add models served from ollama cloud

This commit is contained in:
Wenxi Onyx 2025-09-28 13:20:35 -07:00
parent 208cd5fcb5
commit 4adb854e51

View file

@ -16247,6 +16247,36 @@
"output_cost_per_token": 0.0,
"supports_function_calling": true
},
"ollama/deepseek-v3.1:671b-cloud" : {
"input_cost_per_token": 0.0,
"litellm_provider": "ollama",
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 0.0,
"supports_function_calling": true
},
"ollama/gpt-oss-120b-cloud" : {
"input_cost_per_token": 0.0,
"litellm_provider": "ollama",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0,
"supports_function_calling": true
},
"ollama/gpt-oss-20b-cloud" : {
"input_cost_per_token": 0.0,
"litellm_provider": "ollama",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0,
"supports_function_calling": true
},
"ollama/internlm2_5-20b-chat": {
"input_cost_per_token": 0.0,
"litellm_provider": "ollama",
@ -16408,6 +16438,16 @@
"mode": "completion",
"output_cost_per_token": 0.0
},
"ollama/qwen3-coder:480b-cloud": {
"input_cost_per_token": 0.0,
"litellm_provider": "ollama",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 0.0,
"supports_function_calling": true
},
"ollama/vicuna": {
"input_cost_per_token": 0.0,
"litellm_provider": "ollama",