chore: import upstream snapshot with attribution
This commit is contained in:
@@ -0,0 +1,12 @@
|
||||
base_model = "anthropic/claude-fable-5"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 10
|
||||
output = 50
|
||||
cache_read = 1
|
||||
cache_write = 12.5
|
||||
|
||||
[limit]
|
||||
context = 1_000_000
|
||||
output = 128_000
|
||||
@@ -0,0 +1,11 @@
|
||||
base_model = "anthropic/claude-haiku-4-5"
|
||||
reasoning_options = [{ type = "budget_tokens", min = 1_024, max = 32_000 }]
|
||||
|
||||
[cost]
|
||||
input = 1
|
||||
output = 5
|
||||
cache_read = 0.1
|
||||
cache_write = 1.25
|
||||
|
||||
[limit]
|
||||
input = 136_000
|
||||
@@ -0,0 +1,12 @@
|
||||
base_model = "anthropic/claude-opus-4-5"
|
||||
reasoning_options = [{ type = "budget_tokens", min = 1_024, max = 32_000 }]
|
||||
|
||||
[cost]
|
||||
input = 5
|
||||
output = 25
|
||||
cache_read = 0.5
|
||||
cache_write = 6.25
|
||||
|
||||
[limit]
|
||||
input = 168_000
|
||||
output = 32_000
|
||||
@@ -0,0 +1,17 @@
|
||||
base_model = "anthropic/claude-opus-4-6"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 5
|
||||
output = 25
|
||||
cache_read = 0.5
|
||||
cache_write = 6.25
|
||||
|
||||
[limit]
|
||||
context = 200_000
|
||||
input = 168_000
|
||||
output = 32_000
|
||||
|
||||
[experimental.modes.fast]
|
||||
cost = { input = 30, output = 150, cache_read = 3, cache_write = 37.5 }
|
||||
provider = { body = { speed = "fast" }, headers = { anthropic-beta = "fast-mode-2026-02-01" } }
|
||||
@@ -0,0 +1,17 @@
|
||||
base_model = "anthropic/claude-opus-4-7"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 5
|
||||
output = 25
|
||||
cache_read = 0.5
|
||||
cache_write = 6.25
|
||||
|
||||
[limit]
|
||||
context = 200_000
|
||||
input = 168_000
|
||||
output = 32_000
|
||||
|
||||
[experimental.modes.fast]
|
||||
cost = { input = 30, output = 150, cache_read = 3, cache_write = 37.5 }
|
||||
provider = { body = { speed = "fast" }, headers = { anthropic-beta = "fast-mode-2026-02-01" } }
|
||||
@@ -0,0 +1,17 @@
|
||||
base_model = "anthropic/claude-opus-4-8"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 5
|
||||
output = 25
|
||||
cache_read = 0.5
|
||||
cache_write = 6.25
|
||||
|
||||
[limit]
|
||||
context = 200_000
|
||||
input = 168_000
|
||||
output = 64_000
|
||||
|
||||
[experimental.modes.fast]
|
||||
cost = { input = 10, output = 50, cache_read = 1, cache_write = 12.5 }
|
||||
provider = { body = { speed = "fast" }, headers = { anthropic-beta = "fast-mode-2026-02-01" } }
|
||||
@@ -0,0 +1,12 @@
|
||||
base_model = "anthropic/claude-sonnet-4-5"
|
||||
reasoning_options = [{ type = "budget_tokens", min = 1_024, max = 32_000 }]
|
||||
|
||||
[cost]
|
||||
input = 3
|
||||
output = 15
|
||||
cache_read = 0.3
|
||||
cache_write = 3.75
|
||||
|
||||
[limit]
|
||||
input = 168_000
|
||||
output = 32_000
|
||||
@@ -0,0 +1,13 @@
|
||||
base_model = "anthropic/claude-sonnet-4-6"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "max"] }, { type = "budget_tokens", min = 1_024, max = 32_000 }]
|
||||
|
||||
[cost]
|
||||
input = 3
|
||||
output = 15
|
||||
cache_read = 0.3
|
||||
cache_write = 3.75
|
||||
|
||||
[limit]
|
||||
context = 200_000
|
||||
input = 168_000
