Skip to content

Commit 3dd8cd3

Browse files
tomukmatthewstomukmatthews
committed
Remove redundant null tokens from model cost map
1 parent 3bb9cc9 commit 3dd8cd3

File tree

2 files changed

+0
-84
lines changed

2 files changed

+0
-84
lines changed

‎litellm/model_prices_and_context_window_backup.json

-42
Original file line numberDiff line numberDiff line change
@@ -12199,59 +12199,41 @@
1219912199
"mode": "chat"
1220012200
},
1220112201
"nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
12202-
"max_tokens": null,
12203-
"max_input_tokens": null,
12204-
"max_output_tokens": null,
1220512202
"input_cost_per_token": 9e-8,
1220612203
"output_cost_per_token": 2.9e-7,
1220712204
"litellm_provider": "nscale",
1220812205
"mode": "chat",
1220912206
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1221012207
},
1221112208
"nscale/Qwen/Qwen2.5-Coder-3B-Instruct": {
12212-
"max_tokens": null,
12213-
"max_input_tokens": null,
12214-
"max_output_tokens": null,
1221512209
"input_cost_per_token": 1e-8,
1221612210
"output_cost_per_token": 3e-8,
1221712211
"litellm_provider": "nscale",
1221812212
"mode": "chat",
1221912213
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1222012214
},
1222112215
"nscale/Qwen/Qwen2.5-Coder-7B-Instruct": {
12222-
"max_tokens": null,
12223-
"max_input_tokens": null,
12224-
"max_output_tokens": null,
1222512216
"input_cost_per_token": 1e-8,
1222612217
"output_cost_per_token": 3e-8,
1222712218
"litellm_provider": "nscale",
1222812219
"mode": "chat",
1222912220
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1223012221
},
1223112222
"nscale/Qwen/Qwen2.5-Coder-32B-Instruct": {
12232-
"max_tokens": null,
12233-
"max_input_tokens": null,
12234-
"max_output_tokens": null,
1223512223
"input_cost_per_token": 6e-8,
1223612224
"output_cost_per_token": 2e-7,
1223712225
"litellm_provider": "nscale",
1223812226
"mode": "chat",
1223912227
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1224012228
},
1224112229
"nscale/Qwen/QwQ-32B": {
12242-
"max_tokens": null,
12243-
"max_input_tokens": null,
12244-
"max_output_tokens": null,
1224512230
"input_cost_per_token": 1.8e-7,
1224612231
"output_cost_per_token": 2e-7,
1224712232
"litellm_provider": "nscale",
1224812233
"mode": "chat",
1224912234
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1225012235
},
1225112236
"nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
12252-
"max_tokens": null,
12253-
"max_input_tokens": null,
12254-
"max_output_tokens": null,
1225512237
"input_cost_per_token": 3.75e-7,
1225612238
"output_cost_per_token": 3.75e-7,
1225712239
"litellm_provider": "nscale",
@@ -12260,9 +12242,6 @@
1226012242
"notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output."
1226112243
},
1226212244
"nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
12263-
"max_tokens": null,
12264-
"max_input_tokens": null,
12265-
