From bd5c0a7cdd2f074cfe52afe55f6369708545db93 Mon Sep 17 00:00:00 2001 From: Alex Clarke Date: Mon, 14 Sep 2026 14:47:22 -0600 Subject: [PATCH] chore: updated the models.yaml to incorporate cached read/write prices pulled from models.dev and openrouter --- models.yaml | 941 +++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 927 insertions(+), 14 deletions(-) diff --git a/models.yaml b/models.yaml index 3d7ce32..d0846c0 100644 --- a/models.yaml +++ b/models.yaml @@ -8,6 +8,8 @@ max_input_tokens: 1050000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -22,6 +24,8 @@ max_input_tokens: 1050000 input_price: 4.0 output_price: 20.0 + cache_read_price: 0.4 + cache_write_price: 5.0 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -37,6 +41,8 @@ max_input_tokens: 1050000 input_price: 0.2 output_price: 1.2 + cache_read_price: 0.02 + cache_write_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -53,6 +59,8 @@ max_input_tokens: 1050000 input_price: 4.0 output_price: 20.0 + cache_read_price: 0.4 + cache_write_price: 5.0 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -69,6 +77,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -85,6 +95,7 @@ max_input_tokens: 1050000 input_price: 5.0 output_price: 30.0 + cache_read_price: 0.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -113,6 +124,7 @@ max_input_tokens: 400000 input_price: 0.75 output_price: 4.5 + cache_read_price: 0.075 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -128,6 +140,7 @@ max_input_tokens: 400000 input_price: 0.2 output_price: 1.25 + cache_read_price: 0.02 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -143,6 +156,7 @@ max_input_tokens: 1050000 input_price: 2.5 output_price: 15.0 + cache_read_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -171,6 +185,7 @@ max_input_tokens: 128000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -179,6 +194,7 @@ max_input_tokens: 400000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -194,6 +210,7 @@ max_input_tokens: 128000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 32000 supports_vision: true supports_function_calling: true @@ -208,6 +225,7 @@ max_input_tokens: 400000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -223,6 +241,7 @@ max_input_tokens: 128000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -246,6 +265,7 @@ max_input_tokens: 400000 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -270,6 +290,7 @@ max_input_tokens: 400000 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -284,6 +305,7 @@ max_input_tokens: 400000 input_price: 0.25 output_price: 2.0 + cache_read_price: 0.025 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -297,6 +319,7 @@ max_input_tokens: 400000 input_price: 0.05 output_price: 0.4 + cache_read_price: 0.005 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -322,6 +345,7 @@ max_input_tokens: 200000 input_price: 2.0 output_price: 8.0 + cache_read_price: 0.5 patch: body: max_tokens: null @@ -340,6 +364,7 @@ max_input_tokens: 200000 input_price: 1.1 output_price: 4.4 + cache_read_price: 0.275 patch: body: max_tokens: null @@ -359,6 +384,7 @@ max_input_tokens: 1047576 input_price: 2.0 output_price: 8.0 + cache_read_price: 0.5 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -367,6 +393,7 @@ max_input_tokens: 1047576 input_price: 0.4 output_price: 1.6 + cache_read_price: 0.1 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -375,6 +402,7 @@ max_input_tokens: 1047576 input_price: 0.1 output_price: 0.4 + cache_read_price: 0.025 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -395,6 +423,7 @@ max_input_tokens: 200000 input_price: 1.1 output_price: 4.4 + cache_read_price: 0.55 patch: body: max_tokens: null @@ -412,6 +441,7 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 60.0 + cache_read_price: 7.5 max_output_tokens: 100000 supports_vision: true supports_function_calling: true @@ -424,6 +454,7 @@ max_input_tokens: 128000 input_price: 2.5 output_price: 10.0 + cache_read_price: 1.25 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -432,6 +463,7 @@ max_input_tokens: 128000 input_price: 2.5 output_price: 10.0 + cache_read_price: 1.25 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -440,6 +472,7 @@ max_input_tokens: 128000 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.075 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -448,6 +481,7 @@ max_input_tokens: 128000 input_price: 2.5 output_price: 10.0 + cache_read_price: 1.25 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -479,6 +513,7 @@ max_input_tokens: 16385 input_price: 0.5 output_price: 1.5 + cache_read_price: 0.0 max_output_tokens: 4096 supports_function_calling: true - name: text-embedding-3-large @@ -583,6 +618,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -595,6 +632,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -607,6 +646,7 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -619,6 +659,8 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -632,6 +674,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -646,6 +690,7 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -683,6 +728,8 @@ max_input_tokens: 131072 input_price: 2.0 output_price: 120.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -704,6 +751,8 @@ max_input_tokens: 1048576 input_price: 1.5 output_price: 9.0 + cache_read_price: 0.15 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -718,6 +767,8 @@ max_input_tokens: 1048576 input_price: 0.25 output_price: 1.5 + cache_read_price: 0.025 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -732,6 +783,7 @@ max_input_tokens: 131072 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -740,6 +792,7 @@ max_input_tokens: 131072 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -748,6 +801,7 @@ max_input_tokens: 262144 input_price: 0.09 output_price: 0.3 + cache_read_price: 0.05 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -756,6 +810,7 @@ max_input_tokens: 262144 input_price: 0.09 output_price: 0.34 + cache_read_price: 0.05 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -791,6 +846,8 @@ max_input_tokens: 1048576 input_price: 0.25 output_price: 1.5 + cache_read_price: 0.025 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -804,6 +861,8 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -817,6 +876,8 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -829,6 +890,8 @@ max_input_tokens: 1048576 input_price: 0.5 output_price: 3.0 + cache_read_price: 0.05 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -851,6 +914,8 @@ max_input_tokens: 32768 input_price: 0.3 output_price: 30.0 + cache_read_price: 0.075 + cache_write_price: 0.0833 max_output_tokens: 32768 supports_vision: true - name: gemini-2.5-flash @@ -858,6 +923,8 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -866,6 +933,8 @@ max_input_tokens: 1048576 input_price: 0.1 output_price: 0.4 + cache_read_price: 0.01 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -874,6 +943,8 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -910,6 +981,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 0.25 + cache_write_price: 12.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -926,6 +999,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -942,6 +1017,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -958,6 +1035,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -974,6 +1053,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -990,6 +1071,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -1006,6 +1089,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -1022,6 +1107,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 patch: body: temperature: null @@ -1039,6 +1126,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -1055,6 +1144,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 patch: body: temperature: null @@ -1072,6 +1163,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -1085,6 +1178,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -1099,6 +1194,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 patch: body: temperature: null @@ -1115,6 +1212,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -1124,6 +1223,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -1134,6 +1235,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 patch: body: temperature: null @@ -1150,6 +1253,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -1159,6 +1264,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -1169,6 +1276,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 patch: body: temperature: null @@ -1239,6 +1348,7 @@ max_input_tokens: 1000000 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.14 max_output_tokens: 131072 supports_function_calling: true reasoning_levels: @@ -1271,6 +1381,7 @@ max_input_tokens: 256000 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.015 max_output_tokens: 256000 supports_vision: true supports_function_calling: true @@ -1293,6 +1404,7 @@ max_input_tokens: 262144 input_price: 0.4 output_price: 2.0 + cache_read_price: 0.04 max_output_tokens: 262144 supports_function_calling: true - name: devstral-latest @@ -1388,6 +1500,7 @@ max_input_tokens: 262144 input_price: 0.5 output_price: 1.5 + cache_read_price: 0.05 max_output_tokens: 262144 supports_vision: true supports_function_calling: true @@ -1663,6 +1776,7 @@ max_input_tokens: 500000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.5 max_output_tokens: 500000 supports_vision: true supports_function_calling: true @@ -1676,6 +1790,7 @@ max_input_tokens: 500000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.3 max_output_tokens: 500000 supports_vision: true supports_function_calling: true @@ -1688,6 +1803,7 @@ max_input_tokens: 1000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -1701,6 +1817,7 @@ max_input_tokens: 256000 input_price: 1.0 output_price: 2.0 + cache_read_price: 0.2 max_output_tokens: 256000 supports_vision: true supports_function_calling: true @@ -1709,6 +1826,7 @@ max_input_tokens: 1000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -1717,6 +1835,7 @@ max_input_tokens: 1000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -1725,6 +1844,7 @@ max_input_tokens: 1000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 30000 supports_vision: true reasoning_levels: @@ -1848,6 +1968,7 @@ max_input_tokens: 131072 input_price: 0.6 output_price: 3.0 + cache_read_price: 0.3 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -1886,6 +2007,7 @@ max_input_tokens: 131072 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.075 max_output_tokens: 65536 supports_function_calling: true reasoning_levels: @@ -1897,6 +2019,7 @@ max_input_tokens: 131072 input_price: 0.075 output_price: 0.3 + cache_read_price: 0.0375 max_output_tokens: 65536 supports_function_calling: true reasoning_levels: @@ -1967,6 +2090,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -1979,6 +2104,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 0.25 + cache_write_price: 12.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -1995,6 +2122,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2007,6 +2136,7 @@ max_input_tokens: 1048576 input_price: 1.5 output_price: 9.0 + cache_read_price: 0.15 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2020,6 +2150,7 @@ max_input_tokens: 524288 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.5 max_output_tokens: 500000 supports_vision: true supports_function_calling: true @@ -2028,6 +2159,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2043,6 +2176,8 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2056,6 +2191,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2069,6 +2206,7 @@ max_input_tokens: 1048576 input_price: 0.25 output_price: 1.5 + cache_read_price: 0.025 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2082,6 +2220,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2097,6 +2237,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2113,6 +2255,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2128,6 +2272,8 @@ max_input_tokens: 65536 input_price: 2.0 output_price: 120.