forked from phoenix/litellm-mirror
build(model_prices_and_context_window.json): add token-based replicate costs to model cost map
This commit is contained in:
Krrish Dholakia
parent
2cfb97141d
commit
dc5c175406
2 changed files with 234 additions and 0 deletions
|
|
@ -1418,6 +1418,123 @@
|
|||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-13b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.0000001,
|
||||
"output_cost_per_token": 0.0000005,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-13b-chat": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.0000001,
|
||||
"output_cost_per_token": 0.0000005,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-70b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-70b-chat": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-7b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-7b-chat": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-70b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-70b-instruct": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-8b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-8b-instruct": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/mistralai/mistral-7b-v0.1": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/mistralai/mistral-7b-instruct-v0.2": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/mistralai/mixtral-8x7b-instruct-v0.1": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.0000003,
|
||||
"output_cost_per_token": 0.000001,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"openrouter/openai/gpt-3.5-turbo": {
|
||||
"max_tokens": 4095,
|
||||
"input_cost_per_token": 0.0000015,
|
||||
|
|
|
|||
|
|
@ -1418,6 +1418,123 @@
|
|||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-13b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.0000001,
|
||||
"output_cost_per_token": 0.0000005,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-13b-chat": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.0000001,
|
||||
"output_cost_per_token": 0.0000005,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-70b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-70b-chat": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-7b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-2-7b-chat": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-70b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-70b-instruct": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000065,
|
||||
"output_cost_per_token": 0.00000275,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-8b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/meta/llama-3-8b-instruct": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/mistralai/mistral-7b-v0.1": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/mistralai/mistral-7b-instruct-v0.2": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"output_cost_per_token": 0.00000025,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"replicate/mistralai/mixtral-8x7b-instruct-v0.1": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.0000003,
|
||||
"output_cost_per_token": 0.000001,
|
||||
"litellm_provider": "replicate",
|
||||
"mode": "chat"
|
||||
},
|
||||
"openrouter/openai/gpt-3.5-turbo": {
|
||||
"max_tokens": 4095,
|
||||
"input_cost_per_token": 0.0000015,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue