|
93 | 93 | "minimum": 0, |
94 | 94 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
95 | 95 | }, |
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 | | - }, |
101 | 96 | "cache_creation_input_token_cost_above_1hr": { |
102 | 97 | "type": "number", |
103 | 98 | "minimum": 0, |
|
118 | 113 | "minimum": 0, |
119 | 114 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
120 | 115 | }, |
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": { |
127 | 117 | "type": "number", |
128 | 118 | "minimum": 0, |
129 | 119 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
130 | 120 | }, |
131 | | - "cache_creation_input_token_cost_above_272k_tokens": { |
| 121 | + "cache_creation_input_token_cost_above_272k_tokens_batches": { |
132 | 122 | "type": "number", |
133 | 123 | "minimum": 0, |
134 | 124 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
135 | 125 | }, |
136 | | - "cache_creation_input_token_cost_above_272k_tokens_batches": { |
| 126 | + "cache_creation_input_token_cost_above_272k_tokens_decisions": { |
137 | 127 | "type": "number", |
138 | 128 | "minimum": 0, |
139 | 129 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
|
153 | 143 | "minimum": 0, |
154 | 144 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
155 | 145 | }, |
156 | | - "cache_creation_input_token_cost_above_32k_tokens": { |
| 146 | + "cache_creation_input_token_cost_batches": { |
157 | 147 | "type": "number", |
158 | | - "minimum": 0, |
159 | | - "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
| 148 | + "minimum": 0 |
160 | 149 | }, |
161 | | - "cache_creation_input_token_cost_batches": { |
| 150 | + "cache_creation_input_token_cost_decisions": { |
162 | 151 | "type": "number", |
163 | 152 | "minimum": 0 |
164 | 153 | }, |
|
199 | 188 | "minimum": 0, |
200 | 189 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
201 | 190 | }, |
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 | | - }, |
207 | 191 | "cache_read_input_token_cost_above_200k_tokens": { |
208 | 192 | "type": "number", |
209 | 193 | "minimum": 0, |
|
219 | 203 | "minimum": 0, |
220 | 204 | "description": "Priority service-tier rate for the same-named base field." |
221 | 205 | }, |
222 | | - "cache_read_input_token_cost_above_256k_tokens": { |
| 206 | + "cache_read_input_token_cost_above_272k_tokens": { |
223 | 207 | "type": "number", |
224 | 208 | "minimum": 0, |
225 | 209 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
226 | 210 | }, |
227 | | - "cache_read_input_token_cost_above_272k_tokens": { |
| 211 | + "cache_read_input_token_cost_above_272k_tokens_batches": { |
228 | 212 | "type": "number", |
229 | 213 | "minimum": 0, |
230 | 214 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
231 | 215 | }, |
232 | | - "cache_read_input_token_cost_above_272k_tokens_batches": { |
| 216 | + "cache_read_input_token_cost_above_272k_tokens_decisions": { |
233 | 217 | "type": "number", |
234 | 218 | "minimum": 0, |
235 | 219 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
|
249 | 233 | "minimum": 0, |
250 | 234 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
251 | 235 | }, |
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 | | - }, |
257 | 236 | "cache_read_input_token_cost_above_512k_tokens": { |
258 | 237 | "type": "number", |
259 | 238 | "minimum": 0, |
|
267 | 246 | "type": "number", |
268 | 247 | "minimum": 0 |
269 | 248 | }, |
| 249 | + "cache_read_input_token_cost_decisions": { |
| 250 | + "type": "number", |
| 251 | + "minimum": 0 |
| 252 | + }, |
270 | 253 | "cache_read_input_token_cost_flex": { |
271 | 254 | "type": "number", |
272 | 255 | "minimum": 0, |
|
314 | 297 | "format": "date", |
315 | 298 | "pattern": "^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$" |
316 | 299 | }, |
| 300 | + "explicit_cache_read_input_token_cost": { |
| 301 | + "type": "number", |
| 302 | + "minimum": 0 |
| 303 | + }, |
317 | 304 | "gemini_audio_only_live": { |
318 | 305 | "type": "boolean" |
319 | 306 | }, |
|
397 | 384 | "type": "number", |
398 | 385 | "minimum": 0 |
399 | 386 | }, |
| 387 | + "input_cost_per_text_message": { |
| 388 | + "type": "number", |
| 389 | + "minimum": 0 |
| 390 | + }, |
400 | 391 | "input_cost_per_token": { |
401 | 392 | "type": "number", |
402 | 393 | "minimum": 0, |
|
432 | 423 | "minimum": 0, |
433 | 424 | "description": "Priority service-tier rate for the same-named base field." |