"max_output_tokens": null,
1226612245
"input_cost_per_token": 2.5e-8,
1226712246
"output_cost_per_token": 2.5e-8,
1226812247
"litellm_provider": "nscale",
@@ -12271,9 +12250,6 @@
1227112250
"notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
1227212251
},
1227312252
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
12274-
"max_tokens": null,
12275-
"max_input_tokens": null,
12276-
"max_output_tokens": null,
1227712253
"input_cost_per_token": 9e-8,
1227812254
"output_cost_per_token": 9e-8,
1227912255
"litellm_provider": "nscale",
@@ -12282,9 +12258,6 @@
1228212258
"notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
1228312259
},
1228412260
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
12285-
"max_tokens": null,
12286-
"max_input_tokens": null,
12287-
"max_output_tokens": null,
1228812261
"input_cost_per_token": 2e-7,
1228912262
"output_cost_per_token": 2e-7,
1229012263
"litellm_provider": "nscale",
@@ -12293,9 +12266,6 @@
1229312266
"notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
1229412267
},
1229512268
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
12296-
"max_tokens": null,
12297-
"max_input_tokens": null,
12298-
"max_output_tokens": null,
1229912269
"input_cost_per_token": 7e-8,
1230012270
"output_cost_per_token": 7e-8,
1230112271
"litellm_provider": "nscale",
@@ -12304,9 +12274,6 @@
1230412274
"notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output."
1230512275
},
1230612276
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
12307-
"max_tokens": null,
12308-
"max_input_tokens": null,
12309-
"max_output_tokens": null,
1231012277
"input_cost_per_token": 1.5e-7,
1231112278
"output_cost_per_token": 1.5e-7,
1231212279
"litellm_provider": "nscale",
@@ -12315,9 +12282,6 @@
1231512282
"notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
1231612283
},
1231712284
"nscale/mistralai/mixtral-8x22b-instruct-v0.1": {
12318-
"max_tokens": null,
12319-
"max_input_tokens": null,
12320-
"max_output_tokens": null,
1232112285
"input_cost_per_token": 6e-7,
1232212286
"output_cost_per_token": 6e-7,
1232312287
"litellm_provider": "nscale",
@@ -12326,9 +12290,6 @@
1232612290
"notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
1232712291
},
1232812292
"nscale/meta-llama/Llama-3.1-8B-Instruct": {
12329-
"max_tokens": null,
12330-
"max_input_tokens": null,
12331-
"max_output_tokens": null,
1233212293
"input_cost_per_token": 3e-8,
1233312294
"output_cost_per_token": 3e-8,
1233412295
"litellm_provider": "nscale",
@@ -12337,9 +12298,6 @@
1233712298
"notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output."
1233812299
},
1233912300
"nscale/meta-llama/Llama-3.3-70B-Instruct": {
12340-
"max_tokens": null,
12341-
"max_input_tokens": null,
12342-
"max_output_tokens": null,
1234312301
"input_cost_per_token": 2e-7,
1234412302
"output_cost_per_token": 2e-7,
1234512303
"litellm_provider": "nscale",