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -2136,6 +2282,7 @@ max_input_tokens: 131072 input_price: 0.5 output_price: 60.0 + cache_read_price: 0.05 max_output_tokens: 32768 supports_vision: true reasoning_levels: @@ -2146,6 +2293,8 @@ max_input_tokens: 1048576 input_price: 1.5 output_price: 9.0 + cache_read_price: 0.15 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2160,6 +2309,8 @@ max_input_tokens: 1048576 input_price: 0.25 output_price: 1.5 + cache_read_price: 0.025 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2174,6 +2325,7 @@ max_input_tokens: 200000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -2182,6 +2334,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2197,6 +2351,7 @@ max_input_tokens: 2000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -2205,6 +2360,7 @@ max_input_tokens: 2000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -2213,6 +2369,8 @@ max_input_tokens: 1048576 input_price: 0.25 output_price: 1.5 + cache_read_price: 0.025 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2226,6 +2384,8 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2239,6 +2399,8 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2251,6 +2413,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2265,6 +2429,7 @@ max_input_tokens: 202752 input_price: 1.0 output_price: 3.2 + cache_read_price: 0.1 max_output_tokens: 131072 supports_function_calling: true - name: claude-opus-4-6@default @@ -2272,6 +2437,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2286,6 +2453,7 @@ max_input_tokens: 200000 input_price: 0.6 output_price: 2.2 + cache_read_price: 0.06 max_output_tokens: 128000 supports_function_calling: true - name: deepseek-ai/deepseek-v3.2-maas @@ -2293,6 +2461,7 @@ max_input_tokens: 163840 input_price: 0.56 output_price: 1.68 + cache_read_price: 0.056 max_output_tokens: 65536 supports_function_calling: true - name: gemini-3-flash-preview @@ -2300,6 +2469,8 @@ max_input_tokens: 1048576 input_price: 0.5 output_price: 3.0 + cache_read_price: 0.05 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2314,6 +2485,7 @@ max_input_tokens: 128000 input_price: 0.2 output_price: 0.5 + cache_read_price: 0.05 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -2322,6 +2494,7 @@ max_input_tokens: 128000 input_price: 0.2 output_price: 0.5 + cache_read_price: 0.05 max_output_tokens: 30000 supports_vision: true supports_function_calling: true @@ -2330,6 +2503,7 @@ max_input_tokens: 262144 input_price: 0.6 output_price: 2.5 + cache_read_price: 0.06 max_output_tokens: 262144 supports_function_calling: true - name: claude-opus-4-5@20251101 @@ -2337,6 +2511,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -2351,6 +2527,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 patch: body: temperature: null @@ -2366,6 +2544,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -2376,6 +2556,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 patch: body: temperature: null @@ -2391,6 +2573,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -2401,6 +2585,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 patch: body: temperature: null @@ -2416,6 +2602,7 @@ max_input_tokens: 163840 input_price: 0.6 output_price: 1.7 + cache_read_price: 0.06 max_output_tokens: 32768 supports_function_calling: true - name: gemini-2.5-flash-image @@ -2423,6 +2610,8 @@ max_input_tokens: 32768 input_price: 0.3 output_price: 30.0 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 32768 supports_vision: true - name: qwen/qwen3-235b-a22b-instruct-2507-maas @@ -2437,6 +2626,8 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 75.0 + cache_read_price: 1.5 + cache_write_price: 18.75 max_output_tokens: 32000 require_max_tokens: true supports_vision: true @@ -2457,6 +2648,7 @@ max_input_tokens: 131072 input_price: 0.07 output_price: 0.25 + cache_read_price: 0.007 max_output_tokens: 32768 supports_function_calling: true reasoning_levels: @@ -2468,6 +2660,8 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2481,6 +2675,8 @@ max_input_tokens: 1048576 input_price: 0.1 output_price: 0.4 + cache_read_price: 0.01 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2489,6 +2685,8 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -2502,6 +2700,8 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 75.0 + cache_read_price: 1.5 + cache_write_price: 18.75 max_output_tokens: 32000 require_max_tokens: true supports_vision: true @@ -2511,6 +2711,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -2734,6 +2936,8 @@ max_input_tokens: 1050000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2748,6 +2952,8 @@ max_input_tokens: 1050000 input_price: 11.0 output_price: 55.0 + cache_read_price: 1.1 + cache_write_price: 13.75 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2762,6 +2968,8 @@ max_input_tokens: 1050000 input_price: 11.0 output_price: 55.0 + cache_read_price: 1.1 + cache_write_price: 13.75 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2776,6 +2984,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 0.25 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2790,6 +3000,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 0.25 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2804,6 +3016,8 @@ max_input_tokens: 1000000 input_price: 11.0 output_price: 55.0 + cache_read_price: 0.275 + cache_write_price: 13.75 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2820,6 +3034,7 @@ max_input_tokens: 500000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.5 max_output_tokens: 500000 supports_vision: true supports_function_calling: true @@ -2833,6 +3048,7 @@ max_input_tokens: 500000 input_price: 2.2 output_price: 6.6 + cache_read_price: 0.55 max_output_tokens: 500000 supports_vision: true supports_function_calling: true @@ -2846,6 +3062,7 @@ max_input_tokens: 500000 input_price: 2.2 output_price: 6.6 + cache_read_price: 0.55 max_output_tokens: 500000 supports_vision: true supports_function_calling: true @@ -2859,6 +3076,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2873,6 +3092,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2887,6 +3108,8 @@ max_input_tokens: 1000000 input_price: 5.5 output_price: 27.5 + cache_read_price: 0.55 + cache_write_price: 6.875 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2901,6 +3124,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2915,6 +3140,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2929,6 +3156,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -2945,6 +3174,8 @@ max_input_tokens: 1050000 input_price: 0.2 output_price: 1.2 + cache_read_price: 0.02 + cache_write_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2960,6 +3191,8 @@ max_input_tokens: 1050000 input_price: 4.0 output_price: 20.0 + cache_read_price: 0.4 + cache_write_price: 5.0 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2975,6 +3208,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -2990,6 +3225,8 @@ max_input_tokens: 1050000 input_price: 0.22 output_price: 1.32 + cache_read_price: 0.022 + cache_write_price: 0.275 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3005,6 +3242,8 @@ max_input_tokens: 1050000 input_price: 2.2 output_price: 13.2 + cache_read_price: 0.22 + cache_write_price: 2.75 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3020,6 +3259,8 @@ max_input_tokens: 1050000 input_price: 0.22 output_price: 1.32 + cache_read_price: 0.022 + cache_write_price: 0.275 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3035,6 +3276,8 @@ max_input_tokens: 1050000 input_price: 4.4 output_price: 22.0 + cache_read_price: 0.44 + cache_write_price: 5.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3050,6 +3293,8 @@ max_input_tokens: 1050000 input_price: 2.2 output_price: 13.2 + cache_read_price: 0.22 + cache_write_price: 2.75 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3065,6 +3310,8 @@ max_input_tokens: 1050000 input_price: 0.22 output_price: 1.32 + cache_read_price: 0.022 + cache_write_price: 0.275 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3080,6 +3327,8 @@ max_input_tokens: 1050000 input_price: 4.4 output_price: 22.0 + cache_read_price: 0.44 + cache_write_price: 5.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3095,6 +3344,8 @@ max_input_tokens: 1050000 input_price: 2.2 output_price: 13.2 + cache_read_price: 0.22 + cache_write_price: 2.75 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3110,6 +3361,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3124,6 +3377,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3138,6 +3393,8 @@ max_input_tokens: 1000000 input_price: 2.2 output_price: 11.0 + cache_read_price: 0.22 + cache_write_price: 2.75 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3152,6 +3409,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3166,6 +3425,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3180,6 +3441,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -3196,6 +3459,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3210,6 +3475,8 @@ max_input_tokens: 1000000 input_price: 11.0 output_price: 55.0 + cache_read_price: 1.1 + cache_write_price: 13.75 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3224,6 +3491,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3238,6 +3507,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -3254,6 +3525,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3268,6 +3541,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3282,6 +3557,8 @@ max_input_tokens: 1000000 input_price: 5.5 output_price: 27.5 + cache_read_price: 0.55 + cache_write_price: 6.875 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3296,6 +3573,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3310,6 +3589,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3324,6 +3605,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -3340,6 +3623,7 @@ max_input_tokens: 272000 input_price: 5.5 output_price: 33.0 + cache_read_price: 0.55 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3354,6 +3638,7 @@ max_input_tokens: 1000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -3367,6 +3652,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3381,6 +3668,8 @@ max_input_tokens: 1000000 input_price: 5.5 output_price: 27.5 + cache_read_price: 0.55 + cache_write_price: 6.875 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3395,6 +3684,8 @@ max_input_tokens: 1000000 input_price: 5.5 output_price: 27.5 + cache_read_price: 0.55 + cache_write_price: 6.875 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3409,6 +3700,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3423,6 +3716,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3437,6 +3732,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -3493,6 +3790,7 @@ max_input_tokens: 272000 input_price: 2.75 output_price: 16.5 + cache_read_price: 0.275 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3507,6 +3805,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3520,6 +3820,8 @@ max_input_tokens: 1000000 input_price: 3.3 output_price: 16.5 + cache_read_price: 0.33 + cache_write_price: 4.125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3533,6 +3835,8 @@ max_input_tokens: 1000000 input_price: 3.3 output_price: 16.5 + cache_read_price: 0.33 + cache_write_price: 4.125 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3546,6 +3850,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3559,6 +3865,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3572,6 +3880,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -3588,6 +3898,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 patch: body: inferenceConfig: @@ -3620,6 +3932,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3633,6 +3947,8 @@ max_input_tokens: 1000000 input_price: 16.5 output_price: 82.5 + cache_read_price: 1.65 + cache_write_price: 20.625 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3646,6 +3962,8 @@ max_input_tokens: 1000000 input_price: 5.5 output_price: 27.5 + cache_read_price: 0.55 + cache_write_price: 6.875 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3659,6 +3977,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -3672,6 +3992,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -3688,6 +4010,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 patch: body: inferenceConfig: @@ -3756,6 +4080,8 @@ max_input_tokens: 1000000 input_price: 0.33 output_price: 