phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

Merge pull request #3545 from Merlinvt/main

Browse source 
add additional models from openrouter
This commit is contained in:
Krish Dholakia 2024-05-11 09:08:28 -07:00 • committed by GitHub
commit 3be5b72b43
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 132 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

142
model_prices_and_context_window.json
View file

@ -1571,6 +1571,135 @@
"litellm_provider": "replicate",
"mode": "chat"
},
"openrouter/microsoft/wizardlm-2-8x22b:nitro": {
"max_tokens": 65536,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000001,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/google/gemini-pro-1.5": {
"max_tokens": 8192,
"max_input_tokens": 1000000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.0000075,
"input_cost_per_image": 0.00265,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true
},
"openrouter/mistralai/mixtral-8x22b-instruct": {
"max_tokens": 65536,
"input_cost_per_token": 0.00000065,
"output_cost_per_token": 0.00000065,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/cohere/command-r-plus": {
"max_tokens": 128000,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000015,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/databricks/dbrx-instruct": {
"max_tokens": 32768,
"input_cost_per_token": 0.0000006,
"output_cost_per_token": 0.0000006,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/anthropic/claude-3-haiku": {
"max_tokens": 200000,
"input_cost_per_token": 0.00000025,
"output_cost_per_token": 0.00000125,
"input_cost_per_image": 0.0004,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true
},
"openrouter/anthropic/claude-3-sonnet": {
"max_tokens": 200000,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000015,
"input_cost_per_image": 0.0048,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true
},
"openrouter/mistralai/mistral-large": {
"max_tokens": 32000,
"input_cost_per_token": 0.000008,
"output_cost_per_token": 0.000024,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/cognitivecomputations/dolphin-mixtral-8x7b": {
"max_tokens": 32769,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/google/gemini-pro-vision": {
"max_tokens": 45875,
"input_cost_per_token": 0.000000125,
"output_cost_per_token": 0.000000375,
"input_cost_per_image": 0.0025,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true
},
"openrouter/fireworks/firellava-13b": {
"max_tokens": 4096,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/meta-llama/llama-3-8b-instruct:free": {
"max_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/meta-llama/llama-3-8b-instruct:extended": {
"max_tokens": 16384,
"input_cost_per_token": 0.000000225,
"output_cost_per_token": 0.00000225,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/meta-llama/llama-3-70b-instruct:nitro": {
"max_tokens": 8192,
"input_cost_per_token": 0.0000009,
"output_cost_per_token": 0.0000009,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/meta-llama/llama-3-70b-instruct": {
"max_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/openai/gpt-4-vision-preview": {
"max_tokens": 130000,
"input_cost_per_token": 0.00001,
"output_cost_per_token": 0.00003,
"input_cost_per_image": 0.01445,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true
},
"openrouter/openai/gpt-3.5-turbo": {
"max_tokens": 4095,
"input_cost_per_token": 0.0000015,
@ -1621,14 +1750,14 @@
"tool_use_system_prompt_tokens": 395
},
"openrouter/google/palm-2-chat-bison": {
"max_tokens": 8000,
"max_tokens": 25804,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005,
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/google/palm-2-codechat-bison": {
"max_tokens": 8000,
"max_tokens": 20070,
"input_cost_per_token": 0.0000005,
"output_cost_per_token": 0.0000005,
"litellm_provider": "openrouter",
@ -1711,13 +1840,6 @@
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/meta-llama/llama-3-70b-instruct": {
"max_tokens": 8192,
"input_cost_per_token": 0.0000008,
"output_cost_per_token": 0.0000008,
"litellm_provider": "openrouter",
"mode": "chat"
},
"j2-ultra": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -3226,4 +3348,4 @@
"mode": "embedding"
}
}
}