},
"azure_ai/FW-GLM-5": {
"cache_read_input_token_cost": 2.2e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -8922,6 +8963,7 @@
},
"azure_ai/FW-GLM-5.1": {
"cache_read_input_token_cost": 2.86e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 1.54e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 202800,
@ -8988,6 +9030,7 @@
},
"azure_ai/FW-Kimi-K2.5": {
"cache_read_input_token_cost": 1.1e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 6.6e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
@ -9080,6 +9123,7 @@
},
"azure_ai/FW-MiniMax-M2.5": {
"cache_read_input_token_cost": 3.3e-08,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 3.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
@ -9164,6 +9208,7 @@
]
},
"azure_ai/MAI-Image-2e": {
"deprecation_date": "2026-08-15",
"input_cost_per_token": 5e-06,
"litellm_provider": "azure_ai",
"mode": "image_generation",
@ -9175,6 +9220,7 @@
]
},
"azure_ai/Llama-3.2-11B-Vision-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 3.7e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9188,6 +9234,7 @@
"supports_vision": true
},
"azure_ai/Llama-3.2-90B-Vision-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 2.04e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9249,6 +9296,7 @@
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-405B-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 5.33e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9271,6 +9319,7 @@
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-8B-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9453,6 +9502,7 @@
},
"azure_ai/mistral-document-ai-2505": {
"litellm_provider": "azure_ai",
"deprecation_date": "2026-07-20",
"ocr_cost_per_page": 0.003,
"mode": "ocr",
"supported_endpoints": [
@ -9529,6 +9579,7 @@
"output_cost_per_token": 0.0
},
"azure_ai/cohere-rerank-v3.5": {
"deprecation_date": "2026-05-14",
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
@ -9591,6 +9642,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-r1": {
"deprecation_date": "2026-08-13",
"input_cost_per_token": 1.35e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9614,6 +9666,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v3-0324": {
"deprecation_date": "2026-07-13",
"input_cost_per_token": 1.14e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9626,6 +9679,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v3.1": {
"deprecation_date": "2026-07-13",
"input_cost_per_token": 1.23e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9639,6 +9693,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-pro": {
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
@ -9652,6 +9707,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
@ -9683,6 +9739,7 @@
"supports_embedding_image_input": true
},
"azure_ai/global/grok-3": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9697,6 +9754,7 @@
"supports_web_search": true
},
"azure_ai/global/grok-3-mini": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9712,6 +9770,7 @@
"supports_web_search": true
},
"azure_ai/grok-3": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9726,6 +9785,7 @@
"supports_web_search": true
},
"azure_ai/grok-3-mini": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9776,6 +9836,7 @@
"input_cost_per_token": 2e-07,
"output_cost_per_token": 5e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2026-05-01",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
@ -9789,6 +9850,7 @@
"input_cost_per_token": 2e-07,
"output_cost_per_token": 5e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2026-05-01",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
@ -9863,6 +9925,7 @@
"supports_tool_choice": true
},
"azure_ai/kimi-k2.5": {
"deprecation_date": "2027-01-26",
"input_cost_per_token": 6e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
@ -9877,6 +9940,7 @@
"supports_vision": true
},
"azure_ai/kimi-k2.6": {
"deprecation_date": "2027-04-16",
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
@ -10004,6 +10068,7 @@
"supports_vision": true
},
"babbage-002": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 4e-07,
"litellm_provider": "text-completion-openai",
"max_input_tokens": 16384,
@ -12635,6 +12700,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-05,
"supports_native_structured_output": true,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -14801,6 +14867,7 @@
"mode": "search"
},
"davinci-002": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 2e-06,
"litellm_provider": "text-completion-openai",
"max_input_tokens": 16384,
@ -18357,6 +18424,7 @@
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-20",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
@ -18402,6 +18470,7 @@
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-02",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
@ -18795,6 +18864,7 @@
"input_cost_per_audio_token": 3e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-20",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
@ -19068,6 +19138,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-20",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
@ -19809,6 +19880,7 @@
"web_search_billing_unit": "per_query"
},
"gemini/gemini-robotics-er-1.6-preview": {
"deprecation_date": "2026-08-31",
"input_cost_per_audio_token": 2e-06,
"input_cost_per_token": 1e-06,
"litellm_provider": "gemini",
@ -23004,6 +23076,7 @@
"supports_tool_choice": true
},
"gpt-3.5-turbo-instruct": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 1.5e-06,
"litellm_provider": "text-completion-openai",
"max_input_tokens": 8192,
@ -30074,6 +30147,7 @@
]
},
"multimodalembedding@001": {
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2e-07,
"input_cost_per_image": 0.0001,
"input_cost_per_token": 8e-07,
@ -35835,7 +35909,7 @@
"source": "https://docs.mistral.ai/capabilities/code_generation/"
},
"text-embedding-004": {
"deprecation_date": "2026-01-14",
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2.5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -35847,6 +35921,7 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
},
"text-embedding-005": {
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2.5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -35920,6 +35995,7 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"text-moderation-007": {
"deprecation_date": "2025-10-27",
"input_cost_per_token": 0.0,
"litellm_provider": "openai",
"max_input_tokens": 32768,
@ -35929,6 +36005,7 @@
"output_cost_per_token": 0.0
},
"text-moderation-latest": {
"deprecation_date": "2025-10-27",
"input_cost_per_token": 0.0,
"litellm_provider": "openai",
"max_input_tokens": 32768,
@ -35938,6 +36015,7 @@
"output_cost_per_token": 0.0
},
"text-moderation-stable": {
"deprecation_date": "2025-10-27",
"input_cost_per_token": 0.0,
"litellm_provider": "openai",
"max_input_tokens": 32768,
@ -35947,6 +36025,7 @@
"output_cost_per_token": 0.0
},
"text-multilingual-embedding-002": {
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2.5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -39386,6 +39465,7 @@
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-02",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
@ -40308,6 +40388,7 @@
"supports_tool_choice": true
},
"vertex_ai/veo-2.0-generate-001": {
"deprecation_date": "2026-06-30",
"litellm_provider": "vertex_ai-video-models",
"max_input_tokens": 1024,
"max_tokens": 1024,
@ -40322,6 +40403,7 @@
]
},
"vertex_ai/veo-3.0-fast-generate-001": {
"deprecation_date": "2026-06-30",
"litellm_provider": "vertex_ai-video-models",
"max_input_tokens": 1024,
"max_tokens": 1024,
@ -40336,6 +40418,7 @@
]
},
"vertex_ai/veo-3.0-generate-001": {
"deprecation_date": "2026-06-30",
"litellm_provider": "vertex_ai-video-models",
"max_input_tokens": 1024,
"max_tokens": 1024,
@ -48138,6 +48221,7 @@
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
@ -48171,6 +48255,7 @@
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,

87
model_prices_and_context_window.json
View file

@ -2890,6 +2890,7 @@
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_1hr": 2e-06,
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2026-10-19",
"input_cost_per_token": 1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -2913,6 +2914,7 @@
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 5e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2026-10-19",
"max_input_tokens": 200000,
"max_output_tokens": 64000,
"max_tokens": 64000,
@ -2934,6 +2936,7 @@
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2.5e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-02-02",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -2963,6 +2966,7 @@
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2.5e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-04-06",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3086,6 +3090,7 @@
"cache_creation_input_token_cost": 1.875e-05,
"cache_creation_input_token_cost_above_1hr": 3e-05,
"cache_read_input_token_cost": 1.5e-06,
"deprecation_date": "2026-08-05",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -3107,6 +3112,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-19",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -3162,6 +3168,7 @@