|
||||
output = 32_000
|
||||
@@ -0,0 +1,13 @@
|
||||
base_model = "anthropic/claude-sonnet-4-0"
|
||||
reasoning_options = []
|
||||
|
||||
[cost]
|
||||
input = 3
|
||||
output = 15
|
||||
cache_read = 0.3
|
||||
cache_write = 3.75
|
||||
|
||||
[limit]
|
||||
context = 216_000
|
||||
input = 128_000
|
||||
output = 16_000
|
||||
@@ -0,0 +1,12 @@
|
||||
base_model = "anthropic/claude-sonnet-5"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 2
|
||||
output = 10
|
||||
cache_read = 0.2
|
||||
cache_write = 2.5
|
||||
|
||||
[limit]
|
||||
context = 1_000_000
|
||||
output = 128_000
|
||||
@@ -0,0 +1,12 @@
|
||||
base_model = "google/gemini-2.5-pro"
|
||||
reasoning_options = [{ type = "budget_tokens", min = 128, max = 32_768 }]
|
||||
|
||||
[cost]
|
||||
input = 1.25
|
||||
output = 10
|
||||
cache_read = 0.125
|
||||
|
||||
[limit]
|
||||
context = 128_000
|
||||
input = 128_000
|
||||
output = 64_000
|
||||
@@ -0,0 +1,13 @@
|
||||
base_model = "google/gemini-3-flash-preview"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }, { type = "budget_tokens", min = 256, max = 32_000 }]
|
||||
|
||||
[cost]
|
||||
input = 0.5
|
||||
output = 3
|
||||
cache_read = 0.05
|
||||
input_audio = 1
|
||||
|
||||
[limit]
|
||||
context = 128_000
|
||||
input = 128_000
|
||||
output = 64_000
|
||||
@@ -0,0 +1,18 @@
|
||||
base_model = "google/gemini-3.1-pro-preview"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }, { type = "budget_tokens", min = 256, max = 32_000 }]
|
||||
|
||||
[cost]
|
||||
input = 2
|
||||
output = 12
|
||||
cache_read = 0.2
|
||||
|
||||
[[cost.tiers]]
|
||||
tier = { type = "context", size = 200_000 }
|
||||
input = 4
|
||||
output = 18
|
||||
cache_read = 0.4
|
||||
|
||||
[limit]
|
||||
context = 1_000_000
|
||||
input = 936_000
|
||||
output = 64_000
|
||||
@@ -0,0 +1,13 @@
|
||||
base_model = "google/gemini-3.5-flash"
|
||||
reasoning_options = [{ type = "effort", values = ["minimal", "low", "medium", "high"] }, { type = "budget_tokens", min = 256, max = 24_000 }]
|
||||
|
||||
[cost]
|
||||
input = 1.5
|
||||
output = 9
|
||||
cache_read = 0.15
|
||||
input_audio = 1.5
|
||||
|
||||
[limit]
|
||||
context = 200_000
|
||||
input = 128_000
|
||||
output = 64_000
|
||||
@@ -0,0 +1,11 @@
|
||||
base_model = "openai/gpt-4.1"
|
||||
|
||||
[cost]
|
||||
input = 2
|
||||
output = 8
|
||||
cache_read = 0.5
|
||||
|
||||
[limit]
|
||||
context = 128_000
|
||||
input = 128_000
|
||||
output = 16_384
|
||||
@@ -0,0 +1,12 @@
|
||||
base_model = "openai/gpt-5-mini"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
|
||||
|
||||
[cost]
|
||||
input = 0.25
|
||||
output = 2
|
||||
cache_read = 0.025
|
||||
|
||||
[limit]
|
||||
context = 264_000
|
||||
input = 128_000
|
||||
output = 64_000
|
||||
@@ -0,0 +1,7 @@
|
||||
base_model = "openai/gpt-5.2-codex"
|
||||
reasoning_options = []
|
||||
|
||||
[cost]
|
||||
input = 1.75
|
||||
output = 14
|
||||
cache_read = 0.175
|
||||
@@ -0,0 +1,7 @@
|
||||
base_model = "openai/gpt-5.2"
|
||||
reasoning_options = []
|
||||
|
||||
[cost]
|
||||
input = 1.75
|
||||
output = 14
|
||||
cache_read = 0.175
|
||||
@@ -0,0 +1,7 @@
|
||||
