chore(sync): update Requesty model catalog (#5143)

Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>

providers/requesty/models/claude-fable-5.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 10
-output = 50
-cache_read = 1
-cache_write = 12.5
+input = 9
+output = 45
+cache_read = 0.9
+cache_write = 11.25

providers/requesty/models/claude-fable-5@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 11
-output = 55
-cache_read = 1.1
-cache_write = 13.75
+input = 9.9
+output = 49.5
+cache_read = 0.99
+cache_write = 12.375

providers/requesty/models/claude-haiku-4-5.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1
-output = 5
-cache_read = 0.1
-cache_write = 1.25
+input = 0.9
+output = 4.5
+cache_read = 0.09
+cache_write = 1.125

providers/requesty/models/claude-haiku-4-5@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.1
-output = 5.5
-cache_read = 0.11
-cache_write = 1.375
+input = 0.99
+output = 4.95
+cache_read = 0.099
+cache_write = 1.2375

providers/requesty/models/claude-opus-4-1.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 15
-output = 75
-cache_read = 1.5
-cache_write = 18.75
+input = 13.5
+output = 67.5
+cache_read = 1.35
+cache_write = 16.875

providers/requesty/models/claude-opus-4-5.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5
-output = 25
-cache_read = 0.5
-cache_write = 6.25
+input = 4.5
+output = 22.5
+cache_read = 0.45
+cache_write = 5.625

providers/requesty/models/claude-opus-4-5@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5.5
-output = 27.5
-cache_read = 0.55
-cache_write = 6.875
+input = 4.95
+output = 24.75
+cache_read = 0.495
+cache_write = 6.1875

providers/requesty/models/claude-opus-4-6.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5
-output = 25
-cache_read = 0.5
-cache_write = 6.25
+input = 4.5
+output = 22.5
+cache_read = 0.45
+cache_write = 5.625

providers/requesty/models/claude-opus-4-6@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5.5
-output = 27.5
-cache_read = 0.55
-cache_write = 6.875
+input = 4.95
+output = 24.75
+cache_read = 0.495
+cache_write = 6.1875

providers/requesty/models/claude-opus-4-7.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5
-output = 25
-cache_read = 0.5
-cache_write = 6.25
+input = 4.5
+output = 22.5
+cache_read = 0.45
+cache_write = 5.625

providers/requesty/models/claude-opus-4-7@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5.5
-output = 27.5
-cache_read = 0.55
-cache_write = 6.875
+input = 4.95
+output = 24.75
+cache_read = 0.495
+cache_write = 6.1875

providers/requesty/models/claude-opus-4-8.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5
-output = 25
-cache_read = 0.5
-cache_write = 6.25
+input = 4.5
+output = 22.5
+cache_read = 0.45
+cache_write = 5.625

providers/requesty/models/claude-opus-4-8@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5.5
-output = 27.5
-cache_read = 0.55
-cache_write = 6.875
+input = 4.95
+output = 24.75
+cache_read = 0.495
+cache_write = 6.1875

providers/requesty/models/claude-opus-5.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5
-output = 25
-cache_read = 0.5
-cache_write = 6.25
+input = 4.5
+output = 22.5
+cache_read = 0.45
+cache_write = 5.625

providers/requesty/models/claude-opus-5@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5.5
-output = 27.5
-cache_read = 0.55
-cache_write = 6.875
+input = 4.95
+output = 24.75
+cache_read = 0.495
+cache_write = 6.1875

providers/requesty/models/claude-sonnet-4-5.toml

@@ -9,17 +9,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 3
-output = 15
-cache_read = 0.3
-cache_write = 3.75
+input = 2.7
+output = 13.5
+cache_read = 0.27
+cache_write = 3.375
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 6
-output = 22.5
-cache_read = 0.6
-cache_write = 7.5
+input = 5.4
+output = 20.25
+cache_read = 0.54
+cache_write = 6.75
 
 [limit]
 context = 1_000_000

providers/requesty/models/claude-sonnet-4-5@eu.toml

@@ -10,17 +10,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 3.3
-output = 16.5
-cache_read = 0.3
-cache_write = 4.125
+input = 2.97
+output = 14.85
+cache_read = 0.27
+cache_write = 3.7125
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 6.6
-output = 24.75
-cache_read = 0.6
-cache_write = 8.25
+input = 5.94
+output = 22.275
+cache_read = 0.54
+cache_write = 7.425
 