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-02-10",
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
@ -3235,6 +3242,7 @@
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-10-26",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3327,6 +3335,7 @@
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-02",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3373,6 +3382,7 @@
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-02",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3419,6 +3429,7 @@
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 0.00012,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-07",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3464,6 +3475,7 @@
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 0.00012,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-07",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3505,6 +3517,7 @@
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3545,6 +3558,7 @@
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3585,6 +3599,7 @@
"input_cost_per_token": 2e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -3625,6 +3640,7 @@
"input_cost_per_token": 2e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -4493,6 +4509,7 @@
},
"azure/gpt-4.1": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "azure",
@ -4560,6 +4577,7 @@
},
"azure/gpt-4.1-mini": {
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 4e-07,
"input_cost_per_token_batches": 2e-07,
"litellm_provider": "azure",
@ -4627,6 +4645,7 @@
},
"azure/gpt-4.1-nano": {
"cache_read_input_token_cost": 2.5e-08,
"deprecation_date": "2026-10-14",
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
"litellm_provider": "azure",
@ -4903,6 +4922,7 @@
},
"azure/gpt-4o-mini": {
"cache_read_input_token_cost": 7.5e-08,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 1.65e-07,
"litellm_provider": "azure",
"max_input_tokens": 128000,
@ -5345,6 +5365,7 @@
},
"azure/gpt-5": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2027-02-09",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5508,6 +5529,7 @@
},
"azure/gpt-5-mini": {
"cache_read_input_token_cost": 2.5e-08,
"deprecation_date": "2027-02-09",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5573,6 +5595,7 @@
},
"azure/gpt-5-nano": {
"cache_read_input_token_cost": 5e-09,
"deprecation_date": "2027-02-09",
"input_cost_per_token": 5e-08,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5670,6 +5693,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"deprecation_date": "2027-05-15",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -5737,6 +5761,7 @@
},
"azure/gpt-5.1-codex": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2027-05-15",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5798,6 +5823,7 @@
},
"azure/gpt-5.1-codex-mini": {
"cache_read_input_token_cost": 2.5e-08,
"deprecation_date": "2027-05-15",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -5828,6 +5854,7 @@
},
"azure/gpt-5.2": {
"cache_read_input_token_cost": 1.75e-07,
"deprecation_date": "2027-06-08",
"input_cost_per_token": 1.75e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -6145,6 +6172,7 @@
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "azure",
"deprecation_date": "2027-09-02",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -6381,6 +6409,7 @@
"azure/gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"deprecation_date": "2027-09-07",
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"litellm_provider": "azure",
@ -7054,6 +7083,7 @@
"input_cost_per_token_priority": 1e-05,
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
"litellm_provider": "azure",
"deprecation_date": "2027-10-26",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -7411,6 +7441,7 @@
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 7.5e-07,
"litellm_provider": "azure",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -7492,6 +7523,7 @@
"cache_read_input_token_cost": 2e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "azure",
"deprecation_date": "2027-09-21",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
@ -7699,6 +7731,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
"litellm_provider": "azure",
"deprecation_date": "2027-06-16",
"mode": "image_generation",
"output_cost_per_image_token": 3.2e-05,
"supported_endpoints": [
@ -7724,6 +7757,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
"litellm_provider": "azure",
"deprecation_date": "2027-10-21",
"mode": "image_generation",
"output_cost_per_token": 1e-05,
"output_cost_per_image_token": 3e-05,
@ -7851,6 +7885,7 @@
