phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

added sambanova cloud models (#7187)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 12s
Details

Browse source 
Co-authored-by: Rodrigo Maldonado <rodrigo.maldonado@sambanovasystems.com>
This commit is contained in:
Rodrigo Maldonado 2024-12-18 14:20:38 -05:00 • committed by GitHub
parent 523beedb4c
commit d214d3cc3f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 70 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

70
model_prices_and_context_window.json
View file

@ -15,6 +15,76 @@
"supports_prompt_caching": true, "supports_prompt_caching": true,
"supports_response_schema": true "supports_response_schema": true
}, },
"sambanova/Meta-Llama-3.1-8B-Instruct": {
"max_tokens": 16000,
"max_input_tokens": 16000,
"max_output_tokens": 16000,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000002,
"litellm_provider": "sambanova",
"supports_function_calling": true,
"mode": "chat"
},
"sambanova/Meta-Llama-3.1-70B-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.0000006,
"output_cost_per_token": 0.0000012,
"litellm_provider": "sambanova",
"supports_function_calling": true,
"mode": "chat"
},
"sambanova/Meta-Llama-3.1-405B-Instruct": {
"max_tokens": 16000,
"max_input_tokens": 16000,
"max_output_tokens": 16000,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.000010,
"litellm_provider": "sambanova",
"supports_function_calling": true,
"mode": "chat"
},
"sambanova/Meta-Llama-3.2-1B-Instruct": {
"max_tokens": 16000,
"max_input_tokens": 16000,
"max_output_tokens": 16000,
"input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000008,
"litellm_provider": "sambanova",
"supports_function_calling": true,
"mode": "chat"
},
"sambanova/Meta-Llama-3.2-3B-Instruct": {
"max_tokens": 4000,
"max_input_tokens": 4000,
"max_output_tokens": 4000,
"input_cost_per_token": 0.0000008,
"output_cost_per_token": 0.0000016,
"litellm_provider": "sambanova",
"supports_function_calling": true,
"mode": "chat"
},
"sambanova/Qwen2.5-Coder-32B-Instruct": {
"max_tokens": 8000,
"max_input_tokens": 8000,
"max_output_tokens": 8000,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.000003,
"litellm_provider": "sambanova",
"supports_function_calling": true,
"mode": "chat"
},
"sambanova/Qwen2.5-72B-Instruct": {
"max_tokens": 8000,
"max_input_tokens": 8000,
"max_output_tokens": 8000,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000004,
"litellm_provider": "sambanova",
"supports_function_calling": true,
"mode": "chat"
},
"gpt-4": { "gpt-4": {
"max_tokens": 4096, "max_tokens": 4096,
"max_input_tokens": 8192, "max_input_tokens": 8192,