github/claude-relay-service
1
0
Fork 0
mirror of https://github.com/Wei-Shaw/claude-relay-service.git synced 2026-01-22 16:43:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: 同步模型价格数据 (c2ad0cd96d378b8cf8782b84ad06de436d2fa92cbd74c46afd8862c9b577ea70)

Browse Source
This commit is contained in:
github-actions[bot]
2026-01-13 22:33:45 +00:00
parent c5069a06a4
commit d444527a8c
2 changed files with 52 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
model_prices_and_context_window.json
View File

@@ -1644,7 +1644,7 @@
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.38e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -1944,7 +1944,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -2893,7 +2893,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -2964,7 +2964,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -2997,7 +2997,7 @@
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -3092,9 +3092,9 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/",
@@ -3377,7 +3377,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -3440,7 +3440,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -3500,7 +3500,7 @@
"cache_read_input_token_cost": 1.75e-07,
"input_cost_per_token": 1.75e-06,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -3637,7 +3637,7 @@
"azure/gpt-5.2-pro": {
"input_cost_per_token": 2.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -3668,7 +3668,7 @@
"azure/gpt-5.2-pro-2025-12-11": {
"input_cost_per_token": 2.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -4684,7 +4684,7 @@
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.38e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -7813,14 +7813,14 @@
"supports_vision": true
},
"deepseek-chat": {
"cache_read_input_token_cost": 6e-08,
"input_cost_per_token": 6e-07,
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 2.8e-07,
"litellm_provider": "deepseek",
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.7e-06,
"output_cost_per_token": 4.2e-07,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@@ -7834,14 +7834,14 @@
"supports_tool_choice": true
},
"deepseek-reasoner": {
"cache_read_input_token_cost": 6e-08,
"input_cost_per_token": 6e-07,
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 2.8e-07,
"litellm_provider": "deepseek",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 1.7e-06,
"output_cost_per_token": 4.2e-07,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@@ -10045,15 +10045,15 @@
},
"deepseek/deepseek-chat": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 2.7e-07,
"input_cost_per_token_cache_hit": 7e-08,
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 2.8e-07,
"input_cost_per_token_cache_hit": 2.8e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.1e-06,
"output_cost_per_token": 4.2e-07,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
@@ -10089,14 +10089,15 @@
"supports_tool_choice": true
},
"deepseek/deepseek-reasoner": {
"input_cost_per_token": 5.5e-07,
"input_cost_per_token_cache_hit": 1.4e-07,
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 2.8e-07,
"input_cost_per_token_cache_hit": 2.8e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2.19e-06,
"output_cost_per_token": 4.2e-07,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
@@ -17470,7 +17471,7 @@
"input_cost_per_token_flex": 6.25e-07,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -17507,7 +17508,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -17543,7 +17544,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -17852,7 +17853,7 @@
"input_cost_per_token_flex": 6.25e-07,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -17887,9 +17888,9 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"supported_endpoints": [
@@ -17951,7 +17952,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -17983,7 +17984,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -18046,7 +18047,7 @@
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@@ -18081,7 +18082,7 @@
"input_cost_per_token_flex": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -18120,7 +18121,7 @@
"input_cost_per_token_flex": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -18158,7 +18159,7 @@
"input_cost_per_token_flex": 2.5e-08,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -18193,7 +18194,7 @@
"input_cost_per_token": 5e-08,
"input_cost_per_token_flex": 2.5e-08,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -23206,9 +23207,9 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"supported_modalities": [
@@ -23225,7 +23226,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -23244,7 +23245,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -23263,7 +23264,7 @@
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 2.5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@@ -23282,7 +23283,7 @@
"cache_read_input_token_cost": 5e-09,
"input_cost_per_token": 5e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",

2
model_prices_and_context_window.sha256
View File

@@ -1 +1 @@
f12fec3516e45adc1566fd305e063b03f3b3c2bcd97cb84be1a1c61f3df9d0ca
c2ad0cd96d378b8cf8782b84ad06de436d2fa92cbd74c46afd8862c9b577ea70