 [limit]
 context = 1_000_000

providers/requesty/models/claude-sonnet-4-6.toml

@@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 3
-output = 15
-cache_read = 0.3
-cache_write = 3.75
+input = 2.7
+output = 13.5
+cache_read = 0.27
+cache_write = 3.375
 
 [limit]
 output = 128_000

providers/requesty/models/claude-sonnet-4-6@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 3.3
-output = 16.5
-cache_read = 0.3
-cache_write = 4.125
+input = 2.97
+output = 14.85
+cache_read = 0.27
+cache_write = 3.7125

providers/requesty/models/claude-sonnet-4@eu.toml

@@ -10,17 +10,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 3
-output = 15
-cache_read = 0.3
-cache_write = 3.75
+input = 2.7
+output = 13.5
+cache_read = 0.27
+cache_write = 3.375
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 6
-output = 22.5
-cache_read = 0.6
-cache_write = 7.5
+input = 5.4
+output = 20.25
+cache_read = 0.54
+cache_write = 6.75
 
 [limit]
 context = 1_000_000

providers/requesty/models/claude-sonnet-5.toml

@@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2
-output = 10
-cache_read = 0.2
-cache_write = 2.5
+input = 1.8
+output = 9
+cache_read = 0.18
+cache_write = 2.25

providers/requesty/models/claude-sonnet-5@eu.toml

@@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2.2
-output = 11
-cache_read = 0.22
-cache_write = 2.75
+input = 1.98
+output = 9.9
+cache_read = 0.198
+cache_write = 2.475

providers/requesty/models/deepseek-v4-flash-0731.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.14
-output = 0.28
-cache_read = 0.07
+input = 0.126
+output = 0.252
+cache_read = 0.063
 
 [limit]
 context = 1_048_576

providers/requesty/models/deepseek-v4-flash-0731@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.14
-output = 0.28
-cache_read = 0.07
+input = 0.126
+output = 0.252
+cache_read = 0.063
 
 [limit]
 context = 1_048_576

providers/requesty/models/deepseek-v4-flash.toml

@@ -3,6 +3,6 @@ reasoning = false
 structured_output = false
 
 [cost]
-input = 0.44
-output = 1.32
-cache_read = 0.014
+input = 0.396
+output = 1.188
+cache_read = 0.0126

providers/requesty/models/deepseek-v4-pro-0813.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.32
-output = 3.96
-cache_read = 0.044
+input = 1.188
+output = 3.564
+cache_read = 0.0396
 
 [limit]
 output = 131_072

providers/requesty/models/deepseek-v4-pro.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.32
-output = 3.96
-cache_read = 0.044
+input = 1.188
+output = 3.564
+cache_read = 0.0396

providers/requesty/models/deepseek-v4-pro@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.75
-output = 3.5
-cache_read = 0.44
+input = 1.575
+output = 3.15
+cache_read = 0.396
 
 [limit]
 context = 1_048_576

providers/requesty/models/devstral-latest.toml

@@ -10,9 +10,9 @@ structured_output = true
 open_weights = false
 
 [cost]
-input = 0.44
-output = 2.2
-cache_read = 0.44
+input = 0.396
+output = 1.98
+cache_read = 0.396
 
 [limit]
 context = 256_000

providers/requesty/models/devstral-latest@eu.toml

@@ -10,9 +10,9 @@ structured_output = true
 open_weights = false
 
 [cost]
-input = 0.44
-output = 2.2
-cache_read = 0.44
+input = 0.396
+output = 1.98
+cache_read = 0.396
 
 [limit]
 context = 256_000

providers/requesty/models/fugu-ultra.toml

@@ -3,15 +3,15 @@ reasoning = false
 structured_output = false
 
 [cost]
-input = 5
-output = 30
-cache_read = 0.5
+input = 4.5
+output = 27
+cache_read = 0.45
 
 [[cost.tiers]]
 tier = { type = "context", size = 272_000 }
-input = 10
-output = 45
-cache_read = 1
+input = 9
+output = 40.5
+cache_read = 0.9
 
 [limit]
 context = 1_048_576

providers/requesty/models/gemini-2.5-flash@eu.toml

@@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.3
-output = 2.5
-cache_read = 0.075
-cache_write = 0.55
+input = 0.27
+output = 2.25
+cache_read = 0.0675
+cache_write = 0.495
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3-pro-image.toml

@@ -10,17 +10,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2
-output = 12
-cache_read = 0.2
-cache_write = 4.5
+input = 1.8
+output = 10.8
+cache_read = 0.18
+cache_write = 4.05
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 4
-output = 18
-cache_read = 0.2
-cache_write = 4.5
+input = 3.6
+output = 16.2
+cache_read = 0.18
+cache_write = 4.05
 
 [limit]
 context = 1_048_576

providers/requesty/models/gemini-3.1-flash-image.toml

@@ -10,10 +10,10 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.5
-output = 2
+input = 0.45
+output = 1.8
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 0.5
-output = 2
+input = 0.45
+output = 1.8

providers/requesty/models/gemini-3.1-flash-lite.toml

@@ -8,17 +8,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.25
-output = 1.5
-cache_read = 0.025
-cache_write = 0.08333
+input = 0.225
+output = 1.35
+cache_read = 0.0225
+cache_write = 0.074997
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 0.5
-output = 2.25
-cache_read = 0.025
-cache_write = 0.08333
+input = 0.45
+output = 2.025
+cache_read = 0.0225
+cache_write = 0.074997
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.1-flash-lite@eu.toml

@@ -9,17 +9,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.275
-output = 1.65
-cache_read = 0.0275
-cache_write = 0.091663
+input = 0.2475
+output = 1.485
+cache_read = 0.02475
+cache_write = 0.082497
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 0.55
-output = 2.475
-cache_read = 0.0275
-cache_write = 0.091663
+input = 0.495
+output = 2.2275
+cache_read = 0.02475
+cache_write = 0.082497
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.1-pro-preview.toml

@@ -8,17 +8,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2
-output = 12
-cache_read = 0.2
-cache_write = 4.5
+input = 1.8
+output = 10.8
+cache_read = 0.18
+cache_write = 4.05
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 4
-output = 18
-cache_read = 0.2
-cache_write = 4.5
+input = 3.6
+output = 16.2
+cache_read = 0.18
+cache_write = 4.05
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.5-flash-lite.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.3
-output = 2.5
-cache_read = 0.03
+input = 0.27
+output = 2.25
+cache_read = 0.027
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.5-flash-lite@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.33
-output = 2.75
-cache_read = 0.033
+input = 0.297
+output = 2.475
+cache_read = 0.0297
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.5-flash.toml

@@ -8,10 +8,10 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.5
-output = 9
-cache_read = 0.15
-cache_write = 1.583
+input = 1.35
+output = 8.1
+cache_read = 0.135
+cache_write = 1.4247
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.5-flash@eu.toml

@@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.65
-output = 9.9
-cache_read = 0.165
-cache_write = 1.7413
+input = 1.485
+output = 8.91
+cache_read = 0.1485
+cache_write = 1.56717
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.6-flash.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.5
-output = 7
-cache_read = 0.15
+input = 1.35
+output = 6.3
+cache_read = 0.135
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.7-flash.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.75
-output = 3.75
-cache_read = 0.075
+input = 0.6
+output = 3
+cache_read = 0.06
 
 [limit]
 output = 65_535

providers/requesty/models/gemini-3.7-flash@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.825
-output = 4.125
-cache_read = 0.0825
+input = 0.66
+output = 3.3
+cache_read = 0.066
 
 [limit]
 output = 65_535

providers/requesty/models/gemma-4-26b-a4b-it.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.07
-output = 0.34
-cache_read = 0.07
+input = 0.063
+output = 0.306
+cache_read = 0.063
 
 [limit]
 output = 262_144

providers/requesty/models/glm-5.1.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.4
-output = 4.4
-cache_read = 0.26
+input = 1.26
+output = 3.96
+cache_read = 0.234
 
 [limit]
 output = 128_000

providers/requesty/models/glm-5.1@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.4
-output = 4.4
-cache_read = 1.4
+input = 1.26
+output = 3.96
+cache_read = 1.26
 
 [limit]
 output = 200_000

providers/requesty/models/glm-5.2-fast.toml

@@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2.1
-output = 6.6
-cache_read = 0.21
+input = 1.89
+output = 5.94
+cache_read = 0.189
 
 [limit]
 context = 1_000_000

providers/requesty/models/glm-5.2.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.2
-output = 4.2
-cache_read = 0.26
+input = 1.08
+output = 3.78
+cache_read = 0.234
 
 [limit]
 context = 1_048_576

providers/requesty/models/glm-5.2@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.2
-output = 4.2
-cache_read = 0.26
+input = 1.08
+output = 3.78
+cache_read = 0.234
 
 [limit]
 context = 1_048_576

providers/requesty/models/glm-5.3.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.4
-output = 4.4
-cache_read = 0.26
+input = 1.26
+output = 3.96
+cache_read = 0.234
 
 [limit]
 output = 128_000

providers/requesty/models/gpt-4.1-mini@eu.toml

@@ -2,6 +2,6 @@ base_model = "openai/gpt-4.1-mini"
 name = "GPT-4.1 mini (EU)"
 
 [cost]
-input = 0.44
-output = 1.76
-cache_read = 0.11
+input = 0.396
+output = 1.584
+cache_read = 0.099

providers/requesty/models/gpt-4.1-nano@eu.toml

@@ -2,6 +2,6 @@ base_model = "openai/gpt-4.1-nano"
 name = "GPT-4.1 nano (EU)"
 
 [cost]
-input = 0.11
-output = 0.44
-cache_read = 0.0275
+input = 0.099
+output = 0.396
+cache_read = 0.02475

providers/requesty/models/gpt-4.1@eu.toml

@@ -2,6 +2,6 @@ base_model = "openai/gpt-4.1"
 name = "GPT-4.1 (EU)"
 
 [cost]
-input = 2.2
-output = 8.8
-cache_read = 0.55
+input = 1.98
+output = 7.92
+cache_read = 0.495

providers/requesty/models/gpt-4o-mini@eu.toml

@@ -2,9 +2,9 @@ base_model = "openai/gpt-4o-mini"
 name = "GPT-4o mini (EU)"
 
 [cost]
-input = 0.165
-output = 0.66
-cache_read = 0.0825
+input = 0.1485
+output = 0.594
+cache_read = 0.07425
 
 [limit]
 output = 16_000

providers/requesty/models/gpt-5-mini@eu.toml

@@ -10,9 +10,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.275
-output = 2.2
-cache_read = 0.0275
+input = 0.2475
+output = 1.98
+cache_read = 0.02475
 
 [limit]
 context = 200_000

providers/requesty/models/gpt-5-nano@eu.toml

@@ -10,9 +10,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.055
-output = 0.44
-cache_read = 0.0055
+input = 0.0495
+output = 0.396
+cache_read = 0.00495
 
 [limit]
 context = 200_000

providers/requesty/models/gpt-5.1@eu.toml

@@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.375
-output = 11
-cache_read = 0.1375
+input = 1.2375
+output = 9.9
+cache_read = 0.12375

providers/requesty/models/gpt-5.3-chat.toml

@@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.75
-output = 14
-cache_read = 0.175
+input = 1.575
+output = 12.6
+cache_read = 0.1575
 
 [limit]
 context = 128_000

providers/requesty/models/gpt-5.3-codex.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.75
-output = 14
-cache_read = 0.175
+input = 1.575
+output = 12.6
+cache_read = 0.1575

providers/requesty/models/gpt-5.4-mini.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.75
-output = 4.5
-cache_read = 0.075
+input = 0.675
+output = 4.05
+cache_read = 0.0675

providers/requesty/models/gpt-5.4-nano.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.2
-output = 1.25
-cache_read = 0.02
+input = 0.18
+output = 1.125
+cache_read = 0.018

providers/requesty/models/gpt-5.4-pro.toml

@@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 30
-output = 180
-cache_read = 30
+input = 27
+output = 162
+cache_read = 27

providers/requesty/models/gpt-5.4.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2.75
-output = 16.5
-cache_read = 0.275
+input = 2.475
+output = 14.85
+cache_read = 0.2475

providers/requesty/models/gpt-5.4@eu.toml

@@ -9,12 +9,12 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2.5
-output = 15
-cache_read = 0.25
+input = 2.25
+output = 13.5
+cache_read = 0.225
 
 [[cost.tiers]]
 tier = { type = "context", size = 272_000 }
-input = 5
-output = 22.5
-cache_read = 0.5
+input = 4.5
+output = 20.25
+cache_read = 0.45

providers/requesty/models/gpt-5.5-pro.toml

@@ -8,5 +8,5 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 30
-output = 180
+input = 27
+output = 162

providers/requesty/models/gpt-5.5.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5.5
-output = 33
-cache_read = 0.55
+input = 4.95
+output = 29.7
+cache_read = 0.495

providers/requesty/models/gpt-5.5@eu.toml

@@ -9,12 +9,12 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5
-output = 30
-cache_read = 0.5
+input = 4.5
+output = 27
+cache_read = 0.45
 
 [[cost.tiers]]
 tier = { type = "context", size = 272_000 }
-input = 10
-output = 45
-cache_read = 1
+input = 9
+output = 40.5
+cache_read = 0.9

providers/requesty/models/gpt-5.6-luna.toml

@@ -8,12 +8,12 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.2
-output = 1.2
-cache_read = 0.02
+input = 0.18
+output = 1.08
+cache_read = 0.018
 