2.75 + cache_read_price: 0.0825 + cache_write_price: 0.33 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -3768,6 +4094,8 @@ max_input_tokens: 1000000 input_price: 0.374 output_price: 3.157 + cache_read_price: 0.0935 + cache_write_price: 0.374 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -3780,6 +4108,8 @@ max_input_tokens: 1000000 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.075 + cache_write_price: 0.3 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -3792,6 +4122,8 @@ max_input_tokens: 1000000 input_price: 0.396 output_price: 3.311 + cache_read_price: 0.099 + cache_write_price: 0.396 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -3836,6 +4168,8 @@ max_input_tokens: 1000000 input_price: 0.33 output_price: 2.75 + cache_read_price: 0.0825 + cache_write_price: 0.33 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -3855,6 +4189,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3867,6 +4203,8 @@ max_input_tokens: 200000 input_price: 5.5 output_price: 27.5 + cache_read_price: 0.55 + cache_write_price: 6.875 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3879,6 +4217,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3891,6 +4231,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -3905,6 +4247,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 patch: body: inferenceConfig: @@ -3966,6 +4310,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3974,6 +4320,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3982,6 +4330,8 @@ max_input_tokens: 200000 input_price: 1.1 output_price: 5.5 + cache_read_price: 0.11 + cache_write_price: 1.375 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3990,6 +4340,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -3998,6 +4350,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -4006,6 +4360,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -4016,6 +4372,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 patch: body: inferenceConfig: @@ -4033,6 +4391,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -4041,6 +4401,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -4049,6 +4411,8 @@ max_input_tokens: 200000 input_price: 3.3 output_price: 16.5 + cache_read_price: 0.33 + cache_write_price: 4.125 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -4057,6 +4421,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -4065,6 +4431,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -4073,6 +4441,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -4083,6 +4453,8 @@ max_input_tokens: 200000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 patch: body: inferenceConfig: @@ -4137,6 +4509,8 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 75.0 + cache_read_price: 1.5 + cache_write_price: 18.75 max_output_tokens: 32000 supports_vision: true supports_function_calling: true @@ -4211,6 +4585,8 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 75.0 + cache_read_price: 1.5 + cache_write_price: 18.75 max_output_tokens: 32000 require_max_tokens: true supports_vision: true @@ -4255,6 +4631,8 @@ max_input_tokens: 300000 input_price: 2.5 output_price: 12.5 + cache_read_price: 0.625 + cache_write_price: 2.5 max_output_tokens: 5120 supports_vision: true supports_function_calling: true @@ -4390,6 +4768,8 @@ max_input_tokens: 300000 input_price: 0.06 output_price: 0.24 + cache_read_price: 0.015 + cache_write_price: 0.06 max_output_tokens: 10000 supports_vision: true supports_function_calling: true @@ -4398,6 +4778,8 @@ max_input_tokens: 128000 input_price: 0.035 output_price: 0.14 + cache_read_price: 0.00875 + cache_write_price: 0.035 max_output_tokens: 10000 supports_function_calling: true - name: amazon.nova-pro-v1:0 @@ -4405,6 +4787,8 @@ max_input_tokens: 300000 input_price: 0.8 output_price: 3.2 + cache_read_price: 0.2 + cache_write_price: 0.8 max_output_tokens: 10000 supports_vision: true supports_function_calling: true @@ -4413,6 +4797,8 @@ max_input_tokens: 300000 input_price: 0.063 output_price: 0.252 + cache_read_price: 0.01575 + cache_write_price: 0.063 max_output_tokens: 10000 supports_vision: true supports_function_calling: true @@ -4421,6 +4807,8 @@ max_input_tokens: 128000 input_price: 0.037 output_price: 0.148 + cache_read_price: 0.00925 + cache_write_price: 0.037 max_output_tokens: 10000 supports_function_calling: true - name: apac.amazon.nova-pro-v1:0 @@ -4428,6 +4816,8 @@ max_input_tokens: 300000 input_price: 0.84 output_price: 3.36 + cache_read_price: 0.21 + cache_write_price: 0.84 max_output_tokens: 10000 supports_vision: true supports_function_calling: true @@ -4436,6 +4826,8 @@ max_input_tokens: 300000 input_price: 0.064 output_price: 0.256 + cache_read_price: 0.016 + cache_write_price: 0.064 max_output_tokens: 10000 supports_vision: true supports_function_calling: true @@ -4444,6 +4836,8 @@ max_input_tokens: 300000 input_price: 0.069 output_price: 0.276 + cache_read_price: 0.01725 + cache_write_price: 0.069 max_output_tokens: 10000 supports_vision: true supports_function_calling: true @@ -4452,6 +4846,8 @@ max_input_tokens: 128000 input_price: 0.04 output_price: 0.16 + cache_read_price: 0.01 + cache_write_price: 0.04 max_output_tokens: 10000 supports_function_calling: true - name: eu.amazon.nova-pro-v1:0 @@ -4459,6 +4855,8 @@ max_input_tokens: 300000 input_price: 0.92 output_price: 3.68 + cache_read_price: 0.23 + cache_write_price: 0.92 max_output_tokens: 10000 supports_vision: true supports_function_calling: true @@ -4467,6 +4865,8 @@ max_input_tokens: 300000 input_price: 0.06 output_price: 0.24 + cache_read_price: 0.015 + cache_write_price: 0.06 max_output_tokens: 5120 supports_vision: true supports_function_calling: true @@ -4475,6 +4875,8 @@ max_input_tokens: 128000 input_price: 0.035 output_price: 0.14 + cache_read_price: 0.00875 + cache_write_price: 0.035 max_output_tokens: 5120 supports_function_calling: true - name: us.amazon.nova-pro-v1:0 @@ -4482,6 +4884,8 @@ max_input_tokens: 300000 input_price: 0.8 output_price: 3.2 + cache_read_price: 0.2 + cache_write_price: 0.8 max_output_tokens: 5120 supports_vision: true supports_function_calling: true @@ -4548,6 +4952,7 @@ max_input_tokens: 1310720 input_price: 0.15 output_price: 0.5 + cache_read_price: 0.03 max_output_tokens: 1048576 require_max_tokens: true supports_vision: true @@ -4557,6 +4962,7 @@ max_input_tokens: 262144 input_price: 0.45 output_price: 3.2 + cache_read_price: 0.05 max_output_tokens: 262144 require_max_tokens: true supports_vision: true @@ -4570,6 +4976,7 @@ max_input_tokens: 1310720 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.26 max_output_tokens: 1310720 require_max_tokens: true supports_function_calling: true @@ -4582,6 +4989,7 @@ max_input_tokens: 1048576 input_price: 1.32 output_price: 3.96 + cache_read_price: 0.044 max_output_tokens: 1048576 require_max_tokens: true supports_function_calling: true @@ -4593,6 +5001,7 @@ max_input_tokens: 1310720 input_price: 0.44 output_price: 1.32 + cache_read_price: 0.014 max_output_tokens: 1048576 require_max_tokens: true supports_function_calling: true @@ -4604,6 +5013,7 @@ max_input_tokens: 262144 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.26 max_output_tokens: 256000 require_max_tokens: true supports_function_calling: true @@ -4616,6 +5026,7 @@ max_input_tokens: 262144 input_price: 0.95 output_price: 4.0 + cache_read_price: 0.19 max_output_tokens: 262144 require_max_tokens: true supports_vision: true @@ -4629,6 +5040,7 @@ max_input_tokens: 262144 input_price: 0.95 output_price: 4.0 + cache_read_price: 0.16 max_output_tokens: 256000 require_max_tokens: true supports_vision: true @@ -4858,6 +5270,8 @@ max_input_tokens: 1000000 input_price: 0.15 output_price: 0.47 + cache_read_price: 0.016 + cache_write_price: 0.2 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -4870,6 +5284,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.25 + cache_write_price: 2.5 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -4882,6 +5298,7 @@ max_input_tokens: 1000000 input_price: 0.2 output_price: 0.4 + cache_read_price: 0.04 max_output_tokens: 384000 supports_function_calling: true reasoning_levels: @@ -4892,6 +5309,8 @@ max_input_tokens: 1000000 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.28 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true reasoning_levels: @@ -4907,6 +5326,8 @@ max_input_tokens: 1000000 input_price: 0.5 output_price: 3.0 + cache_read_price: 0.05 + cache_write_price: 0.625 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -4915,6 +5336,8 @@ max_input_tokens: 1000000 input_price: 2.5 output_price: 7.5 + cache_read_price: 0.5 + cache_write_price: 3.125 max_output_tokens: 65536 supports_function_calling: true - name: qwen3.6-flash @@ -4922,6 +5345,7 @@ max_input_tokens: 1000000 input_price: 0.1875 output_price: 1.125 + cache_write_price: 0.234375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -4930,6 +5354,7 @@ max_input_tokens: 262144 input_price: 0.6 output_price: 3.6 + cache_read_price: 0.03 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -4938,6 +5363,8 @@ max_input_tokens: 262144 input_price: 1.3 output_price: 7.8 + cache_read_price: 0.13 + cache_write_price: 1.625 max_output_tokens: 65536 supports_function_calling: true - name: qwen3.6-35b-a3b @@ -4945,6 +5372,7 @@ max_input_tokens: 262144 input_price: 0.248 output_price: 1.485 + cache_read_price: 0.05 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -4953,6 +5381,8 @@ max_input_tokens: 1000000 input_price: 0.5 output_price: 3.0 + cache_read_price: 0.05 + cache_write_price: 0.625 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -4977,6 +5407,7 @@ max_input_tokens: 262144 input_price: 0.25 output_price: 2.0 + cache_read_price: 0.1563 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -4996,6 +5427,7 @@ max_input_tokens: 262144 input_price: 0.6 output_price: 3.6 + cache_read_price: 0.225 patch: body: enable_thinking: false @@ -5007,6 +5439,8 @@ max_input_tokens: 262144 input_price: 1.2 output_price: 6.0 + cache_read_price: 0.156 + cache_write_price: 0.975 max_output_tokens: 65536 supports_function_calling: true - name: qwen3-max:thinking @@ -5015,6 +5449,8 @@ max_input_tokens: 262144 input_price: 1.2 output_price: 6.0 + cache_read_price: 0.156 + cache_write_price: 0.975 patch: body: enable_thinking: true @@ -5068,6 +5504,8 @@ max_input_tokens: 1000000 input_price: 0.3 output_price: 1.5 + cache_read_price: 0.039 + cache_write_price: 0.2438 max_output_tokens: 65536 supports_function_calling: true - name: qwen3-coder-plus @@ -5075,6 +5513,8 @@ max_input_tokens: 1048576 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.13 + cache_write_price: 0.8125 max_output_tokens: 65536 supports_function_calling: true - name: qwen3-14b @@ -5256,6 +5696,8 @@ max_input_tokens: 1000000 input_price: 0.4 output_price: 1.2 + cache_read_price: 0.052 + cache_write_price: 0.325 max_output_tokens: 32768 supports_function_calling: true - name: qwen-vl-plus @@ -5369,6 +5811,7 @@ max_input_tokens: 1048576 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -5381,6 +5824,7 @@ max_input_tokens: 262144 input_price: 0.95 output_price: 4.0 + cache_read_price: 0.19 max_output_tokens: 262144 supports_vision: true supports_function_calling: true @@ -5389,6 +5833,7 @@ max_input_tokens: 262144 input_price: 1.9 output_price: 8.0 + cache_read_price: 0.38 max_output_tokens: 262144 supports_vision: true supports_function_calling: true @@ -5397,6 +5842,7 @@ max_input_tokens: 262144 input_price: 0.95 output_price: 4.0 + cache_read_price: 0.16 max_output_tokens: 262144 supports_vision: true supports_function_calling: true @@ -5407,6 +5853,7 @@ max_input_tokens: 1000000 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.003 max_output_tokens: 384000 supports_vision: true supports_function_calling: true @@ -5419,6 +5866,7 @@ max_input_tokens: 1000000 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.003 max_output_tokens: 384000 supports_vision: true supports_function_calling: true @@ -5431,6 +5879,7 @@ max_input_tokens: 1000000 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.003 max_output_tokens: 384000 supports_vision: true supports_function_calling: true @@ -5443,6 +5892,7 @@ max_input_tokens: 1000000 input_price: 0.435 output_price: 0.87 + cache_read_price: 0.003625 max_output_tokens: 384000 supports_function_calling: true reasoning_levels: @@ -5468,6 +5918,8 @@ max_input_tokens: 1000000 input_price: 0.075 output_price: 0.25 + cache_read_price: 0.015 + cache_write_price: 0.0 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -5480,6 +5932,8 @@ max_input_tokens: 1000000 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.26 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true reasoning_levels: @@ -5491,6 +5945,8 @@ max_input_tokens: 1000000 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.26 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true reasoning_levels: @@ -5501,6 +5957,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 22.0 + cache_read_price: 1.2 + cache_write_price: 0.0 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -5509,6 +5967,8 @@ max_input_tokens: 200000 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.26 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true - name: glm-5 @@ -5516,6 +5976,8 @@ max_input_tokens: 204800 input_price: 1.0 output_price: 3.2 + cache_read_price: 0.2 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true - name: glm-5:instruct @@ -5524,6 +5986,8 @@ max_input_tokens: 204800 input_price: 1.0 output_price: 3.2 + cache_read_price: 0.2 + cache_write_price: 0.0 patch: body: thinking: @@ -5535,6 +5999,8 @@ max_input_tokens: 200000 input_price: 0.0 output_price: 0.0 + cache_read_price: 0.0 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true - name: glm-4.7-flashx @@ -5542,6 +6008,8 @@ max_input_tokens: 200000 input_price: 0.07 output_price: 0.4 + cache_read_price: 0.01 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true - name: glm-4.7 @@ -5549,6 +6017,8 @@ max_input_tokens: 204800 input_price: 0.6 output_price: 2.2 + cache_read_price: 0.11 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true - name: glm-4.7:instruct @@ -5557,6 +6027,8 @@ max_input_tokens: 204800 input_price: 0.6 output_price: 2.2 + cache_read_price: 0.11 + cache_write_price: 0.0 patch: body: thinking: @@ -5576,6 +6048,8 @@ max_input_tokens: 204800 input_price: 0.6 output_price: 2.2 + cache_read_price: 0.11 + cache_write_price: 0.0 max_output_tokens: 131072 supports_function_calling: true - name: glm-4.5v @@ -5591,6 +6065,8 @@ max_input_tokens: 131072 input_price: 0.6 output_price: 2.2 + cache_read_price: 0.11 + cache_write_price: 0.0 max_output_tokens: 98304 supports_function_calling: true - name: glm-4.5-air @@ -5598,6 +6074,8 @@ max_input_tokens: 131072 input_price: 0.2 output_price: 1.1 + cache_read_price: 0.03 + cache_write_price: 0.0 max_output_tokens: 98304 supports_function_calling: true - name: glm-4.5-flash @@ -5605,6 +6083,8 @@ max_input_tokens: 131072 input_price: 0.0 output_price: 0.0 + cache_read_price: 0.0 + cache_write_price: 0.0 max_output_tokens: 98304 supports_function_calling: true - name: embedding-3 @@ -5630,6 +6110,7 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.06 max_output_tokens: 512000 supports_vision: true supports_function_calling: true @@ -5638,6 +6119,8 @@ max_input_tokens: 204800 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.06 + cache_write_price: 0.375 max_output_tokens: 131072 supports_function_calling: true - name: MiniMax-M2.7-highspeed @@ -5645,6 +6128,8 @@ max_input_tokens: 204800 input_price: 0.6 output_price: 2.4 + cache_read_price: 0.06 + cache_write_price: 0.375 max_output_tokens: 131072 supports_function_calling: true - name: MiniMax-M2.5-highspeed @@ -5652,6 +6137,8 @@ max_input_tokens: 204800 input_price: 0.6 output_price: 2.4 + cache_read_price: 0.06 + cache_write_price: 0.375 max_output_tokens: 131072 supports_function_calling: true - name: MiniMax-M2.5 @@ -5659,6 +6146,8 @@ max_input_tokens: 204800 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.03 + cache_write_price: 0.375 max_output_tokens: 131072 supports_function_calling: true - name: MiniMax-M2.1 @@ -5666,6 +6155,8 @@ max_input_tokens: 204800 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.03 + cache_write_price: 0.375 max_output_tokens: 131072 supports_function_calling: true - name: MiniMax-M2 @@ -5813,6 +6304,7 @@ max_input_tokens: 131072 input_price: 0.8 output_price: 1.6 + cache_read_price: 0.2 max_output_tokens: 32768 supports_function_calling: true - name: aion-labs/aion-3.0 @@ -5820,6 +6312,7 @@ max_input_tokens: 131072 input_price: 3.0 output_price: 6.0 + cache_read_price: 0.75 max_output_tokens: 32768 supports_function_calling: true - name: aion-labs/aion-3.0-mini @@ -5827,6 +6320,7 @@ max_input_tokens: 131072 input_price: 0.7 output_price: 1.4 + cache_read_price: 0.18 max_output_tokens: 32768 supports_function_calling: true - name: aion-labs/aion-rp-llama-3.1-8b @@ -5863,6 +6357,7 @@ max_input_tokens: 1000000 input_price: 2.5 output_price: 12.5 + cache_read_price: 0.625 max_output_tokens: 32000 supports_vision: true supports_function_calling: true @@ -5885,6 +6380,8 @@ max_input_tokens: 200000 input_price: 0.25 output_price: 1.25 + cache_read_price: 0.03 + cache_write_price: 0.3 max_output_tokens: 4096 require_max_tokens: true supports_vision: true @@ -5894,6 +6391,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -5910,6 +6409,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 0.25 + cache_write_price: 12.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -5926,6 +6427,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.125 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -5942,6 +6445,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -5958,6 +6463,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -5967,6 +6474,8 @@ max_input_tokens: 200000 input_price: 0.5 output_price: 2.5 + cache_read_price: 0.05 + cache_write_price: 0.625 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -5976,6 +6485,8 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 75.0 + cache_read_price: 1.5 + cache_write_price: 18.75 max_output_tokens: 32000 require_max_tokens: true supports_vision: true @@ -5985,6 +6496,8 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 75.0 + cache_read_price: 1.5 + cache_write_price: 18.75 max_output_tokens: 32000 require_max_tokens: true supports_vision: true @@ -5994,6 +6507,8 @@ max_input_tokens: 200000 input_price: 7.5 output_price: 37.5 + cache_read_price: 0.75 + cache_write_price: 9.375 max_output_tokens: 32000 require_max_tokens: true supports_vision: true @@ -6003,6 +6518,8 @@ max_input_tokens: 200000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -6012,6 +6529,8 @@ max_input_tokens: 200000 input_price: 2.5 output_price: 12.5 + cache_read_price: 0.25 + cache_write_price: 3.125 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -6021,6 +6540,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6036,6 +6557,8 @@ max_input_tokens: 1000000 input_price: 2.5 output_price: 12.5 + cache_read_price: 0.25 + cache_write_price: 3.125 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6045,6 +6568,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6054,6 +6579,8 @@ max_input_tokens: 1000000 input_price: 2.5 output_price: 12.5 + cache_read_price: 0.25 + cache_write_price: 3.125 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6063,6 +6590,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6072,6 +6601,8 @@ max_input_tokens: 1000000 input_price: 2.5 output_price: 12.5 + cache_read_price: 0.25 + cache_write_price: 3.125 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6081,6 +6612,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6097,6 +6630,8 @@ max_input_tokens: 1000000 input_price: 2.5 output_price: 12.5 + cache_read_price: 0.25 + cache_write_price: 3.125 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6106,6 +6641,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -6115,6 +6652,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -6124,6 +6663,8 @@ max_input_tokens: 1000000 input_price: 1.5 output_price: 7.5 + cache_read_price: 0.15 + cache_write_price: 1.875 max_output_tokens: 64000 require_max_tokens: true supports_vision: true @@ -6133,6 +6674,8 @@ max_input_tokens: 1000000 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 + cache_write_price: 3.75 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6148,6 +6691,8 @@ max_input_tokens: 1000000 input_price: 1.5 output_price: 7.5 + cache_read_price: 0.15 + cache_write_price: 1.875 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6157,6 +6702,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6173,6 +6720,8 @@ max_input_tokens: 1000000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 128000 require_max_tokens: true supports_vision: true @@ -6182,6 +6731,7 @@ max_input_tokens: 262144 input_price: 0.25 output_price: 0.8 + cache_read_price: 0.06 max_output_tokens: 80000 supports_function_calling: true - name: baidu/ernie-4.5-vl-424b-a47b @@ -6244,6 +6794,7 @@ max_input_tokens: 128000 input_price: 0.1 output_price: 0.2 + cache_read_price: 0.1 max_output_tokens: 2048 supports_vision: true - name: cognitivecomputations/dolphin-mistral-24b-venice-edition @@ -6304,6 +6855,7 @@ max_input_tokens: 163840 input_price: 0.25 output_price: 0.95 + cache_read_price: 0.13 max_output_tokens: 32768 supports_function_calling: true - name: deepseek/deepseek-r1 @@ -6318,6 +6870,7 @@ max_input_tokens: 163840 input_price: 0.5 output_price: 2.15 + cache_read_price: 0.35 max_output_tokens: 32768 supports_function_calling: true - name: deepseek/deepseek-r1-distill-llama-70b @@ -6331,6 +6884,7 @@ max_input_tokens: 163840 input_price: 0.27 output_price: 1.0 + cache_read_price: 0.135 max_output_tokens: 32768 supports_function_calling: true - name: deepseek/deepseek-v3.2 @@ -6338,6 +6892,7 @@ max_input_tokens: 163840 input_price: 0.269 output_price: 0.4 + cache_read_price: 0.1345 max_output_tokens: 65536 supports_function_calling: true - name: deepseek/deepseek-v3.2-exp @@ -6350,8 +6905,9 @@ - name: deepseek/deepseek-v4-flash type: chat max_input_tokens: 1048576 - input_price: 0.0886 - output_price: 0.1772 + input_price: 0.0794 + output_price: 0.1588 + cache_read_price: 0.0159 max_output_tokens: 384000 supports_function_calling: true - name: deepseek/deepseek-v4-flash-0731 @@ -6359,6 +6915,7 @@ max_input_tokens: 1310720 input_price: 0.06 output_price: 0.12 + cache_read_price: 0.012 max_output_tokens: 943718 supports_function_calling: true - name: deepseek/deepseek-v4-flash-0731:batch @@ -6366,6 +6923,7 @@ max_input_tokens: 1048576 input_price: 0.11 output_price: 0.33 + cache_read_price: 0.0035 max_output_tokens: 943718 supports_function_calling: true - name: deepseek/deepseek-v4-flash-vision-exp @@ -6373,6 +6931,7 @@ max_input_tokens: 1048576 input_price: 0.22 output_price: 0.66 + cache_read_price: 0.007 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -6381,6 +6940,7 @@ max_input_tokens: 1048576 input_price: 0.11 output_price: 0.33 + cache_read_price: 0.0035 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -6389,20 +6949,23 @@ max_input_tokens: 1048576 input_price: 1.6 output_price: 3.2 + cache_read_price: 0.135 max_output_tokens: 393216 supports_function_calling: true - name: deepseek/deepseek-v4-pro-0813 type: chat max_input_tokens: 1048576 - input_price: 0.9834 - output_price: 2.9502 - max_output_tokens: 384000 + input_price: 0.5795 + output_price: 1.7384 + cache_read_price: 0.0184 + max_output_tokens: 393216 supports_function_calling: true - name: deepseek/deepseek-v4-pro-0813:batch type: chat max_input_tokens: 1048576 input_price: 0.66 output_price: 1.98 + cache_read_price: 0.022 max_output_tokens: 943718 supports_function_calling: true - name: deepseek/deepseek-v4.1-flash @@ -6410,6 +6973,7 @@ max_input_tokens: 1048576 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.003 max_output_tokens: 384000 supports_vision: true supports_function_calling: true @@ -6426,6 +6990,8 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -6439,6 +7005,8 @@ max_input_tokens: 32768 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 8192 supports_vision: true - name: google/gemini-2.5-flash-lite @@ -6446,6 +7014,8 @@ max_input_tokens: 1048576 input_price: 0.1 output_price: 0.4 + cache_read_price: 