Skip to content

Commit f44d4a7

Browse files
committed
chore(cost-map): accept the mirrored map's search_free_requests and token_count_model.litellm_provider in the schema
1 parent ebf92c9 commit f44d4a7

1 file changed

Lines changed: 94 additions & 46 deletions

File tree

‎model_prices_and_context_window.schema.json‎

Lines changed: 94 additions & 46 deletions
Original file line numberDiff line numberDiff line change
@@ -93,11 +93,6 @@
9393
"minimum": 0,
9494
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
9595
},
96-
"cache_creation_input_token_cost_above_128k_tokens": {
97-
"type": "number",
98-
"minimum": 0,
99-
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
100-
},
10196
"cache_creation_input_token_cost_above_1hr": {
10297
"type": "number",
10398
"minimum": 0,
@@ -118,22 +113,17 @@
118113
"minimum": 0,
119114
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
120115
},
121-
"cache_creation_input_token_cost_above_200k_tokens_batches": {
122-
"type": "number",
123-
"minimum": 0,
124-
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
125-
},
126-
"cache_creation_input_token_cost_above_256k_tokens": {
116+
"cache_creation_input_token_cost_above_272k_tokens": {
127117
"type": "number",
128118
"minimum": 0,
129119
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
130120
},
131-
"cache_creation_input_token_cost_above_272k_tokens": {
121+
"cache_creation_input_token_cost_above_272k_tokens_batches": {
132122
"type": "number",
133123
"minimum": 0,
134124
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
135125
},
136-
"cache_creation_input_token_cost_above_272k_tokens_batches": {
126+
"cache_creation_input_token_cost_above_272k_tokens_decisions": {
137127
"type": "number",
138128
"minimum": 0,
139129
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -153,12 +143,11 @@
153143
"minimum": 0,
154144
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
155145
},
156-
"cache_creation_input_token_cost_above_32k_tokens": {
146+
"cache_creation_input_token_cost_batches": {
157147
"type": "number",
158-
"minimum": 0,
159-
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
148+
"minimum": 0
160149
},
161-
"cache_creation_input_token_cost_batches": {
150+
"cache_creation_input_token_cost_decisions": {
162151
"type": "number",
163152
"minimum": 0
164153
},
@@ -199,11 +188,6 @@
199188
"minimum": 0,
200189
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
201190
},
202-
"cache_read_input_token_cost_above_128k_tokens": {
203-
"type": "number",
204-
"minimum": 0,
205-
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
206-
},
207191
"cache_read_input_token_cost_above_200k_tokens": {
208192
"type": "number",
209193
"minimum": 0,
@@ -219,17 +203,17 @@
219203
"minimum": 0,
220204
"description": "Priority service-tier rate for the same-named base field."
221205
},
222-
"cache_read_input_token_cost_above_256k_tokens": {
206+
"cache_read_input_token_cost_above_272k_tokens": {
223207
"type": "number",
224208
"minimum": 0,
225209
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
226210
},
227-
"cache_read_input_token_cost_above_272k_tokens": {
211+
"cache_read_input_token_cost_above_272k_tokens_batches": {
228212
"type": "number",
229213
"minimum": 0,
230214
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
231215
},
232-
"cache_read_input_token_cost_above_272k_tokens_batches": {
216+
"cache_read_input_token_cost_above_272k_tokens_decisions": {
233217
"type": "number",
234218
"minimum": 0,
235219
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -249,11 +233,6 @@
249233
"minimum": 0,
250234
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
251235
},
252-
"cache_read_input_token_cost_above_32k_tokens": {
253-
"type": "number",
254-
"minimum": 0,
255-
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
256-
},
257236
"cache_read_input_token_cost_above_512k_tokens": {
258237
"type": "number",
259238
"minimum": 0,
@@ -267,6 +246,10 @@
267246
"type": "number",
268247
"minimum": 0
269248
},
249+
"cache_read_input_token_cost_decisions": {
250+
"type": "number",
251+
"minimum": 0
252+
},
270253
"cache_read_input_token_cost_flex": {
271254
"type": "number",
272255
"minimum": 0,
@@ -314,6 +297,10 @@
314297
"format": "date",
315298
"pattern": "^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$"
316299
},
300+
"explicit_cache_read_input_token_cost": {
301+
"type": "number",
302+
"minimum": 0
303+
},
317304
"gemini_audio_only_live": {
318305
"type": "boolean"
319306
},
@@ -397,6 +384,10 @@
397384
"type": "number",
398385
"minimum": 0
399386
},
387+
"input_cost_per_text_message": {
388+
"type": "number",
389+
"minimum": 0
390+
},
400391
"input_cost_per_token": {
401392
"type": "number",
402393
"minimum": 0,
@@ -432,17 +423,17 @@
432423
"minimum": 0,
433424
"description": "Priority service-tier rate for the same-named base field."
434425
},
435-
"input_cost_per_token_above_256k_tokens": {
426+
