tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-23 22:27:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1368 from deepinfra/udpate-models-2

Browse Source 
Update deepinfra models
This commit is contained in:
Ishaan Jaff
2024-01-08 22:46:14 +05:30
committed by GitHub
parent 6263103680 2486f92523
commit 8a85b719f7
1 changed files with 106 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model_prices_and_context_window.json
+106 -22
View File
@@ -1477,48 +1477,132 @@
"litellm_provider": "ollama",
"mode": "completion"
},
"deepinfra/lizpreciatior/lzlv_70b_fp16_hf": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000070,
"output_cost_per_token": 0.00000090,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/Gryphe/MythoMax-L2-13b": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000022,
"output_cost_per_token": 0.00000022,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/mistralai/Mistral-7B-Instruct-v0.1": {
"max_tokens": 32768,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000013,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/meta-llama/Llama-2-70b-chat-hf": {
"max_tokens": 4096,
"input_cost_per_token": 0.000000700,
"output_cost_per_token": 0.000000950,
"input_cost_per_token": 0.00000070,
"output_cost_per_token": 0.00000090,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b": {
"max_tokens": 32768,
"input_cost_per_token": 0.00000027,
"output_cost_per_token": 0.00000027,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/codellama/CodeLlama-34b-Instruct-hf": {
"max_tokens": 4096,
"input_cost_per_token": 0.0000006,
"output_cost_per_token": 0.0000006,
"input_cost_per_token": 0.00000060,
"output_cost_per_token": 0.00000060,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/meta-llama/Llama-2-13b-chat-hf": {
},
"deepinfra/deepinfra/mixtral": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000035,
"output_cost_per_token": 0.00000035,
"input_cost_per_token": 0.00000027,
"output_cost_per_token": 0.00000027,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/meta-llama/Llama-2-7b-chat-hf": {
"mode": "completion"
},
"deepinfra/Phind/Phind-CodeLlama-34B-v2": {
"max_tokens": 4096,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"input_cost_per_token": 0.00000060,
"output_cost_per_token": 0.00000060,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/mistralai/Mistral-7B-Instruct-v0.1": {
},
"deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": {
"max_tokens": 32768,
"input_cost_per_token": 0.00000027,
"output_cost_per_token": 0.00000027,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/deepinfra/airoboros-70b": {
"max_tokens": 4096,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"input_cost_per_token": 0.00000070,
"output_cost_per_token": 0.00000090,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1": {
},
"deepinfra/01-ai/Yi-34B-Chat": {
"max_tokens": 4096,
"input_cost_per_token": 0.0000007,
"output_cost_per_token": 0.00000095,
"input_cost_per_token": 0.00000060,
"output_cost_per_token": 0.00000060,
"litellm_provider": "deepinfra",
"mode": "chat"
},
},
"deepinfra/01-ai/Yi-6B-200K": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000013,
"litellm_provider": "deepinfra",
"mode": "completion"
},
"deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000070,
"output_cost_per_token": 0.00000090,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/meta-llama/Llama-2-13b-chat-hf": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000022,
"output_cost_per_token": 0.00000022,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/amazon/MistralLite": {
"max_tokens": 32768,
"input_cost_per_token": 0.00000020,
"output_cost_per_token": 0.00000020,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/meta-llama/Llama-2-7b-chat-hf": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000013,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/01-ai/Yi-34B-200K": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000060,
"output_cost_per_token": 0.00000060,
"litellm_provider": "deepinfra",
"mode": "completion"
},
"deepinfra/openchat/openchat_3.5": {
"max_tokens": 4096,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000013,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"perplexity/pplx-7b-chat": {
"max_tokens": 8192,
"input_cost_per_token": 0.0000000,