0.01 + cache_write_price: 0.0833 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -6454,6 +7024,7 @@ max_input_tokens: 1048576 input_price: 0.05 output_price: 0.2 + cache_read_price: 0.01 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -6462,6 +7033,7 @@ max_input_tokens: 1048576 input_price: 0.15 output_price: 1.25 + cache_read_price: 0.03 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -6470,6 +7042,8 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6483,6 +7057,8 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6491,6 +7067,8 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 + cache_write_price: 0.375 max_output_tokens: 65535 supports_vision: true supports_function_calling: true @@ -6499,6 +7077,7 @@ max_input_tokens: 1048576 input_price: 0.625 output_price: 5.0 + cache_read_price: 0.125 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6507,6 +7086,8 @@ max_input_tokens: 1048576 input_price: 0.5 output_price: 3.0 + cache_read_price: 0.05 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6529,6 +7110,8 @@ max_input_tokens: 131072 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -6537,6 +7120,8 @@ max_input_tokens: 65536 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 32768 supports_vision: true - name: google/gemini-3.1-flash-image @@ -6558,6 +7143,8 @@ max_input_tokens: 1048576 input_price: 0.25 output_price: 1.5 + cache_read_price: 0.025 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6579,6 +7166,8 @@ max_input_tokens: 1048576 input_price: 0.25 output_price: 1.5 + cache_read_price: 0.025 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6587,6 +7176,7 @@ max_input_tokens: 1048576 input_price: 0.125 output_price: 0.75 + cache_read_price: 0.0125 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6595,6 +7185,8 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6608,6 +7200,8 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6624,6 +7218,8 @@ max_input_tokens: 1048576 input_price: 1.5 output_price: 9.0 + cache_read_price: 0.15 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6638,6 +7234,8 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 2.5 + cache_read_price: 0.03 + cache_write_price: 0.0833 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6646,6 +7244,7 @@ max_input_tokens: 1048576 input_price: 0.15 output_price: 1.25 + cache_read_price: 0.015 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6654,6 +7253,7 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 4.5 + cache_read_price: 0.075 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6662,6 +7262,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6670,6 +7272,8 @@ max_input_tokens: 1048576 input_price: 0.375 output_price: 1.875 + cache_read_price: 0.0375 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6678,6 +7282,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6686,6 +7292,8 @@ max_input_tokens: 1048576 input_price: 0.375 output_price: 1.875 + cache_read_price: 0.0375 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6694,6 +7302,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6702,6 +7312,8 @@ max_input_tokens: 1048576 input_price: 0.375 output_price: 1.875 + cache_read_price: 0.0375 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -6724,6 +7336,7 @@ max_input_tokens: 131072 input_price: 0.08 output_price: 0.45 + cache_read_price: 0.04 max_output_tokens: 117964 supports_vision: true supports_function_calling: true @@ -6739,6 +7352,7 @@ max_input_tokens: 262144 input_price: 0.09 output_price: 0.3 + cache_read_price: 0.05 max_output_tokens: 235929 supports_vision: true supports_function_calling: true @@ -6755,6 +7369,7 @@ max_input_tokens: 262144 input_price: 0.09 output_price: 0.34 + cache_read_price: 0.05 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -6805,6 +7420,7 @@ max_input_tokens: 131072 input_price: 0.06 output_price: 0.25 + cache_read_price: 0.015 max_output_tokens: 117964 supports_function_calling: true - name: inception/mercury-2 @@ -6812,6 +7428,7 @@ max_input_tokens: 128000 input_price: 0.25 output_price: 0.75 + cache_read_price: 0.025 max_output_tokens: 50000 supports_function_calling: true - name: inception/mercury-2.5 @@ -6819,6 +7436,7 @@ max_input_tokens: 260000 input_price: 0.04 output_price: 0.15 + cache_read_price: 0.004 max_output_tokens: 65536 supports_function_calling: true - name: inclusionai/ling-3.0-flash @@ -6826,6 +7444,7 @@ max_input_tokens: 262144 input_price: 0.021 output_price: 0.063 + cache_read_price: 0.0042 max_output_tokens: 32768 supports_function_calling: true - name: inclusionai/ling-3.0-flash-fin @@ -6833,6 +7452,7 @@ max_input_tokens: 262144 input_price: 0.06 output_price: 0.18 + cache_read_price: 0.012 max_output_tokens: 235929 supports_function_calling: true - name: inclusionai/ling-3.0-flash-fin:free @@ -6854,6 +7474,7 @@ max_input_tokens: 131072 input_price: 0.06 output_price: 0.18 + cache_read_price: 0.012 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -6870,18 +7491,21 @@ max_input_tokens: 128000 input_price: 0.05 output_price: 0.23 + cache_read_price: 0.05 max_output_tokens: 4096 - name: inference-net/schematron-v2-turbo type: chat max_input_tokens: 128000 input_price: 0.03 output_price: 0.15 + cache_read_price: 0.03 max_output_tokens: 8192 - name: kwaipilot/kat-coder-pro-v2 type: chat max_input_tokens: 262144 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.06 max_output_tokens: 144000 supports_function_calling: true - name: kwaipilot/kat-coder-pro-v2.5 @@ -6889,6 +7513,7 @@ max_input_tokens: 262144 input_price: 0.74 output_price: 2.96 + cache_read_price: 0.15 max_output_tokens: 235929 supports_function_calling: true - name: liquid/lfm-2.5-2.6b:free @@ -6909,6 +7534,7 @@ max_input_tokens: 1048756 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.006 max_output_tokens: 262144 supports_function_calling: true - name: meta-llama/llama-3.1-70b-instruct @@ -6923,6 +7549,7 @@ max_input_tokens: 131072 input_price: 0.05 output_price: 0.08 + cache_read_price: 0.025 max_output_tokens: 117964 supports_function_calling: true - name: meta-llama/llama-3.2-1b-instruct @@ -6947,9 +7574,9 @@ - name: meta-llama/llama-4-maverick type: chat max_input_tokens: 1048576 - input_price: 0.2 - output_price: 0.696 - max_output_tokens: 115200 + input_price: 0.1875 + output_price: 0.6525 + max_output_tokens: 16384 supports_vision: true supports_function_calling: true - name: meta-llama/llama-4-scout @@ -6972,6 +7599,7 @@ max_input_tokens: 131072 input_price: 0.35 output_price: 1.5 + cache_read_price: 0.04 max_output_tokens: 117964 supports_vision: true supports_function_calling: true @@ -6980,6 +7608,7 @@ max_input_tokens: 131072 input_price: 0.175 output_price: 0.75 + cache_read_price: 0.02 max_output_tokens: 117964 supports_vision: true supports_function_calling: true @@ -6988,6 +7617,7 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 4.25 + cache_read_price: 0.15 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -6996,6 +7626,7 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 4.25 + cache_read_price: 0.15 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -7004,6 +7635,7 @@ max_input_tokens: 1048576 input_price: 0.1 output_price: 0.2 + cache_read_price: 0.002 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -7012,6 +7644,7 @@ max_input_tokens: 1048576 input_price: 1.25 output_price: 4.25 + cache_read_price: 0.15 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -7020,6 +7653,7 @@ max_input_tokens: 1048576 input_price: 0.1 output_price: 0.2 + cache_read_price: 0.002 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -7061,12 +7695,14 @@ max_input_tokens: 65536 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.03 max_output_tokens: 2048 - name: minimax/minimax-m2.1 type: chat max_input_tokens: 204800 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.03 max_output_tokens: 131072 supports_function_calling: true - name: minimax/minimax-m2.5 @@ -7074,6 +7710,7 @@ max_input_tokens: 204800 input_price: 0.27 output_price: 1.08 + cache_read_price: 0.027 max_output_tokens: 128000 supports_function_calling: true - name: minimax/minimax-m2.7 @@ -7081,6 +7718,7 @@ max_input_tokens: 204800 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.06 max_output_tokens: 131072 supports_function_calling: true - name: minimax/minimax-m3 @@ -7088,6 +7726,7 @@ max_input_tokens: 1048576 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.06 max_output_tokens: 512000 supports_vision: true supports_function_calling: true @@ -7096,6 +7735,7 @@ max_input_tokens: 524288 input_price: 0.3 output_price: 1.2 + cache_read_price: 0.06 max_output_tokens: 471859 supports_vision: true supports_function_calling: true @@ -7104,6 +7744,7 @@ max_input_tokens: 256000 input_price: 0.3 output_price: 0.9 + cache_read_price: 0.03 max_output_tokens: 204800 supports_function_calling: true - name: mistralai/codestral-2508:batch @@ -7111,6 +7752,7 @@ max_input_tokens: 256000 input_price: 0.15 output_price: 0.45 + cache_read_price: 0.015 max_output_tokens: 204800 supports_function_calling: true - name: mistralai/devstral-2512 @@ -7118,6 +7760,7 @@ max_input_tokens: 262144 input_price: 0.4 output_price: 2.0 + cache_read_price: 0.04 max_output_tokens: 209715 supports_function_calling: true - name: mistralai/ministral-14b-2512 @@ -7125,6 +7768,7 @@ max_input_tokens: 262144 input_price: 0.2 output_price: 0.2 + cache_read_price: 0.02 max_output_tokens: 209715 supports_vision: true supports_function_calling: true @@ -7133,6 +7777,7 @@ max_input_tokens: 131072 input_price: 0.1 output_price: 0.1 + cache_read_price: 0.01 max_output_tokens: 104857 supports_vision: true supports_function_calling: true @@ -7141,6 +7786,7 @@ max_input_tokens: 262144 input_price: 0.15 output_price: 0.15 + cache_read_price: 0.015 max_output_tokens: 209715 supports_vision: true supports_function_calling: true @@ -7149,6 +7795,7 @@ max_input_tokens: 262144 input_price: 0.075 output_price: 0.075 + cache_read_price: 0.0075 max_output_tokens: 209715 supports_vision: true supports_function_calling: true @@ -7157,6 +7804,7 @@ max_input_tokens: 128000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.2 max_output_tokens: 102400 supports_function_calling: true - name: mistralai/mistral-large-2407 @@ -7164,6 +7812,7 @@ max_input_tokens: 131072 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.2 max_output_tokens: 104857 supports_function_calling: true - name: mistralai/mistral-large-2512 @@ -7171,6 +7820,7 @@ max_input_tokens: 262144 input_price: 0.5 output_price: 1.5 + cache_read_price: 0.05 max_output_tokens: 209715 supports_vision: true supports_function_calling: true @@ -7179,6 +7829,7 @@ max_input_tokens: 262144 input_price: 0.25 output_price: 0.75 + cache_read_price: 0.025 max_output_tokens: 209715 supports_vision: true supports_function_calling: true @@ -7187,6 +7838,7 @@ max_input_tokens: 131072 input_price: 0.4 output_price: 2.0 + cache_read_price: 0.04 max_output_tokens: 104857 supports_vision: true supports_function_calling: true @@ -7211,6 +7863,7 @@ max_input_tokens: 131072 input_price: 0.4 output_price: 2.0 + cache_read_price: 0.04 max_output_tokens: 104857 supports_vision: true supports_function_calling: true @@ -7219,6 +7872,7 @@ max_input_tokens: 131072 input_price: 0.2 output_price: 1.0 + cache_read_price: 0.02 max_output_tokens: 104857 supports_vision: true supports_function_calling: true @@ -7234,6 +7888,7 @@ max_input_tokens: 32768 input_price: 0.2 output_price: 0.6 + cache_read_price: 0.02 max_output_tokens: 26214 supports_function_calling: true - name: mistralai/mistral-small-24b-instruct-2501 @@ -7247,6 +7902,7 @@ max_input_tokens: 262144 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.015 max_output_tokens: 209715 supports_vision: true supports_function_calling: true @@ -7255,6 +7911,7 @@ max_input_tokens: 262144 input_price: 0.075 output_price: 0.3 + cache_read_price: 0.0075 max_output_tokens: 209715 supports_vision: true supports_function_calling: true @@ -7278,6 +7935,7 @@ max_input_tokens: 65536 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.2 max_output_tokens: 52428 supports_function_calling: true - name: mistralai/voxtral-small-24b-2507 @@ -7285,6 +7943,7 @@ max_input_tokens: 32768 input_price: 0.1 output_price: 0.3 + cache_read_price: 0.01 max_output_tokens: 26214 supports_function_calling: true - name: moonshotai/kimi-k2 @@ -7306,6 +7965,7 @@ max_input_tokens: 262144 input_price: 0.6 output_price: 2.5 + cache_read_price: 0.15 max_output_tokens: 98304 supports_function_calling: true - name: moonshotai/kimi-k2.5 @@ -7313,6 +7973,7 @@ max_input_tokens: 262144 input_price: 0.45 output_price: 2.25 + cache_read_price: 0.07 max_output_tokens: 235929 supports_vision: true supports_function_calling: true @@ -7321,6 +7982,7 @@ max_input_tokens: 262144 input_price: 0.95 output_price: 4.0 + cache_read_price: 0.16 max_output_tokens: 235929 supports_vision: true supports_function_calling: true @@ -7329,6 +7991,7 @@ max_input_tokens: 262144 input_price: 0.71 output_price: 3.5 + cache_read_price: 0.15 max_output_tokens: 235929 supports_vision: true supports_function_calling: true @@ -7337,6 +8000,7 @@ max_input_tokens: 1048576 input_price: 2.6481 output_price: 13.2827 + cache_read_price: 0.3026 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -7345,6 +8009,7 @@ max_input_tokens: 1048576 input_price: 3.0 output_price: 15.0 + cache_read_price: 0.3 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -7399,6 +8064,7 @@ max_input_tokens: 262144 input_price: 0.05 output_price: 0.2 + cache_read_price: 0.03 max_output_tokens: 235929 supports_function_calling: true - name: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free @@ -7428,6 +8094,7 @@ max_input_tokens: 262144 input_price: 0.6 output_price: 2.4 + cache_read_price: 0.12 max_output_tokens: 182520 supports_function_calling: true - name: nvidia/nemotron-3-ultra-550b-a55b:free @@ -7456,6 +8123,7 @@ max_input_tokens: 262144 input_price: 0.08 output_price: 0.2 + cache_read_price: 0.04 max_output_tokens: 131072 supports_function_calling: true - name: nvidia/nemotron-3.5-lightning:free @@ -7534,6 +8202,7 @@ max_input_tokens: 1047576 input_price: 2.0 output_price: 8.0 + cache_read_price: 0.5 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -7542,6 +8211,7 @@ max_input_tokens: 1047576 input_price: 0.4 output_price: 1.6 + cache_read_price: 0.1 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -7550,6 +8220,7 @@ max_input_tokens: 1047576 input_price: 0.2 output_price: 0.8 + cache_read_price: 0.05 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -7558,6 +8229,7 @@ max_input_tokens: 1047576 input_price: 0.1 output_price: 0.4 + cache_read_price: 0.025 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -7566,6 +8238,7 @@ max_input_tokens: 1047576 input_price: 0.05 output_price: 0.2 + cache_read_price: 0.0125 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -7574,6 +8247,7 @@ max_input_tokens: 1047576 input_price: 1.0 output_price: 4.0 + cache_read_price: 0.25 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -7582,6 +8256,7 @@ max_input_tokens: 128000 input_price: 2.5 output_price: 10.0 + cache_read_price: 1.25 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7598,6 +8273,7 @@ max_input_tokens: 128000 input_price: 2.5 output_price: 10.0 + cache_read_price: 1.25 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7606,6 +8282,7 @@ max_input_tokens: 128000 input_price: 2.5 output_price: 10.0 + cache_read_price: 1.25 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7614,6 +8291,7 @@ max_input_tokens: 128000 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.075 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7622,6 +8300,7 @@ max_input_tokens: 128000 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.075 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7630,6 +8309,7 @@ max_input_tokens: 128000 input_price: 0.075 output_price: 0.3 + cache_read_price: 0.0375 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7638,6 +8318,7 @@ max_input_tokens: 128000 input_price: 1.25 output_price: 5.0 + cache_read_price: 0.625 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7646,6 +8327,7 @@ max_input_tokens: 400000 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7660,6 +8342,7 @@ max_input_tokens: 400000 input_price: 10.0 output_price: 10.0 + cache_read_price: 1.25 max_output_tokens: 128000 supports_vision: true - name: openai/gpt-5-image-mini @@ -7667,6 +8350,7 @@ max_input_tokens: 400000 input_price: 2.5 output_price: 2.0 + cache_read_price: 0.25 max_output_tokens: 128000 supports_vision: true - name: openai/gpt-5-mini @@ -7674,6 +8358,7 @@ max_input_tokens: 400000 input_price: 0.25 output_price: 2.0 + cache_read_price: 0.025 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7682,6 +8367,7 @@ max_input_tokens: 400000 input_price: 0.125 output_price: 1.0 + cache_read_price: 0.0125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7690,6 +8376,7 @@ max_input_tokens: 400000 input_price: 0.05 output_price: 0.4 + cache_read_price: 0.005 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7698,6 +8385,7 @@ max_input_tokens: 400000 input_price: 0.025 output_price: 0.2 + cache_read_price: 0.0025 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7722,6 +8410,7 @@ max_input_tokens: 400000 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7730,6 +8419,7 @@ max_input_tokens: 400000 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.13 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7738,6 +8428,7 @@ max_input_tokens: 400000 input_price: 1.25 output_price: 10.0 + cache_read_price: 0.125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7746,6 +8437,7 @@ max_input_tokens: 400000 input_price: 0.25 output_price: 2.0 + cache_read_price: 0.03 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7754,6 +8446,7 @@ max_input_tokens: 400000 input_price: 0.625 output_price: 5.0 + cache_read_price: 0.0625 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7762,6 +8455,7 @@ max_input_tokens: 400000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7777,6 +8471,7 @@ max_input_tokens: 128000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 32000 supports_vision: true supports_function_calling: true @@ -7785,6 +8480,7 @@ max_input_tokens: 400000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7814,6 +8510,7 @@ max_input_tokens: 400000 input_price: 0.875 output_price: 7.0 + cache_read_price: 0.0875 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7822,6 +8519,7 @@ max_input_tokens: 400000 input_price: 1.75 output_price: 14.0 + cache_read_price: 0.175 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7836,6 +8534,7 @@ max_input_tokens: 1050000 input_price: 2.5 output_price: 15.0 + cache_read_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7851,6 +8550,7 @@ max_input_tokens: 272000 input_price: 8.0 output_price: 15.0 + cache_read_price: 2.0 max_output_tokens: 128000 supports_vision: true - name: openai/gpt-5.4-mini @@ -7858,6 +8558,7 @@ max_input_tokens: 400000 input_price: 0.75 output_price: 4.5 + cache_read_price: 0.075 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7873,6 +8574,7 @@ max_input_tokens: 400000 input_price: 0.375 output_price: 2.25 + cache_read_price: 0.0375 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7881,6 +8583,7 @@ max_input_tokens: 400000 input_price: 0.2 output_price: 1.25 + cache_read_price: 0.02 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7896,6 +8599,7 @@ max_input_tokens: 400000 input_price: 0.1 output_price: 0.625 + cache_read_price: 0.01 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7925,6 +8629,7 @@ max_input_tokens: 1050000 input_price: 1.25 output_price: 7.5 + cache_read_price: 0.125 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7933,6 +8638,7 @@ max_input_tokens: 1050000 input_price: 5.0 output_price: 30.0 + cache_read_price: 0.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7969,6 +8675,7 @@ max_input_tokens: 1050000 input_price: 2.5 output_price: 15.0 + cache_read_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7977,6 +8684,8 @@ max_input_tokens: 1050000 input_price: 0.2 output_price: 1.2 + cache_read_price: 0.02 + cache_write_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -7993,6 +8702,8 @@ max_input_tokens: 1050000 input_price: 0.2 output_price: 1.2 + cache_read_price: 0.02 + cache_write_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8009,6 +8720,7 @@ max_input_tokens: 1050000 input_price: 0.1 output_price: 0.6 + cache_read_price: 0.01 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8025,6 +8737,7 @@ max_input_tokens: 1050000 input_price: 0.1 output_price: 0.6 + cache_read_price: 0.01 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8041,6 +8754,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8057,6 +8772,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8073,6 +8790,8 @@ max_input_tokens: 1050000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8089,6 +8808,8 @@ max_input_tokens: 1050000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8105,6 +8826,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8121,6 +8844,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8137,6 +8862,7 @@ max_input_tokens: 1050000 input_price: 1.0 output_price: 6.0 + cache_read_price: 0.1 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8153,6 +8879,7 @@ max_input_tokens: 1050000 input_price: 1.0 output_price: 6.0 + cache_read_price: 0.1 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8169,6 +8896,7 @@ max_input_tokens: 400000 input_price: 0.625 output_price: 5.0 + cache_read_price: 0.0625 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8177,6 +8905,8 @@ max_input_tokens: 1050000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8185,6 +8915,8 @@ max_input_tokens: 1050000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8193,6 +8925,8 @@ max_input_tokens: 1050000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8201,6 +8935,8 @@ max_input_tokens: 1050000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8223,6 +8959,7 @@ max_input_tokens: 400000 input_price: 5.0 output_price: 30.0 + cache_read_price: 0.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8245,6 +8982,7 @@ max_input_tokens: 131072 input_price: 0.03 output_price: 0.13 + cache_read_price: 0.03 max_output_tokens: 117964 supports_function_calling: true - name: openai/gpt-oss-20b:batch @@ -8258,6 +8996,7 @@ max_input_tokens: 131072 input_price: 0.075 output_price: 0.3 + cache_read_price: 0.0375 max_output_tokens: 65536 supports_function_calling: true - name: openai/o1 @@ -8265,6 +9004,7 @@ max_input_tokens: 200000 input_price: 15.0 output_price: 60.0 + cache_read_price: 7.5 max_output_tokens: 100000 supports_vision: true supports_function_calling: true @@ -8280,6 +9020,7 @@ max_input_tokens: 200000 input_price: 2.0 output_price: 8.0 + cache_read_price: 0.5 max_output_tokens: 100000 supports_vision: true supports_function_calling: true @@ -8288,6 +9029,7 @@ max_input_tokens: 200000 input_price: 1.1 output_price: 4.4 + cache_read_price: 0.55 max_output_tokens: 100000 supports_function_calling: true - name: openai/o3-mini-high @@ -8295,6 +9037,7 @@ max_input_tokens: 200000 input_price: 1.1 output_price: 4.4 + cache_read_price: 0.55 max_output_tokens: 100000 supports_function_calling: true - name: openai/o3-mini:batch @@ -8302,6 +9045,7 @@ max_input_tokens: 200000 input_price: 0.55 output_price: 2.2 + cache_read_price: 0.275 max_output_tokens: 100000 supports_function_calling: true - name: openai/o3-pro @@ -8317,6 +9061,7 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 4.0 + cache_read_price: 0.25 max_output_tokens: 100000 supports_vision: true supports_function_calling: true @@ -8325,6 +9070,7 @@ max_input_tokens: 200000 input_price: 1.1 output_price: 4.4 + cache_read_price: 0.275 max_output_tokens: 100000 supports_vision: true supports_function_calling: true @@ -8333,6 +9079,7 @@ max_input_tokens: 200000 input_price: 1.1 output_price: 4.4 + cache_read_price: 0.275 max_output_tokens: 100000 supports_vision: true supports_function_calling: true @@ -8341,6 +9088,7 @@ max_input_tokens: 200000 input_price: 0.55 output_price: 2.2 + cache_read_price: 0.1375 max_output_tokens: 100000 supports_vision: true supports_function_calling: true @@ -8422,6 +9170,7 @@ max_input_tokens: 1048576 input_price: 0.09 output_price: 0.18 + cache_read_price: 0.009 max_output_tokens: 131072 supports_function_calling: true - name: poolside/laguna-s-2.1:free @@ -8436,6 +9185,7 @@ max_input_tokens: 262144 input_price: 0.06 output_price: 0.12 + cache_read_price: 0.03 max_output_tokens: 32768 supports_function_calling: true - name: poolside/laguna-xs-2.1:free @@ -8470,6 +9220,8 @@ max_input_tokens: 1000000 input_price: 0.26 output_price: 0.78 + cache_read_price: 0.052 + cache_write_price: 0.325 max_output_tokens: 32768 supports_function_calling: true - name: qwen/qwen-plus-2025-07-28 @@ -8484,6 +9236,7 @@ max_input_tokens: 128000 input_price: 0.8 output_price: 1.0 + cache_read_price: 0.4 max_output_tokens: 115200 supports_vision: true - name: qwen/qwen3-14b @@ -8505,6 +9258,7 @@ max_input_tokens: 262144 input_price: 0.0875 output_price: 0.35 + cache_read_price: 0.0175 max_output_tokens: 235929 supports_function_calling: true - name: qwen/qwen3-235b-a22b-thinking-2507 @@ -8554,6 +9308,7 @@ max_input_tokens: 262144 input_price: 0.3 output_price: 1.0 + cache_read_price: 0.1 max_output_tokens: 65536 supports_function_calling: true - name: qwen/qwen3-coder-30b-a3b-instruct @@ -8568,6 +9323,8 @@ max_input_tokens: 1000000 input_price: 0.195 output_price: 0.975 + cache_read_price: 0.039 + cache_write_price: 0.2438 max_output_tokens: 65536 supports_function_calling: true - name: qwen/qwen3-coder-next @@ -8575,6 +9332,7 @@ max_input_tokens: 262144 input_price: 0.12 output_price: 0.8 + cache_read_price: 0.07 max_output_tokens: 235929 supports_function_calling: true - name: qwen/qwen3-coder-plus @@ -8582,6 +9340,8 @@ max_input_tokens: 1000000 input_price: 0.65 output_price: 3.25 + cache_read_price: 0.13 + cache_write_price: 0.8125 max_output_tokens: 65536 supports_function_calling: true - name: qwen/qwen3-max @@ -8589,6 +9349,8 @@ max_input_tokens: 262144 input_price: 0.78 output_price: 3.9 + cache_read_price: 0.156 + cache_write_price: 0.975 max_output_tokens: 65536 supports_function_calling: true - name: qwen/qwen3-max-thinking @@ -8617,6 +9379,7 @@ max_input_tokens: 262144 input_price: 0.21 output_price: 1.9 + cache_read_price: 0.1 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -8689,6 +9452,7 @@ max_input_tokens: 262144 input_price: 0.3125 output_price: 1.25 + cache_read_price: 0.1563 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -8697,6 +9461,7 @@ max_input_tokens: 262144 input_price: 0.55 output_price: 3.5 + cache_read_price: 0.225 max_output_tokens: 235929 supports_vision: true supports_function_calling: true @@ -8737,6 +9502,7 @@ max_input_tokens: 1000000 input_price: 0.3 output_price: 1.8 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -8745,6 +9511,7 @@ max_input_tokens: 262144 input_price: 0.3 output_price: 2.0 + cache_read_price: 0.03 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -8753,6 +9520,7 @@ max_input_tokens: 262144 input_price: 0.1 output_price: 0.9 + cache_read_price: 0.05 max_output_tokens: 235929 supports_vision: true supports_function_calling: true @@ -8761,6 +9529,7 @@ max_input_tokens: 1000000 input_price: 0.1875 output_price: 1.125 + cache_write_price: 0.2344 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -8769,6 +9538,7 @@ max_input_tokens: 262144 input_price: 1.027 output_price: 6.162 + cache_write_price: 1.2838 max_output_tokens: 65536 supports_function_calling: true - name: qwen/qwen3.6-plus @@ -8776,6 +9546,7 @@ max_input_tokens: 1000000 input_price: 0.325 output_price: 1.95 + cache_write_price: 0.4063 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -8784,6 +9555,8 @@ max_input_tokens: 1000000 input_price: 0.03 output_price: 0.13 + cache_read_price: 0.006 + cache_write_price: 0.038 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -8792,6 +9565,8 @@ max_input_tokens: 1000000 input_price: 1.475 output_price: 4.425 + cache_read_price: 0.295 + cache_write_price: 1.8438 max_output_tokens: 131072 supports_function_calling: true - name: qwen/qwen3.7-plus @@ -8799,6 +9574,8 @@ max_input_tokens: 1000000 input_price: 0.32 output_price: 1.28 + cache_read_price: 0.064 + cache_write_price: 0.4 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -8807,6 +9584,7 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.25 max_output_tokens: 131072 supports_function_calling: true - name: qwen/qwen3.8-2.4t-a95b:batch @@ -8814,6 +9592,7 @@ max_input_tokens: 1010000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.25 max_output_tokens: 909000 supports_function_calling: true - name: qwen/qwen3.8-27b @@ -8821,6 +9600,7 @@ max_input_tokens: 1000000 input_price: 0.214 output_price: 2.55 + cache_read_price: 0.15 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -8829,6 +9609,8 @@ max_input_tokens: 1000000 input_price: 0.15 output_price: 0.47 + cache_read_price: 0.016 + cache_write_price: 0.2 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -8837,6 +9619,8 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.25 + cache_write_price: 2.5 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -8872,6 +9656,7 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8880,6 +9665,7 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 30.0 + cache_read_price: 0.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8888,6 +9674,7 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 30.0 + cache_read_price: 0.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -8896,6 +9683,7 @@ max_input_tokens: 262144 input_price: 0.95 output_price: 4.0 + cache_read_price: 0.15 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -8930,6 +9718,7 @@ max_input_tokens: 262144 input_price: 0.2 output_price: 1.15 + cache_read_price: 0.04 max_output_tokens: 230400 supports_vision: true supports_function_calling: true @@ -8960,8 +9749,9 @@ - name: tencent/hy3 type: chat max_input_tokens: 262144 - input_price: 0.132 - output_price: 0.528 + input_price: 0.0825 + output_price: 0.33 + cache_read_price: 0.0206 max_output_tokens: 128000 supports_function_calling: true - name: tencent/hy3-preview @@ -8969,6 +9759,7 @@ max_input_tokens: 262144 input_price: 0.18 output_price: 0.6 + cache_read_price: 0.06 max_output_tokens: 235929 supports_function_calling: true - name: tencent/hy4-preview @@ -8976,6 +9767,7 @@ max_input_tokens: 1048576 input_price: 0.834 output_price: 2.501 + cache_read_price: 0.042 max_output_tokens: 64000 supports_function_calling: true - name: thedrummer/cydonia-24b-v4.1 @@ -8983,12 +9775,14 @@ max_input_tokens: 131072 input_price: 0.3 output_price: 0.5 + cache_read_price: 0.15 max_output_tokens: 117964 - name: thedrummer/skyfall-36b-v2 type: chat max_input_tokens: 32768 input_price: 0.55 output_price: 0.8 + cache_read_price: 0.25 max_output_tokens: 29491 - name: thedrummer/unslopnemo-12b type: chat @@ -9002,6 +9796,7 @@ max_input_tokens: 1048576 input_price: 1.0 output_price: 4.05 + cache_read_price: 0.17 max_output_tokens: 471859 supports_vision: true supports_function_calling: true @@ -9010,6 +9805,7 @@ max_input_tokens: 1048576 input_price: 0.45 output_price: 1.2 + cache_read_price: 0.1 max_output_tokens: 262144 supports_vision: true supports_function_calling: true @@ -9018,6 +9814,7 @@ max_input_tokens: 524288 input_price: 0.5 output_price: 1.2 + cache_read_price: 0.1 max_output_tokens: 471859 supports_vision: true supports_function_calling: true @@ -9034,6 +9831,7 @@ max_input_tokens: 524288 input_price: 1.0 output_price: 4.05 + cache_read_price: 0.17 max_output_tokens: 471859 supports_vision: true supports_function_calling: true @@ -9056,6 +9854,7 @@ max_input_tokens: 131072 input_price: 0.15 output_price: 0.6 + cache_read_price: 0.015 max_output_tokens: 117964 supports_function_calling: true - name: upstage/solar-pro4 @@ -9063,6 +9862,7 @@ max_input_tokens: 524288 input_price: 0.09 output_price: 0.36 + cache_read_price: 0.018 max_output_tokens: 131072 supports_function_calling: true - name: writer/palmyra-x5 @@ -9076,6 +9876,7 @@ max_input_tokens: 2000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 1800000 supports_vision: true supports_function_calling: true @@ -9084,6 +9885,7 @@ max_input_tokens: 2000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 1800000 supports_vision: true - name: x-ai/grok-4.3 @@ -9091,6 +9893,7 @@ max_input_tokens: 1000000 input_price: 1.25 output_price: 2.5 + cache_read_price: 0.2 max_output_tokens: 900000 supports_vision: true supports_function_calling: true @@ -9099,6 +9902,7 @@ max_input_tokens: 1000000 input_price: 1.0 output_price: 2.0 + cache_read_price: 0.16 max_output_tokens: 900000 supports_vision: true supports_function_calling: true @@ -9107,6 +9911,7 @@ max_input_tokens: 500000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.3 max_output_tokens: 450000 supports_vision: true supports_function_calling: true @@ -9115,6 +9920,7 @@ max_input_tokens: 500000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.5 max_output_tokens: 450000 supports_vision: true supports_function_calling: true @@ -9123,6 +9929,7 @@ max_input_tokens: 256000 input_price: 1.0 output_price: 2.0 + cache_read_price: 0.2 max_output_tokens: 230400 supports_vision: true supports_function_calling: true @@ -9131,6 +9938,7 @@ max_input_tokens: 1050000 input_price: 0.14 output_price: 0.28 + cache_read_price: 0.0028 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9139,6 +9947,7 @@ max_input_tokens: 1050000 input_price: 0.435 output_price: 0.87 + cache_read_price: 0.0036 max_output_tokens: 131072 supports_function_calling: true - name: z-ai/glm-4.5 @@ -9146,6 +9955,7 @@ max_input_tokens: 131072 input_price: 0.6 output_price: 2.2 + cache_read_price: 0.11 max_output_tokens: 98304 supports_function_calling: true - name: z-ai/glm-4.5-air @@ -9153,6 +9963,7 @@ max_input_tokens: 131072 input_price: 0.13 output_price: 0.85 + cache_read_price: 0.025 max_output_tokens: 98304 supports_function_calling: true - name: z-ai/glm-4.5v @@ -9160,6 +9971,7 @@ max_input_tokens: 65536 input_price: 0.6 output_price: 1.8 + cache_read_price: 0.11 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -9168,6 +9980,7 @@ max_input_tokens: 204800 input_price: 0.43 output_price: 1.75 + cache_read_price: 0.08 max_output_tokens: 16384 supports_function_calling: true - name: z-ai/glm-4.6v @@ -9175,6 +9988,7 @@ max_input_tokens: 131072 input_price: 0.3 output_price: 0.9 + cache_read_price: 0.055 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -9183,6 +9997,7 @@ max_input_tokens: 204800 input_price: 0.4 output_price: 1.75 + cache_read_price: 0.08 max_output_tokens: 131072 supports_function_calling: true - name: z-ai/glm-4.7-flash @@ -9197,6 +10012,7 @@ max_input_tokens: 204800 input_price: 0.6 output_price: 1.92 + cache_read_price: 0.12 max_output_tokens: 128000 supports_function_calling: true - name: z-ai/glm-5-turbo @@ -9204,6 +10020,7 @@ max_input_tokens: 202752 input_price: 1.2 output_price: 4.0 + cache_read_price: 0.24 max_output_tokens: 131072 supports_function_calling: true - name: z-ai/glm-5.1 @@ -9211,6 +10028,7 @@ max_input_tokens: 204800 input_price: 0.966 output_price: 3.036 + cache_read_price: 0.1794 max_output_tokens: 128000 supports_function_calling: true - name: z-ai/glm-5.2 @@ -9218,6 +10036,7 @@ max_input_tokens: 1048576 input_price: 0.6832 output_price: 2.1472 + cache_read_price: 0.1269 max_output_tokens: 131072 supports_function_calling: true - name: z-ai/glm-5.2:batch @@ -9225,6 +10044,7 @@ max_input_tokens: 1048576 input_price: 0.7 output_price: 2.2 + cache_read_price: 0.07 max_output_tokens: 943718 supports_function_calling: true - name: z-ai/glm-5.3 @@ -9232,6 +10052,7 @@ max_input_tokens: 1310720 input_price: 1.4 output_price: 4.4 + cache_read_price: 0.26 max_output_tokens: 943717 supports_function_calling: true - name: z-ai/glm-5.3-flash @@ -9239,6 +10060,7 @@ max_input_tokens: 1310720 input_price: 0.15 output_price: 0.5 + cache_read_price: 0.03 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9247,6 +10069,7 @@ max_input_tokens: 1048576 input_price: 0.075 output_price: 0.25 + cache_read_price: 0.015 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -9255,6 +10078,7 @@ max_input_tokens: 1048576 input_price: 0.7 output_price: 2.2 + cache_read_price: 0.13 max_output_tokens: 943718 supports_function_calling: true - name: z-ai/glm-5v-turbo @@ -9262,6 +10086,7 @@ max_input_tokens: 202752 input_price: 1.2 output_price: 4.0 + cache_read_price: 0.24 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9270,6 +10095,8 @@ max_input_tokens: 1000000 input_price: 10.0 output_price: 50.0 + cache_read_price: 0.25 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9278,6 +10105,8 @@ max_input_tokens: 200000 input_price: 1.0 output_price: 5.0 + cache_read_price: 0.1 + cache_write_price: 1.25 max_output_tokens: 64000 supports_vision: true supports_function_calling: true @@ -9286,6 +10115,8 @@ max_input_tokens: 1000000 input_price: 5.0 output_price: 25.0 + cache_read_price: 0.5 + cache_write_price: 6.