scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 79

fix model prices

Browse source
This commit is contained in:
Ishaan Jaff 2024-05-15 21:00:56 -07:00
parent 881812d5de
commit 5300a4c9b3
1 changed files with 54 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
litellm/model_prices_and_context_window_backup.json
View file

@ -2967,6 +2967,24 @@
"litellm_provider": "ollama",
"mode": "completion"
},
"ollama/llama3": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/llama3:70b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/mistral": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -2976,6 +2994,42 @@
"litellm_provider": "ollama",
"mode": "completion"
},
"ollama/mistral-7B-Instruct-v0.1": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/mistral-7B-Instruct-v0.2": {
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/mixtral-8x7B-Instruct-v0.1": {
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/mixtral-8x22B-Instruct-v0.1": {
"max_tokens": 65536,
"max_input_tokens": 65536,
"max_output_tokens": 65536,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/codellama": {
"max_tokens": 4096,
"max_input_tokens": 4096,