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

(fix) Fix Groq pricing for llama3.1 (#6114)

Browse source 
* Adjust ollama models to chat instead of completions

* Fix Groq prices for llama3.1
This commit is contained in:
Kyrylo Yefimenko 2024-10-08 15:50:58 +01:00 • committed by GitHub
parent 92a1924112
commit b68fee48a6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

12
model_prices_and_context_window.json
View file

@ -1491,8 +1491,8 @@
"max_tokens": 8192, "max_tokens": 8192,
"max_input_tokens": 8192, "max_input_tokens": 8192,
"max_output_tokens": 8192, "max_output_tokens": 8192,
"input_cost_per_token": 0.00000059, "input_cost_per_token": 0.00000005,
"output_cost_per_token": 0.00000079, "output_cost_per_token": 0.00000008,
"litellm_provider": "groq", "litellm_provider": "groq",
"mode": "chat", "mode": "chat",
"supports_function_calling": true "supports_function_calling": true
@ -5303,7 +5303,7 @@
"input_cost_per_token": 0.0, "input_cost_per_token": 0.0,
"output_cost_per_token": 0.0, "output_cost_per_token": 0.0,
"litellm_provider": "ollama", "litellm_provider": "ollama",
"mode": "completion" "mode": "chat"
}, },
"ollama/llama2:7b": { "ollama/llama2:7b": {
"max_tokens": 4096, "max_tokens": 4096,
@ -5312,7 +5312,7 @@
"input_cost_per_token": 0.0, "input_cost_per_token": 0.0,
"output_cost_per_token": 0.0, "output_cost_per_token": 0.0,
"litellm_provider": "ollama", "litellm_provider": "ollama",
"mode": "completion" "mode": "chat"
}, },
"ollama/llama2:13b": { "ollama/llama2:13b": {
"max_tokens": 4096, "max_tokens": 4096,
@ -5321,7 +5321,7 @@
"input_cost_per_token": 0.0, "input_cost_per_token": 0.0,
"output_cost_per_token": 0.0, "output_cost_per_token": 0.0,
"litellm_provider": "ollama", "litellm_provider": "ollama",
"mode": "completion" "mode": "chat"
}, },
"ollama/llama2:70b": { "ollama/llama2:70b": {
"max_tokens": 4096, "max_tokens": 4096,
@ -5330,7 +5330,7 @@
"input_cost_per_token": 0.0, "input_cost_per_token": 0.0,
"output_cost_per_token": 0.0, "output_cost_per_token": 0.0,
"litellm_provider": "ollama", "litellm_provider": "ollama",
"mode": "completion" "mode": "chat"
}, },
"ollama/llama2-uncensored": { "ollama/llama2-uncensored": {
"max_tokens": 4096, "max_tokens": 4096,