Nebius model pricing info updted (#11445)

This commit is contained in:
Akim Tsvigun 2025-06-06 19:43:04 +02:00 • committed by GitHub
parent 2aa75e1403
commit 32281de91f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -14184,5 +14184,133 @@
"max_output_tokens": 4096,
"litellm_provider": "featherless_ai",
"mode": "chat"
},
"nebius/deepseek-ai/DeepSeek-V3-0324": {
"max_tokens": 128000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000015,
"litellm_provider": "nebius",
"supports_function_calling": true,
"mode": "chat"
},
"nebius/deepseek-ai/DeepSeek-V3-0324-fast": {
"max_tokens": 128000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000006,
"litellm_provider": "nebius",
"supports_function_calling": true,
"mode": "chat"
},
"nebius/deepseek-ai/DeepSeek-R1-0528": {
"max_tokens": 128000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000015,
"litellm_provider": "nebius",
"supports_function_calling": false,
"mode": "chat"
},
"nebius/deepseek-ai/DeepSeek-R1-fast": {
"max_tokens": 128000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000006,
"litellm_provider": "nebius",
"supports_function_calling": false,
"mode": "chat"
},
"nebius/meta-llama/Llama-3.3-70B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.0000004,
"litellm_provider": "nebius",
"supports_function_calling": true,
"mode": "chat"
},
"nebius/Qwen/Qwen3-235B-A22B": {
"max_tokens": 40000,
"max_input_tokens": 32000,
"max_output_tokens": 8000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000006,
"litellm_provider": "nebius",
"supports_function_calling": true,
"mode": "chat"
},
"nebius/Qwen/Qwen3-30B-A3B": {
"max_tokens": 40000,
"max_input_tokens": 32000,
"max_output_tokens": 8000,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000003,
"litellm_provider": "nebius",
"supports_function_calling": true,
"mode": "chat"
},
"nebius/Qwen/Qwen3-30B-A3B-fast": {
"max_tokens": 40000,
"max_input_tokens": 32000,
"max_output_tokens": 8000,
"input_cost_per_token": 0.0000003,
"output_cost_per_token": 0.0000009,
"litellm_provider": "nebius",
"supports_function_calling": true,
"mode": "chat"
},
"nebius/Qwen/Qwen3-32B-fast": {
"max_tokens": 40000,
"max_input_tokens": 32000,
"max_output_tokens": 8000,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000003,
"litellm_provider": "nebius",
"supports_function_calling": true,
"mode": "chat"
},
"nebius/Qwen/Qwen2.5-VL-72B-Instruct": {
"max_tokens": 32000,
"max_input_tokens": 24000,
"max_output_tokens": 8000,
"input_cost_per_token": 0.00000025,
"output_cost_per_token": 0.00000075,
"litellm_provider": "nebius",
"supports_function_calling": true,
"supports_vision": true,
"mode": "chat"
},
"nebius/google/gemma-3-27b-it-fast": {
"max_tokens": 128000,
"max_input_tokens": 64000,
"max_output_tokens": 64000,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000006,
"litellm_provider": "nebius",
"supports_function_calling": true,
"supports_vision": true,
"mode": "chat"
},
"nebius/BAAI/bge-en-icl": {
"max_tokens": 32000,
"max_input_tokens": 32000,
"input_cost_per_token": 0.00000001,
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding"
},
"nebius/BAAI/bge-multilingual-gemma2": {
"max_tokens": 32000,
"max_input_tokens": 32000,
"input_cost_per_token": 0.00000001,
"output_cost_per_token": 0.0,
"litellm_provider": "nebius",
"mode": "embedding"
}
}