chore: import upstream snapshot with attribution

2026-07-13 12:28:55 +08:00
commit db42b91b75
6397 changed files with 146012 additions and 0 deletions
@@ -0,0 +1,8 @@
+base_model = "anthropic/claude-haiku-4-5"
+reasoning_options = []
+
+[cost]
+input = 1
+output = 5
+cache_read = 0.1
+cache_write = 1.25
@@ -0,0 +1,8 @@
+base_model = "anthropic/claude-opus-4-1"
+reasoning_options = []
+
+[cost]
+input = 15
+output = 75
+cache_read = 1.5
+cache_write = 18.75
@@ -0,0 +1,8 @@
+base_model = "anthropic/claude-opus-4-5"
+reasoning_options = []
+
+[cost]
+input = 5
+output = 25
+cache_read = 0.5
+cache_write = 6.25
@@ -0,0 +1,12 @@
+base_model = "anthropic/claude-opus-4-6"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 5
+output = 25
+cache_read = 0.5
+cache_write = 6.25
+
+[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 +1,12 @@
+base_model = "anthropic/claude-opus-4-7"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 5
+output = 25
+cache_read = 0.5
+cache_write = 6.25
+
+[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 +1,8 @@
+base_model = "anthropic/claude-opus-4-0"
+reasoning_options = []
+
+[cost]
+input = 15
+output = 75
+cache_read = 1.5
+cache_write = 18.75
@@ -0,0 +1,8 @@
+base_model = "anthropic/claude-sonnet-4-5"
+reasoning_options = []
+
+[cost]
+input = 3
+output = 15
+cache_read = 0.3
+cache_write = 3.75
@@ -0,0 +1,8 @@
+base_model = "anthropic/claude-sonnet-4-6"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 3
+output = 15
+cache_read = 0.3
+cache_write = 3.75
@@ -0,0 +1,8 @@
+base_model = "anthropic/claude-sonnet-4-0"
+reasoning_options = []
+
+[cost]
+input = 3
+output = 15
+cache_read = 0.3
+cache_write = 3.75
@@ -0,0 +1,6 @@
+base_model = "deepseek/deepseek-chat"
+
+[cost]
+input = 0.14
+output = 0.28
+cache_read = 0.028
@@ -0,0 +1,10 @@
+base_model = "deepseek/deepseek-reasoner"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.435
+output = 0.87
+cache_read = 0.028
@@ -0,0 +1,10 @@
+base_model = "deepseek/deepseek-v4-flash"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.19
+output = 0.37
+cache_read = 0.0028
@@ -0,0 +1,10 @@
+base_model = "deepseek/deepseek-v4-pro"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.56
+output = 1.12
+cache_read = 0.003625
@@ -0,0 +1,8 @@
+base_model = "google/gemini-2.5-flash-lite"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 0.1
+output = 0.4
+cache_read = 0.01
+input_audio = 0.3
@@ -0,0 +1,8 @@
+base_model = "google/gemini-2.5-flash"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 0.3
+output = 2.5
+cache_read = 0.03
+input_audio = 1
@@ -0,0 +1,13 @@
+base_model = "google/gemini-2.5-pro"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 2.5
+output = 15
+cache_read = 0.125
+
+[[cost.tiers]]
+tier = { type = "context", size = 200_000 }
+input = 2.5
+output = 15
+cache_read = 0.25
@@ -0,0 +1,8 @@
+base_model = "google/gemini-3-flash-preview"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 0.5
+output = 3
+cache_read = 0.05
+input_audio = 1
@@ -0,0 +1,13 @@
+base_model = "google/gemini-3-pro-preview"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 4
+output = 18
+cache_read = 0.2
+
+[[cost.tiers]]
+tier = { type = "context", size = 200_000 }
+input = 4
+output = 18
+cache_read = 0.4
@@ -0,0 +1,8 @@
+base_model = "google/gemini-3.1-flash-lite-preview"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 0.25
+output = 1.5
+cache_read = 0.025
+input_audio = 0.5
@@ -0,0 +1,13 @@
+base_model = "google/gemini-3.1-pro-preview-customtools"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 4
+output = 18
+cache_read = 0.2
+
+[[cost.tiers]]
+tier = { type = "context", size = 200_000 }
+input = 4
+output = 18
+cache_read = 0.4
@@ -0,0 +1,13 @@
+base_model = "google/gemini-3.1-pro-preview"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 4