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9294,14 +10125,34 @@ max_input_tokens: 1000000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true + - name: ~deepseek/deepseek-flash-latest + type: chat + max_input_tokens: 1048576 + input_price: 0.15 + output_price: 0.6 + cache_read_price: 0.003 + max_output_tokens: 943718 + supports_vision: true + supports_function_calling: true + - name: ~deepseek/deepseek-pro-latest + type: chat + max_input_tokens: 1048576 + input_price: 0.5795 + output_price: 1.7384 + cache_read_price: 0.0184 + max_output_tokens: 393216 + supports_function_calling: true - name: ~deepseek/deepseek-v4-flash-latest type: chat max_input_tokens: 1310720 input_price: 0.04 output_price: 0.1 + cache_read_price: 0.01 max_output_tokens: 393216 supports_function_calling: true - name: ~google/gemini-flash-latest @@ -9309,6 +10160,8 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 3.75 + cache_read_price: 0.075 + cache_write_price: 0.0417 max_output_tokens: 65536 supports_vision: true supports_function_calling: true @@ -9317,14 +10170,17 @@ max_input_tokens: 1048576 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 0.375 max_output_tokens: 65536 supports_vision: true supports_function_calling: true - name: ~moonshotai/kimi-latest type: chat max_input_tokens: 1048576 - input_price: 2.1 - output_price: 10.95 + input_price: 1.975 + output_price: 11.06 + cache_read_price: 0.2291 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -9333,6 +10189,8 @@ max_input_tokens: 1050000 input_price: 10.0 output_price: 50.0 + cache_read_price: 1.0 + cache_write_price: 12.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9341,6 +10199,8 @@ max_input_tokens: 1050000 input_price: 0.2 output_price: 1.2 + cache_read_price: 0.02 + cache_write_price: 0.25 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9349,6 +10209,7 @@ max_input_tokens: 400000 input_price: 0.75 output_price: 4.5 + cache_read_price: 0.075 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9357,6 +10218,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 10.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9365,6 +10228,8 @@ max_input_tokens: 1050000 input_price: 2.0 output_price: 12.0 + cache_read_price: 0.2 + cache_write_price: 2.5 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9373,6 +10238,7 @@ max_input_tokens: 500000 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.5 max_output_tokens: 450000 supports_vision: true supports_function_calling: true @@ -9381,14 +10247,16 @@ max_input_tokens: 1310720 input_price: 0.075 output_price: 0.25 + cache_read_price: 0.015 max_output_tokens: 131072 supports_vision: true supports_function_calling: true - name: ~z-ai/glm-latest type: chat max_input_tokens: 1310720 - input_price: 0.92 - output_price: 3.1372 + input_price: 0.9 + output_price: 3.069 + cache_read_price: 0.18 max_output_tokens: 943718 supports_function_calling: true - provider: github @@ -9499,6 +10367,7 @@ max_input_tokens: 1048576 input_price: 0.2 output_price: 0.6 + cache_read_price: 0.006 max_output_tokens: 384000 supports_vision: true supports_function_calling: true @@ -9513,6 +10382,7 @@ max_input_tokens: 1000000 input_price: 0.113 output_price: 0.382 + cache_read_price: 0.0141 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9521,6 +10391,7 @@ max_input_tokens: 1048576 input_price: 0.15 output_price: 0.5 + cache_read_price: 0.03 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9533,6 +10404,7 @@ max_input_tokens: 1048576 input_price: 0.44 output_price: 1.32 + cache_read_price: 0.014 max_output_tokens: 384000 supports_vision: true supports_function_calling: true @@ -9546,6 +10418,7 @@ max_input_tokens: 262144 input_price: 0.4 output_price: 3.0 + cache_read_price: 0.04 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -9558,6 +10431,7 @@ max_input_tokens: 1048576 input_price: 1.2 output_price: 4.0 + cache_read_price: 0.12 max_output_tokens: 131072 supports_function_calling: true reasoning_levels: @@ -9569,6 +10443,7 @@ max_input_tokens: 262144 input_price: 2.0 output_price: 6.0 + cache_read_price: 0.2 max_output_tokens: 131072 supports_function_calling: true reasoning_levels: @@ -9580,6 +10455,7 @@ max_input_tokens: 1048576 input_price: 1.3 output_price: 2.6 + cache_read_price: 0.1 max_output_tokens: 384000 supports_function_calling: true reasoning_levels: @@ -9590,6 +10466,7 @@ max_input_tokens: 256000 input_price: 1.65 output_price: 4.951 + cache_read_price: 0.206 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9598,6 +10475,7 @@ max_input_tokens: 1048576 input_price: 0.06 output_price: 0.18 + cache_read_price: 0.015 max_output_tokens: 384000 supports_function_calling: true - name: thinkingmachines/Inkling-Small @@ -9605,6 +10483,7 @@ max_input_tokens: 524288 input_price: 0.45 output_price: 1.2 + cache_read_price: 0.1 max_output_tokens: 1048576 supports_vision: true supports_function_calling: true @@ -9613,6 +10492,7 @@ max_input_tokens: 1048576 input_price: 2.85 output_price: 14.25 + cache_read_price: 0.285 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9625,6 +10505,7 @@ max_input_tokens: 524288 input_price: 0.95 output_price: 4.05 + cache_read_price: 0.16 max_output_tokens: 1048576 supports_vision: true supports_function_calling: true @@ -9633,6 +10514,7 @@ max_input_tokens: 262144 input_price: 0.14 output_price: 0.58 + cache_read_price: 0.035 max_output_tokens: 128000 supports_function_calling: true - name: zai-org/GLM-5.2 @@ -9640,6 +10522,7 @@ max_input_tokens: 1048576 input_price: 0.75 output_price: 2.4 + cache_read_price: 0.14 max_output_tokens: 32768 supports_function_calling: true reasoning_levels: @@ -9652,6 +10535,7 @@ max_input_tokens: 262144 input_price: 0.68 output_price: 3.4 + cache_read_price: 0.136 max_output_tokens: 262144 supports_vision: true supports_function_calling: true @@ -9660,6 +10544,7 @@ max_input_tokens: 524288 input_price: 0.28 output_price: 1.1 + cache_read_price: 0.056 max_output_tokens: 512000 supports_vision: true supports_function_calling: true @@ -9668,6 +10553,7 @@ max_input_tokens: 262144 input_price: 0.2 output_price: 1.15 + cache_read_price: 0.04 max_output_tokens: 256000 supports_vision: true supports_function_calling: true @@ -9676,6 +10562,7 @@ max_input_tokens: 256000 input_price: 2.5 output_price: 7.5 + cache_read_price: 0.5 max_output_tokens: 65536 supports_function_calling: true - name: nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning @@ -9691,6 +10578,7 @@ max_input_tokens: 1048576 input_price: 0.09 output_price: 0.18 + cache_read_price: 0.018 max_output_tokens: 16384 supports_function_calling: true reasoning_levels: @@ -9703,6 +10591,7 @@ max_input_tokens: 1048576 input_price: 1.3 output_price: 2.6 + cache_read_price: 0.1 max_output_tokens: 16384 supports_function_calling: true reasoning_levels: @@ -9723,6 +10612,7 @@ max_input_tokens: 262144 input_price: 0.14 output_price: 0.28 + cache_read_price: 0.0028 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -9731,6 +10621,7 @@ max_input_tokens: 1048576 input_price: 1.0 output_price: 3.0 + cache_read_price: 0.2 max_output_tokens: 16384 supports_function_calling: true - name: moonshotai/Kimi-K2.6 @@ -9738,6 +10629,7 @@ max_input_tokens: 262144 input_price: 0.75 output_price: 3.5 + cache_read_price: 0.15 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -9746,6 +10638,7 @@ max_input_tokens: 202752 input_price: 1.05 output_price: 3.5 + cache_read_price: 0.205 max_output_tokens: 16384 supports_function_calling: true - name: google/gemma-4-26B-A4B-it @@ -9785,6 +10678,7 @@ max_input_tokens: 196608 input_price: 0.25 output_price: 1.0 + cache_read_price: 0.05 max_output_tokens: 131072 supports_function_calling: true - name: Qwen/Qwen3.5-122B-A10B @@ -9816,6 +10710,7 @@ max_input_tokens: 256000 input_price: 0.5 output_price: 3.0 + cache_read_price: 0.1 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -9829,6 +10724,7 @@ max_input_tokens: 256000 input_price: 0.1 output_price: 0.4 + cache_read_price: 0.02 max_output_tokens: 32000 supports_vision: true supports_function_calling: true @@ -9837,6 +10733,7 @@ max_input_tokens: 256000 input_price: 0.5 output_price: 3.0 + cache_read_price: 0.1 max_output_tokens: 128000 supports_vision: true supports_function_calling: true @@ -9845,6 +10742,7 @@ max_input_tokens: 196608 input_price: 0.15 output_price: 1.15 + cache_read_price: 0.03 max_output_tokens: 131072 supports_function_calling: true - name: zai-org/GLM-5 @@ -9852,6 +10750,7 @@ max_input_tokens: 202752 input_price: 0.6 output_price: 2.08 + cache_read_price: 0.12 max_output_tokens: 16384 supports_function_calling: true - name: Qwen/Qwen3.5-35B-A3B @@ -9859,6 +10758,7 @@ max_input_tokens: 262144 input_price: 0.14 output_price: 1.0 + cache_read_price: 0.05 max_output_tokens: 81920 supports_vision: true supports_function_calling: true @@ -9867,6 +10767,7 @@ max_input_tokens: 262144 input_price: 0.45 output_price: 3.0 + cache_read_price: 0.22 max_output_tokens: 81920 supports_vision: true supports_function_calling: true @@ -9875,6 +10776,7 @@ max_input_tokens: 262144 input_price: 0.45 output_price: 2.25 + cache_read_price: 0.07 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -9883,6 +10785,7 @@ max_input_tokens: 202752 input_price: 0.06 output_price: 0.4 + cache_read_price: 0.01 max_output_tokens: 16384 supports_function_calling: true - name: zai-org/GLM-4.7 @@ -9890,6 +10793,7 @@ max_input_tokens: 202752 input_price: 0.4 output_price: 1.75 + cache_read_price: 0.08 max_output_tokens: 16384 supports_function_calling: true - name: nvidia/Nemotron-3-Nano-30B-A3B @@ -9897,6 +10801,7 @@ max_input_tokens: 262144 input_price: 0.05 output_price: 0.2 + cache_read_price: 0.025 max_output_tokens: 262144 supports_function_calling: true - name: deepseek-ai/DeepSeek-V3.2 @@ -9904,6 +10809,7 @@ max_input_tokens: 163840 input_price: 0.26 output_price: 0.38 + cache_read_price: 0.13 max_output_tokens: 64000 supports_function_calling: true - name: zai-org/GLM-4.6 @@ -9911,6 +10817,7 @@ max_input_tokens: 202752 input_price: 0.5 output_price: 2.0 + cache_read_price: 0.1 max_output_tokens: 131072 supports_function_calling: true - name: Qwen/Qwen3-Max @@ -9918,6 +10825,7 @@ max_input_tokens: 256000 input_price: 1.2 output_price: 6.0 + cache_read_price: 0.24 max_output_tokens: 65536 supports_function_calling: true - name: Qwen/Qwen3-VL-235B-A22B-Instruct @@ -9925,6 +10833,7 @@ max_input_tokens: 262144 input_price: 0.2 output_price: 0.88 + cache_read_price: 0.11 max_output_tokens: 32768 supports_vision: true supports_function_calling: true @@ -9940,6 +10849,7 @@ max_input_tokens: 163840 input_price: 0.25 output_price: 0.95 + cache_read_price: 0.13 max_output_tokens: 8192 supports_function_calling: true - name: openai/gpt-oss-120b @@ -9976,6 +10886,7 @@ max_input_tokens: 262144 input_price: 0.3 output_price: 1.0 + cache_read_price: 0.1 max_output_tokens: 66536 supports_function_calling: true - name: Qwen/Qwen3-235B-A22B-Instruct-2507 @@ -9990,6 +10901,7 @@ max_input_tokens: 163840 input_price: 0.5 output_price: 2.15 + cache_read_price: 0.35 max_output_tokens: 64000 supports_function_calling: true - name: Qwen/Qwen3-30B-A3B @@ -10026,6 +10938,7 @@ max_input_tokens: 163840 input_price: 0.24 output_price: 0.9 + cache_read_price: 0.135 max_output_tokens: 163840 supports_function_calling: true - name: google/gemma-3-12b-it