 [[cost.tiers]]
 tier = { type = "context", size = 272_000 }
-input = 0.4
-output = 1.8
-cache_read = 0.04
+input = 0.36
+output = 1.62
+cache_read = 0.036

providers/requesty/models/gpt-5.6-luna@eu.toml

@@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.22
-output = 1.32
-cache_read = 0.022
+input = 0.198
+output = 1.188
+cache_read = 0.0198

providers/requesty/models/gpt-5.6-sol.toml

@@ -8,12 +8,12 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5
-output = 30
-cache_read = 0.5
+input = 4.5
+output = 27
+cache_read = 0.45
 
 [[cost.tiers]]
 tier = { type = "context", size = 272_000 }
-input = 10
-output = 45
-cache_read = 1
+input = 9
+output = 40.5
+cache_read = 0.9

providers/requesty/models/gpt-5.6-sol@eu.toml

@@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 5.5
-output = 33
-cache_read = 0.55
+input = 4.95
+output = 29.7
+cache_read = 0.495

providers/requesty/models/gpt-5.6-terra.toml

@@ -8,12 +8,12 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2
-output = 12
-cache_read = 0.2
+input = 1.8
+output = 10.8
+cache_read = 0.18
 
 [[cost.tiers]]
 tier = { type = "context", size = 272_000 }
-input = 4
-output = 18
-cache_read = 0.4
+input = 3.6
+output = 16.2
+cache_read = 0.36

providers/requesty/models/gpt-5.6-terra@eu.toml

@@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2.2
-output = 13.2
-cache_read = 0.22
+input = 1.98
+output = 11.88
+cache_read = 0.198

providers/requesty/models/gpt-5@eu.toml

@@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.375
-output = 11
-cache_read = 0.1375
+input = 1.2375
+output = 9.9
+cache_read = 0.12375

providers/requesty/models/grok-4.2-beta.toml

@@ -17,17 +17,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2
-output = 6
-cache_read = 0.2
-cache_write = 2
+input = 1.8
+output = 5.4
+cache_read = 0.18
+cache_write = 1.8
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 4
-output = 12
-cache_read = 0.4
-cache_write = 4
+input = 3.6
+output = 10.8
+cache_read = 0.36
+cache_write = 3.6
 
 [limit]
 context = 2_000_000

providers/requesty/models/grok-4.3.toml

@@ -8,17 +8,17 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.25
-output = 2.5
-cache_read = 0.2
-cache_write = 1.25
+input = 1.125
+output = 2.25
+cache_read = 0.18
+cache_write = 1.125
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 2.5
-output = 5
-cache_read = 0.4
-cache_write = 2.5
+input = 2.25
+output = 4.5
+cache_read = 0.36
+cache_write = 2.25
 
 [limit]
 output = 1_000_000

providers/requesty/models/grok-4.5.toml

@@ -8,14 +8,14 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2
-output = 6
-cache_read = 0.5
-cache_write = 2
+input = 1.8
+output = 5.4
+cache_read = 0.45
+cache_write = 1.8
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 4
-output = 12
-cache_read = 1
-cache_write = 4
+input = 3.6
+output = 10.8
+cache_read = 0.9
+cache_write = 3.6

providers/requesty/models/grok-4.6.toml

@@ -8,14 +8,14 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2
-output = 6
-cache_read = 0.5
-cache_write = 2
+input = 1.8
+output = 5.4
+cache_read = 0.45
+cache_write = 1.8
 
 [[cost.tiers]]
 tier = { type = "context", size = 200_000 }
-input = 4
-output = 12
-cache_read = 1
-cache_write = 4
+input = 3.6
+output = 10.8
+cache_read = 0.9
+cache_write = 3.6

providers/requesty/models/grok-build-0.1.toml

@@ -2,6 +2,6 @@ base_model = "xai/grok-build-0.1"
 reasoning = false
 
 [cost]
-input = 1
-output = 2
-cache_read = 0.1
+input = 0.9
+output = 1.8
+cache_read = 0.09

providers/requesty/models/hy3.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.14
-output = 0.58
-cache_read = 0.035
+input = 0.126
+output = 0.522
+cache_read = 0.0315
 
 [limit]
 context = 262_144

providers/requesty/models/inkling-256k.toml

@@ -16,9 +16,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.87
-output = 4.68
-cache_read = 0.374
+input = 1.496
+output = 3.744
+cache_read = 0.2992
 