"input_cost_per_token_above_272k_tokens": {
436427
"type": "number",
437428
"minimum": 0,
438429
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
439430
},
440-
"input_cost_per_token_above_272k_tokens": {
431+
"input_cost_per_token_above_272k_tokens_batches": {
441432
"type": "number",
442433
"minimum": 0,
443434
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
444435
},
445-
"input_cost_per_token_above_272k_tokens_batches": {
436+
"input_cost_per_token_above_272k_tokens_decisions": {
446437
"type": "number",
447438
"minimum": 0,
448439
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -462,11 +453,6 @@
462453
"minimum": 0,
463454
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
464455
},
465-
"input_cost_per_token_above_32k_tokens": {
466-
"type": "number",
467-
"minimum": 0,
468-
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
469-
},
470456
"input_cost_per_token_above_512k_tokens": {
471457
"type": "number",
472458
"minimum": 0,
@@ -485,6 +471,10 @@
485471
"type": "number",
486472
"minimum": 0
487473
},
474+
"input_cost_per_token_decisions": {
475+
"type": "number",
476+
"minimum": 0
477+
},
488478
"input_cost_per_token_flex": {
489479
"type": "number",
490480
"minimum": 0,
@@ -563,6 +553,7 @@
563553
"completion",
564554
"embedding",
565555
"evaluation",
556+
"extraction",
566557
"guardrail",
567558
"image_edit",
568559
"image_generation",
@@ -821,17 +812,17 @@
821812
"minimum": 0,
822813
"description": "Priority service-tier rate for the same-named base field."
823814
},
824-
"output_cost_per_token_above_256k_tokens": {
815+
"output_cost_per_token_above_272k_tokens": {
825816
"type": "number",
826817
"minimum": 0,
827818
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
828819
},
829-
"output_cost_per_token_above_272k_tokens": {
820+
"output_cost_per_token_above_272k_tokens_batches": {
830821
"type": "number",
831822
"minimum": 0,
832823
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
833824
},
834-
"output_cost_per_token_above_272k_tokens_batches": {
825+
"output_cost_per_token_above_272k_tokens_decisions": {
835826
"type": "number",
836827
"minimum": 0,
837828
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
@@ -851,11 +842,6 @@
851842
"minimum": 0,
852843
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
853844
},
854-
"output_cost_per_token_above_32k_tokens": {
855-
"type": "number",
856-
"minimum": 0,
857-
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
858-
},
859845
"output_cost_per_token_above_512k_tokens": {
860846
"type": "number",
861847
"minimum": 0,
@@ -870,6 +856,10 @@
870856
"minimum": 0,
871857
"description": "USD per generated token via the provider's batch API."
872858
},
859+
"output_cost_per_token_decisions": {
860+
"type": "number",
861+
"minimum": 0
862+
},
873863
"output_cost_per_token_flex": {
874864
"type": "number",
875865
"minimum": 0,
@@ -965,6 +955,33 @@
965955
},
966956
"additionalProperties": false
967957
},
958+
"search_free_requests": {
959+
"type": "object",
960+
"description": "Free Google Search grounding requests per period, shared across models in the same shared_group.",
961+
"required": [
962+
"count",
963+
"period",
964+
"shared_group"
965+
],
966+
"additionalProperties": false,
967+
"properties": {
968+
"count": {
969+
"type": "integer",
970+
"minimum": 0
971+
},
972+
"period": {
973+
"type": "string",
974+
"enum": [
975+
"day",
976+
"month"
977+
]
978+
},
979+
"shared_group": {
980+
"type": "string",
981+
"pattern": "\\S"
982+
}
983+
}
984+
},
968985
"source": {
969986
"type": "string",
970987
"description": "URL of the provider pricing/model page this entry was taken from."
@@ -1039,6 +1056,12 @@
10391056
"supports_audio_output": {
10401057
"type": "boolean"
10411058
},
1059+
"supports_bedrock_converse_tool_result_images": {
1060+
"type": "boolean"
1061+
},
1062+
"supports_bedrock_native_structured_output": {
1063+
"type": "boolean"
1064+
},
10421065
"supports_bedrock_runtime_chat_completions_inline_reasoning": {
10431066
"type": "boolean"
10441067
},
@@ -1224,6 +1247,31 @@
12241247
"minimum": 0,
12251248
"description": "Tokens added once per request to a local count estimate, for the provider's chat framing."
12261249
},
1250+
"token_count_model": {
1251+
"type": "object",
1252+
"required": [
1253+
"model"
1254+
],
1255+
"additionalProperties": false,
1256+
"properties": {
1257+
"model": {
1258+
"type": "string",
1259+
"pattern": "\\S"
1260+
},
1261+
"region": {
1262+
"type": "string",
1263+
"pattern": "\\S"
1264+
},
1265+
"litellm_provider": {
1266+
"type": "string",
1267+
"enum": [
1268+
"bedrock",
1269+
"bedrock_mantle"
1270+
]
1271+
}
1272+
},
1273+
"description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in."
1274+
},
12271275
"token_count_tokenizer": {
12281276
"type": "string",
12291277
"description": "Tokenizer litellm counts this model's requests with when the provider cannot count them.",

0 commit comments

Comments
 (0)