},
"azure/o1": {
"cache_read_input_token_cost": 7.5e-06,
"deprecation_date": "2026-10-21",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -7945,6 +7980,7 @@
},
"azure/o3": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-10-21",
"input_cost_per_token": 2e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -8042,6 +8078,7 @@
},
"azure/o3-mini": {
"cache_read_input_token_cost": 5.5e-07,
"deprecation_date": "2026-10-01",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -8071,6 +8108,7 @@
"supports_vision": false
},
"azure/o3-pro": {
"deprecation_date": "2026-12-17",
"input_cost_per_token": 2e-05,
"input_cost_per_token_batches": 1e-05,
"litellm_provider": "azure",
@ -8133,6 +8171,7 @@
},
"azure/o4-mini": {
"cache_read_input_token_cost": 2.75e-07,
"deprecation_date": "2026-10-16",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
@ -8877,6 +8916,7 @@
},
"azure_ai/FW-DeepSeek-V3.2": {
"cache_read_input_token_cost": 3.1e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 6.2e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 163840,
@ -8907,6 +8947,7 @@
},
"azure_ai/FW-GLM-5": {
"cache_read_input_token_cost": 2.2e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
@ -8922,6 +8963,7 @@
},
"azure_ai/FW-GLM-5.1": {
"cache_read_input_token_cost": 2.86e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 1.54e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 202800,
@ -8988,6 +9030,7 @@
},
"azure_ai/FW-Kimi-K2.5": {
"cache_read_input_token_cost": 1.1e-07,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 6.6e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
@ -9080,6 +9123,7 @@
},
"azure_ai/FW-MiniMax-M2.5": {
"cache_read_input_token_cost": 3.3e-08,
"deprecation_date": "2027-07-01",
"input_cost_per_token": 3.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
@ -9164,6 +9208,7 @@
]
},
"azure_ai/MAI-Image-2e": {
"deprecation_date": "2026-08-15",
"input_cost_per_token": 5e-06,
"litellm_provider": "azure_ai",
"mode": "image_generation",
@ -9175,6 +9220,7 @@
]
},
"azure_ai/Llama-3.2-11B-Vision-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 3.7e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9188,6 +9234,7 @@
"supports_vision": true
},
"azure_ai/Llama-3.2-90B-Vision-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 2.04e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9249,6 +9296,7 @@
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-405B-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 5.33e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9271,6 +9319,7 @@
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-8B-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9453,6 +9502,7 @@
},
"azure_ai/mistral-document-ai-2505": {
"litellm_provider": "azure_ai",
"deprecation_date": "2026-07-20",
"ocr_cost_per_page": 0.003,
"mode": "ocr",
"supported_endpoints": [
@ -9529,6 +9579,7 @@
"output_cost_per_token": 0.0
},
"azure_ai/cohere-rerank-v3.5": {
"deprecation_date": "2026-05-14",
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
@ -9591,6 +9642,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-r1": {
"deprecation_date": "2026-08-13",
"input_cost_per_token": 1.35e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9614,6 +9666,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v3-0324": {
"deprecation_date": "2026-07-13",
"input_cost_per_token": 1.14e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
@ -9626,6 +9679,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v3.1": {
"deprecation_date": "2026-07-13",
"input_cost_per_token": 1.23e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9639,6 +9693,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-pro": {
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
@ -9652,6 +9707,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
@ -9683,6 +9739,7 @@
"supports_embedding_image_input": true
},
"azure_ai/global/grok-3": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9697,6 +9754,7 @@
"supports_web_search": true
},
"azure_ai/global/grok-3-mini": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9712,6 +9770,7 @@
"supports_web_search": true
},
"azure_ai/grok-3": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9726,6 +9785,7 @@
"supports_web_search": true
},
"azure_ai/grok-3-mini": {
"deprecation_date": "2026-05-01",
"input_cost_per_token": 2.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
@ -9776,6 +9836,7 @@
"input_cost_per_token": 2e-07,
"output_cost_per_token": 5e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2026-05-01",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