base_model = "openai/gpt-5.3-codex"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "xhigh"] }]
|
||||
|
||||
[cost]
|
||||
input = 1.75
|
||||
output = 14
|
||||
cache_read = 0.175
|
||||
@@ -0,0 +1,7 @@
|
||||
base_model = "openai/gpt-5.4-mini"
|
||||
reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "xhigh"] }]
|
||||
|
||||
[cost]
|
||||
input = 0.75
|
||||
output = 4.5
|
||||
cache_read = 0.075
|
||||
@@ -0,0 +1,7 @@
|
||||
base_model = "openai/gpt-5.4-nano"
|
||||
reasoning_options = []
|
||||
|
||||
[cost]
|
||||
input = 0.2
|
||||
output = 1.25
|
||||
cache_read = 0.02
|
||||
@@ -0,0 +1,17 @@
|
||||
base_model = "openai/gpt-5.4"
|
||||
reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "xhigh"] }]
|
||||
|
||||
[cost]
|
||||
input = 2.5
|
||||
output = 15
|
||||
cache_read = 0.25
|
||||
|
||||
[[cost.tiers]]
|
||||
tier = { type = "context", size = 272_000 }
|
||||
input = 5
|
||||
output = 22.5
|
||||
cache_read = 0.5
|
||||
|
||||
[limit]
|
||||
context = 1_050_000
|
||||
input = 922_000
|
||||
@@ -0,0 +1,17 @@
|
||||
base_model = "openai/gpt-5.5"
|
||||
reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "xhigh"] }]
|
||||
|
||||
[cost]
|
||||
input = 5
|
||||
output = 30
|
||||
cache_read = 0.5
|
||||
|
||||
[[cost.tiers]]
|
||||
tier = { type = "context", size = 272_000 }
|
||||
input = 10
|
||||
output = 45
|
||||
cache_read = 1
|
||||
|
||||
[limit]
|
||||
context = 1_050_000
|
||||
input = 922_000
|
||||
@@ -0,0 +1,13 @@
|
||||
base_model = "openai/gpt-5.6-luna"
|
||||
reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "xhigh", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 1
|
||||
output = 6
|
||||
cache_read = 0.1
|
||||
|
||||
[[cost.tiers]]
|
||||
tier = { type = "context", size = 200_000 }
|
||||
input = 2
|
||||
output = 9
|
||||
cache_read = 0.2
|
||||
@@ -0,0 +1,13 @@
|
||||
base_model = "openai/gpt-5.6-sol"
|
||||
reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "xhigh", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 5
|
||||
output = 30
|
||||
cache_read = 0.5
|
||||
|
||||
[[cost.tiers]]
|
||||
tier = { type = "context", size = 272_000 }
|
||||
input = 10
|
||||
output = 45
|
||||
cache_read = 1
|
||||
@@ -0,0 +1,13 @@
|
||||
base_model = "openai/gpt-5.6-terra"
|
||||
reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "xhigh", "max"] }]
|
||||
|
||||
[cost]
|
||||
input = 2.5
|
||||
output = 15
|
||||
cache_read = 0.25
|
||||
|
||||
[[cost.tiers]]
|
||||
tier = { type = "context", size = 272_000 }
|
||||
input = 5
|
||||
output = 22.5
|
||||
cache_read = 0.5
|
||||
@@ -0,0 +1,16 @@
|
||||
base_model = "moonshotai/kimi-k2.7-code"
|
||||
reasoning_options = []
|
||||
|
||||
[cost]
|
||||
input = 0.95
|
||||
output = 4.0
|
||||
cache_read = 0.19
|
||||
|
||||
[limit]
|
||||
context = 256_000
|
||||
input = 224_000
|
||||
output = 32_000
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,12 @@
|
||||
base_model = "microsoft/mai-code-1-flash"
|
||||
reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
|
||||
|
||||
[cost]
|
||||
input = 0.75
|
||||
output = 4.5
|
||||
cache_read = 0.075
|
||||
|
||||
[limit]
|
||||
context = 256_000
|
||||
input = 128_000
|
||||
output = 128_000
|
||||
Reference in New Issue
Block a user