 [limit]
 context = 262_144

providers/requesty/models/inkling.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.87
-output = 4.68
-cache_read = 0.374
+input = 1.683
+output = 4.212
+cache_read = 0.3366
 
 [limit]
 context = 65_536

providers/requesty/models/kat-coder-pro.toml

@@ -10,8 +10,8 @@ structured_output = false
 open_weights = false
 
 [cost]
-input = 0.3
-output = 1.2
+input = 0.27
+output = 1.08
 
 [limit]
 context = 256_000

providers/requesty/models/kimi-k2.6.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.95
-output = 4
-cache_read = 0.16
+input = 0.855
+output = 3.6
+cache_read = 0.144

providers/requesty/models/kimi-k2.6@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.95
-output = 4
-cache_read = 0.95
+input = 0.855
+output = 3.6
+cache_read = 0.855
 
 [limit]
 context = 256_000

providers/requesty/models/kimi-k2.7-code.toml

@@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.95
-output = 4
-cache_read = 0.19
+input = 0.855
+output = 3.6
+cache_read = 0.171

providers/requesty/models/kimi-k2.7-code@eu.toml

@@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.25
-output = 4.5
-cache_read = 0.31
+input = 1.125
+output = 4.05
+cache_read = 0.279

providers/requesty/models/kimi-k3.toml

@@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2.25
-output = 11.25
-cache_read = 0.225
+input = 2.025
+output = 10.125
+cache_read = 0.2025
 
 [limit]
 output = 262_144

providers/requesty/models/kimi-k3@eu.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 2.25
-output = 11.25
-cache_read = 0.225
+input = 2.025
+output = 10.125
+cache_read = 0.2025
 
 [limit]
 output = 262_144

providers/requesty/models/ling-2.6-1t.toml

@@ -10,8 +10,8 @@ structured_output = false
 open_weights = false
 
 [cost]
-input = 0.3
-output = 2.5
+input = 0.27
+output = 2.25
 
 [limit]
 context = 262_144

providers/requesty/models/ling-2.6-flash.toml

@@ -10,8 +10,8 @@ structured_output = false
 open_weights = false
 
 [cost]
-input = 0.1
-output = 0.3
+input = 0.09
+output = 0.27
 
 [limit]
 context = 262_144

providers/requesty/models/mimo-v2.5-pro.toml

@@ -3,6 +3,6 @@ reasoning = false
 structured_output = false
 
 [cost]
-input = 0.435
-output = 0.87
-cache_read = 0.0036
+input = 0.3915
+output = 0.783
+cache_read = 0.00324

providers/requesty/models/mimo-v2.5.toml

@@ -3,6 +3,6 @@ reasoning = false
 structured_output = false
 
 [cost]
-input = 0.14
-output = 0.28
-cache_read = 0.0028
+input = 0.126
+output = 0.252
+cache_read = 0.00252

providers/requesty/models/minimax-m2.7-highspeed.toml

@@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.6
-output = 2.4
-cache_read = 0.06
-cache_write = 1.2
+input = 0.54
+output = 2.16
+cache_read = 0.054
+cache_write = 1.08
 
 [limit]
 context = 200_000

providers/requesty/models/minimax-m2.7.toml

@@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.3
-output = 1.2
-cache_read = 0.06
-cache_write = 1.2
+input = 0.27
+output = 1.08
+cache_read = 0.054
+cache_write = 1.08
 
 [limit]
 context = 200_000

providers/requesty/models/minimax-m3.toml

@@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.3
-output = 1.2
-cache_read = 0.06
+input = 0.24
+output = 0.96
+cache_read = 0.048
 
 [limit]
 context = 1_000_000

providers/requesty/models/minimax-m3@eu.toml

@@ -10,9 +10,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 0.4
-output = 2
-cache_read = 0.1
+input = 0.36
+output = 1.8
+cache_read = 0.09
 
 [limit]
 context = 1_048_576

providers/requesty/models/mistral-medium-3-5.toml

@@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.65
-output = 8.25
-cache_read = 1.65
+input = 1.485
+output = 7.425
+cache_read = 1.485
 
 [limit]
 context = 262_144

providers/requesty/models/mistral-medium-3-5@eu.toml

@@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"]
 type = "budget_tokens"
 
 [cost]
-input = 1.65
-output = 8.25
-cache_read = 1.65
+input = 1.485
+output = 7.425
+cache_read = 1.485
 
 [limit]
 context = 262_144