+output = 18
+cache_read = 0.2
+
+[[cost.tiers]]
+tier = { type = "context", size = 200_000 }
+input = 4
+output = 18
+cache_read = 0.4
@@ -0,0 +1,8 @@
+base_model = "google/gemini-flash-latest"
+reasoning_options = []
+
+[cost]
+input = 0.5
+output = 3
+cache_read = 0.075
+input_audio = 1
@@ -0,0 +1,7 @@
+base_model = "google/gemini-flash-lite-latest"
+reasoning_options = []
+
+[cost]
+input = 0.25
+output = 1.5
+cache_read = 0.025
@@ -0,0 +1,6 @@
+base_model = "google/gemma-4-26b-a4b-it"
+reasoning_options = []
+
+[cost]
+input = 0.06
+output = 0.33
@@ -0,0 +1,6 @@
+base_model = "google/gemma-4-31b-it"
+reasoning_options = []
+
+[cost]
+input = 0.13
+output = 0.38
@@ -0,0 +1,13 @@
+base_model = "xai/grok-4.3"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 2.5
+cache_read = 0.2
+
+[[cost.tiers]]
+tier = { type = "context", size = 200_000 }
+input = 2.5
+output = 5
+cache_read = 0.4
@@ -0,0 +1,10 @@
+base_model = "moonshotai/kimi-k2.5"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.6
+output = 3
+cache_read = 0.1
@@ -0,0 +1,10 @@
+base_model = "moonshotai/kimi-k2.6"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.95
+output = 4
+cache_read = 0.16
@@ -0,0 +1,8 @@
+base_model = "minimax/MiniMax-M2.5-highspeed"
+reasoning_options = []
+
+[cost]
+input = 0.6
+output = 2.4
+cache_read = 0.06
+cache_write = 0.375
@@ -0,0 +1,8 @@
+base_model = "minimax/MiniMax-M2.5"
+reasoning_options = []
+
+[cost]
+input = 0.3
+output = 1.2
+cache_read = 0.03
+cache_write = 0.375
@@ -0,0 +1,8 @@
+base_model = "minimax/MiniMax-M2.7-highspeed"
+reasoning_options = []
+
+[cost]
+input = 0.6
+output = 2.4
+cache_read = 0.06
+cache_write = 0.375
@@ -0,0 +1,8 @@
+base_model = "minimax/MiniMax-M2.7"
+reasoning_options = []
+
+[cost]
+input = 0.3
+output = 1.2
+cache_read = 0.06
+cache_write = 0.375
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-3.5-turbo"
+
+[cost]
+input = 0.5
+output = 1.5
+cache_read = 0
@@ -0,0 +1,5 @@
+base_model = "openai/gpt-4-turbo"
+
+[cost]
+input = 10
+output = 30
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4.1-mini"
+
+[cost]
+input = 0.4
+output = 1.6
+cache_read = 0.1
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4.1-nano"
+
+[cost]
+input = 0.1
+output = 0.4
+cache_read = 0.025
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4.1"
+
+[cost]
+input = 2
+output = 8
+cache_read = 0.5
@@ -0,0 +1,5 @@
+base_model = "openai/gpt-4"
+
+[cost]
+input = 30
+output = 60
@@ -0,0 +1,5 @@
+base_model = "openai/gpt-4o-2024-05-13"
+
+[cost]
+input = 5
+output = 15
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4o-2024-08-06"
+
+[cost]
+input = 2.5
+output = 10
+cache_read = 1.25
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4o-2024-11-20"
+
+[cost]
+input = 2.5
+output = 10
+cache_read = 1.25
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4o-mini"
+
+[cost]
+input = 0.15
+output = 0.6
+cache_read = 0.075
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4o"
+
+[cost]
+input = 2.5
+output = 10
+cache_read = 1.25
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5-chat-latest"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5-codex"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5-mini"
+reasoning_options = []
+
+[cost]
+input = 0.25
+output = 2
+cache_read = 0.025
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5-nano"
+reasoning_options = []
+
+[cost]
+input = 0.05
+output = 0.4
+cache_read = 0.005
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-5-pro"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 15
+output = 120
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.1-chat-latest"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.1-codex-max"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.1-codex-mini"
+reasoning_options = []
+
+[cost]