@ -9789,6 +9850,7 @@
"input_cost_per_token": 2e-07,
"output_cost_per_token": 5e-07,
"litellm_provider": "azure_ai",
"deprecation_date": "2026-05-01",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
@ -9863,6 +9925,7 @@
"supports_tool_choice": true
},
"azure_ai/kimi-k2.5": {
"deprecation_date": "2027-01-26",
"input_cost_per_token": 6e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
@ -9877,6 +9940,7 @@
"supports_vision": true
},
"azure_ai/kimi-k2.6": {
"deprecation_date": "2027-04-16",
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
@ -10004,6 +10068,7 @@
"supports_vision": true
},
"babbage-002": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 4e-07,
"litellm_provider": "text-completion-openai",
"max_input_tokens": 16384,
@ -12635,6 +12700,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-05,
"supports_native_structured_output": true,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -14801,6 +14867,7 @@
"mode": "search"
},
"davinci-002": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 2e-06,
"litellm_provider": "text-completion-openai",
"max_input_tokens": 16384,
@ -18357,6 +18424,7 @@
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-20",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
@ -18402,6 +18470,7 @@
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-02",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
@ -18795,6 +18864,7 @@
"input_cost_per_audio_token": 3e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-20",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
@ -19068,6 +19138,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-20",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
@ -19809,6 +19880,7 @@
"web_search_billing_unit": "per_query"
},
"gemini/gemini-robotics-er-1.6-preview": {
"deprecation_date": "2026-08-31",
"input_cost_per_audio_token": 2e-06,
"input_cost_per_token": 1e-06,
"litellm_provider": "gemini",
@ -23004,6 +23076,7 @@
"supports_tool_choice": true
},
"gpt-3.5-turbo-instruct": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 1.5e-06,
"litellm_provider": "text-completion-openai",
"max_input_tokens": 8192,
@ -30074,6 +30147,7 @@
]
},
"multimodalembedding@001": {
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2e-07,
"input_cost_per_image": 0.0001,
"input_cost_per_token": 8e-07,
@ -35835,7 +35909,7 @@
"source": "https://docs.mistral.ai/capabilities/code_generation/"
},
"text-embedding-004": {
"deprecation_date": "2026-01-14",
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2.5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -35847,6 +35921,7 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
},
"text-embedding-005": {
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2.5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -35920,6 +35995,7 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"text-moderation-007": {
"deprecation_date": "2025-10-27",
"input_cost_per_token": 0.0,
"litellm_provider": "openai",
"max_input_tokens": 32768,
@ -35929,6 +36005,7 @@
"output_cost_per_token": 0.0
},
"text-moderation-latest": {
"deprecation_date": "2025-10-27",
"input_cost_per_token": 0.0,
"litellm_provider": "openai",
"max_input_tokens": 32768,
@ -35938,6 +36015,7 @@
"output_cost_per_token": 0.0
},
"text-moderation-stable": {
"deprecation_date": "2025-10-27",
"input_cost_per_token": 0.0,
"litellm_provider": "openai",
"max_input_tokens": 32768,
@ -35947,6 +36025,7 @@
"output_cost_per_token": 0.0
},
"text-multilingual-embedding-002": {
"deprecation_date": "2027-04-01",
"input_cost_per_character": 2.5e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -39386,6 +39465,7 @@
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "vertex_ai-language-models",
"deprecation_date": "2026-10-02",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
@ -40308,6 +40388,7 @@
"supports_tool_choice": true
},
"vertex_ai/veo-2.0-generate-001": {
"deprecation_date": "2026-06-30",
"litellm_provider": "vertex_ai-video-models",
"max_input_tokens": 1024,
"max_tokens": 1024,
@ -40322,6 +40403,7 @@
]
},
"vertex_ai/veo-3.0-fast-generate-001": {
"deprecation_date": "2026-06-30",
"litellm_provider": "vertex_ai-video-models",
"max_input_tokens": 1024,
"max_tokens": 1024,
@ -40336,6 +40418,7 @@
]
},
"vertex_ai/veo-3.0-generate-001": {
"deprecation_date": "2026-06-30",
"litellm_provider": "vertex_ai-video-models",
"max_input_tokens": 1024,
"max_tokens": 1024,
@ -48138,6 +48221,7 @@
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
@ -48171,6 +48255,7 @@
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,