‎model_prices_and_context_window.json

-42
Original file line numberDiff line numberDiff line change
@@ -12199,59 +12199,41 @@
1219912199
"mode": "chat"
1220012200
},
1220112201
"nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
12202-
"max_tokens": null,
12203-
"max_input_tokens": null,
12204-
"max_output_tokens": null,
1220512202
"input_cost_per_token": 9e-8,
1220612203
"output_cost_per_token": 2.9e-7,
1220712204
"litellm_provider": "nscale",
1220812205
"mode": "chat",
1220912206
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1221012207
},
1221112208
"nscale/Qwen/Qwen2.5-Coder-3B-Instruct": {
12212-
"max_tokens": null,
12213-
"max_input_tokens": null,
12214-
"max_output_tokens": null,
1221512209
"input_cost_per_token": 1e-8,
1221612210
"output_cost_per_token": 3e-8,
1221712211
"litellm_provider": "nscale",
1221812212
"mode": "chat",
1221912213
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1222012214
},
1222112215
"nscale/Qwen/Qwen2.5-Coder-7B-Instruct": {
12222-
"max_tokens": null,
12223-
"max_input_tokens": null,
12224-
"max_output_tokens": null,
1222512216
"input_cost_per_token": 1e-8,
1222612217
"output_cost_per_token": 3e-8,
1222712218
"litellm_provider": "nscale",
1222812219
"mode": "chat",
1222912220
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1223012221
},
1223112222
"nscale/Qwen/Qwen2.5-Coder-32B-Instruct": {
12232-
"max_tokens": null,
12233-
"max_input_tokens": null,
12234-
"max_output_tokens": null,
1223512223
"input_cost_per_token": 6e-8,
1223612224
"output_cost_per_token": 2e-7,
1223712225
"litellm_provider": "nscale",
1223812226
"mode": "chat",
1223912227
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1224012228
},
1224112229
"nscale/Qwen/QwQ-32B": {
12242-
"max_tokens": null,
12243-
"max_input_tokens": null,
12244-
"max_output_tokens": null,
1224512230
"input_cost_per_token": 1.8e-7,
1224612231
"output_cost_per_token": 2e-7,
1224712232
"litellm_provider": "nscale",
1224812233
"mode": "chat",
1224912234
"source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
1225012235
},
1225112236
"nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
12252-
"max_tokens": null,
12253-
"max_input_tokens": null,
12254-
"max_output_tokens": null,
1225512237
"input_cost_per_token": 3.75e-7,
1225612238
"output_cost_per_token": 3.75e-7,
1225712239
"litellm_provider": "nscale",
@@ -12260,9 +12242,6 @@
1226012242
"notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output."
1226112243
},
1226212244
"nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
12263-
"max_tokens": null,
12264-
"max_input_tokens": null,
12265-
"max_output_tokens": null,
1226612245
"input_cost_per_token": 2.5e-8,
1226712246
"output_cost_per_token": 2.5e-8,
1226812247
"litellm_provider": "nscale",
@@ -12271,9 +12250,6 @@
1227112250
"notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
1227212251
},
1227312252
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
12274-
"max_tokens": null,
12275-
"max_input_tokens": null,
12276-
"max_output_tokens": null,
1227712253
"input_cost_per_token": 9e-8,
1227812254
"output_cost_per_token": 9e-8,
1227912255
"litellm_provider": "nscale",
@@ -12282,9 +12258,6 @@
1228212258
"notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
1228312259
},
1228412260
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
12285-
"max_tokens": null,
12286-
"max_input_tokens": null,
12287-
"max_output_tokens": null,
1228812261
"input_cost_per_token": 2e-7,
1228912262
"output_cost_per_token": 2e-7,
1229012263
"litellm_provider": "nscale",
@@ -12293,9 +12266,6 @@
1229312266
"notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
1229412267
},
1229512268
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
12296-
"max_tokens": null,
12297-
"max_input_tokens": null,
12298-
"max_output_tokens": null,
1229912269
"input_cost_per_token": 7e-8,
1230012270
"output_cost_per_token": 7e-8,
1230112271
"litellm_provider": "nscale",
@@ -12304,9 +12274,6 @@
1230412274
"notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output."
1230512275
},
1230612276
"nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
12307-
"max_tokens": null,
12308-
"max_input_tokens": null,
12309-
"max_output_tokens": null,
1231012277
"input_cost_per_token": 1.5e-7,
1231112278
"output_cost_per_token": 1.5e-7,
1231212279
"litellm_provider": "nscale",
@@ -12315,9 +12282,6 @@
1231512282
"notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
1231612283
},
1231712284
"nscale/mistralai/mixtral-8x22b-instruct-v0.1": {
12318-
"max_tokens": null,
12319-
"max_input_tokens": null,
12320-
"max_output_tokens": null,
1232112285
"input_cost_per_token": 6e-7,
1232212286
"output_cost_per_token": 6e-7,
1232312287
"litellm_provider": "nscale",
@@ -12326,9 +12290,6 @@
1232612290
"notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
1232712291
},
1232812292
"nscale/meta-llama/Llama-3.1-8B-Instruct": {
12329-
"max_tokens": null,
12330-
"max_input_tokens": null,
12331-
"max_output_tokens": null,
1233212293
"input_cost_per_token": 3e-8,
1233312294
"output_cost_per_token": 3e-8,
1233412295
"litellm_provider": "nscale",
@@ -12337,9 +12298,6 @@
1233712298
"notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output."
1233812299
},
1233912300
"nscale/meta-llama/Llama-3.3-70B-Instruct": {
12340-
"max_tokens": null,
12341-
"max_input_tokens": null,
12342-
"max_output_tokens": null,
1234312301
"input_cost_per_token": 2e-7,
1234412302
"output_cost_per_token": 2e-7,
1234512303
"litellm_provider": "nscale",

0 commit comments

Comments
 (0)