434 | 425 | }, |
435 | | - "input_cost_per_token_above_256k_tokens": { |
| 426 | + "input_cost_per_token_above_272k_tokens": { |
436 | 427 | "type": "number", |
437 | 428 | "minimum": 0, |
438 | 429 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
439 | 430 | }, |
440 | | - "input_cost_per_token_above_272k_tokens": { |
| 431 | + "input_cost_per_token_above_272k_tokens_batches": { |
441 | 432 | "type": "number", |
442 | 433 | "minimum": 0, |
443 | 434 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
444 | 435 | }, |
445 | | - "input_cost_per_token_above_272k_tokens_batches": { |
| 436 | + "input_cost_per_token_above_272k_tokens_decisions": { |
446 | 437 | "type": "number", |
447 | 438 | "minimum": 0, |
448 | 439 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
|
462 | 453 | "minimum": 0, |
463 | 454 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
464 | 455 | }, |
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 | | - }, |
470 | 456 | "input_cost_per_token_above_512k_tokens": { |
471 | 457 | "type": "number", |
472 | 458 | "minimum": 0, |
|
485 | 471 | "type": "number", |
486 | 472 | "minimum": 0 |
487 | 473 | }, |
| 474 | + "input_cost_per_token_decisions": { |
| 475 | + "type": "number", |
| 476 | + "minimum": 0 |
| 477 | + }, |
488 | 478 | "input_cost_per_token_flex": { |
489 | 479 | "type": "number", |
490 | 480 | "minimum": 0, |
|
563 | 553 | "completion", |
564 | 554 | "embedding", |
565 | 555 | "evaluation", |
| 556 | + "extraction", |
566 | 557 | "guardrail", |
567 | 558 | "image_edit", |
568 | 559 | "image_generation", |
|
821 | 812 | "minimum": 0, |
822 | 813 | "description": "Priority service-tier rate for the same-named base field." |
823 | 814 | }, |
824 | | - "output_cost_per_token_above_256k_tokens": { |
| 815 | + "output_cost_per_token_above_272k_tokens": { |
825 | 816 | "type": "number", |
826 | 817 | "minimum": 0, |
827 | 818 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
828 | 819 | }, |
829 | | - "output_cost_per_token_above_272k_tokens": { |
| 820 | + "output_cost_per_token_above_272k_tokens_batches": { |
830 | 821 | "type": "number", |
831 | 822 | "minimum": 0, |
832 | 823 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
833 | 824 | }, |
834 | | - "output_cost_per_token_above_272k_tokens_batches": { |
| 825 | + "output_cost_per_token_above_272k_tokens_decisions": { |
835 | 826 | "type": "number", |
836 | 827 | "minimum": 0, |
837 | 828 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
|
851 | 842 | "minimum": 0, |
852 | 843 | "description": "Rate applied once the prompt exceeds the token threshold in the field name." |
853 | 844 | }, |
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 | | - }, |
859 | 845 | "output_cost_per_token_above_512k_tokens": { |
860 | 846 | "type": "number", |
861 | 847 | "minimum": 0, |
|
870 | 856 | "minimum": 0, |
871 | 857 | "description": "USD per generated token via the provider's batch API." |
872 | 858 | }, |
| 859 | + "output_cost_per_token_decisions": { |
| 860 | + "type": "number", |
| 861 | + "minimum": 0 |
| 862 | + }, |
873 | 863 | "output_cost_per_token_flex": { |
874 | 864 | "type": "number", |
875 | 865 | "minimum": 0, |
|
965 | 955 | }, |
966 | 956 | "additionalProperties": false |
967 | 957 | }, |
| 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 | + }, |
968 | 985 | "source": { |
969 | 986 | "type": "string", |
970 | 987 | "description": "URL of the provider pricing/model page this entry was taken from." |
|
1039 | 1056 | "supports_audio_output": { |
1040 | 1057 | "type": "boolean" |
1041 | 1058 | }, |
| 1059 | + "supports_bedrock_converse_tool_result_images": { |
| 1060 | + "type": "boolean" |
| 1061 | + }, |
| 1062 | + "supports_bedrock_native_structured_output": { |
| 1063 | + "type": "boolean" |
| 1064 | + }, |
1042 | 1065 | "supports_bedrock_runtime_chat_completions_inline_reasoning": { |
1043 | 1066 | "type": "boolean" |
1044 | 1067 | }, |
|
1224 | 1247 | "minimum": 0, |
1225 | 1248 | "description": "Tokens added once per request to a local count estimate, for the provider's chat framing." |
1226 | 1249 | }, |
| 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 | + }, |
1227 | 1275 | "token_count_tokenizer": { |
1228 | 1276 | "type": "string", |
1229 | 1277 | "description": "Tokenizer litellm counts this model's requests with when the provider cannot count them.", |
|
0 commit comments