+input = 0.25
+output = 2
+cache_read = 0.025
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.1-codex"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.1"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.2-chat-latest"
+reasoning_options = []
+
+[cost]
+input = 1.75
+output = 14
+cache_read = 0.175
@@ -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 +1,6 @@
+base_model = "openai/gpt-5.2-pro"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 21
+output = 168
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.2"
+reasoning_options = []
+
+[cost]
+input = 1.75
+output = 14
+cache_read = 0.175
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-5.3-chat-latest"
+
+[cost]
+input = 1.75
+output = 14
+cache_read = 0.175
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5.3-codex"
+reasoning_options = []
+
+[cost]
+input = 1.75
+output = 14
+cache_read = 0.175
@@ -0,0 +1,11 @@
+base_model = "openai/gpt-5.4-mini"
+reasoning_options = []
+
+[cost]
+input = 0.75
+output = 4.5
+cache_read = 0.075
+
+[experimental.modes.fast]
+cost = { input = 1.5, output = 9, cache_read = 0.15 }
+provider = { body = { service_tier = "priority" } }
@@ -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 +1,11 @@
+base_model = "openai/gpt-5.4-pro"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 60
+output = 270
+
+[[cost.tiers]]
+tier = { type = "context", size = 272_000 }
+input = 60
+output = 270
@@ -0,0 +1,17 @@
+base_model = "openai/gpt-5.4"
+reasoning_options = []
+
+[cost]
+input = 5
+output = 22.5
+cache_read = 0.25
+
+[[cost.tiers]]
+tier = { type = "context", size = 272_000 }
+input = 5
+output = 22.5
+cache_read = 0.5
+
+[experimental.modes.fast]
+cost = { input = 5, output = 30, cache_read = 0.5 }
+provider = { body = { service_tier = "priority" } }
@@ -0,0 +1,11 @@
+base_model = "openai/gpt-5.5-pro"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 30
+output = 180
+
+[[cost.tiers]]
+tier = { type = "context", size = 272_000 }
+input = 60
+output = 270
@@ -0,0 +1,17 @@
+base_model = "openai/gpt-5.5"
+reasoning_options = []
+
+[cost]
+input = 5
+output = 30
+cache_read = 0.5
+
+[[cost.tiers]]
+tier = { type = "context", size = 272_000 }
+input = 10
+output = 45
+cache_read = 1
+
+[experimental.modes.fast]
+cost = { input = 12.5, output = 75, cache_read = 1.25 }
+provider = { body = { service_tier = "priority" } }
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,23 @@
+name = "OrcaRouter Auto"
+description = "Automatic model router for matching prompts to suitable backends and budgets"
+family = "auto"
+release_date = "2025-01-01"
+last_updated = "2026-05-14"
+attachment = true
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128_000
+output = 16_384
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen3-max"
+
+[cost]
+input = 0.359
+output = 1.434
@@ -0,0 +1,6 @@
+base_model = "alibaba/qwen3.5-122b-a10b"
+reasoning_options = []
+
+[cost]
+input = 0.115
+output = 0.917
@@ -0,0 +1,6 @@
+base_model = "alibaba/qwen3.5-27b"
+reasoning_options = []
+
+[cost]
+input = 0.086
+output = 0.688
@@ -0,0 +1,6 @@
+base_model = "alibaba/qwen3.5-35b-a3b"
+reasoning_options = []
+
+[cost]
+input = 0.057
+output = 0.459
@@ -0,0 +1,6 @@
+base_model = "alibaba/qwen3.5-397b-a17b"
+reasoning_options = []
+
+[cost]
+input = 0.172
+output = 1.032
@@ -0,0 +1,7 @@
+base_model = "alibaba/qwen3.5-plus"
+reasoning_options = []
+
+[cost]
+input = 0.115
+output = 0.688
+reasoning = 2.4
@@ -0,0 +1,6 @@
+base_model = "alibaba/qwen3.6-35b-a3b"
+reasoning_options = []
+
+[cost]
+input = 0.248
+output = 1.485
@@ -0,0 +1,15 @@
+base_model = "alibaba/qwen3.6-plus"
+reasoning_options = []
+
+[cost]
+input = 0.5
+output = 3
+cache_read = 0.05
+cache_write = 0.625
+
+[[cost.tiers]]
+tier = { type = "context", size = 256_000 }
+input = 2
+output = 6
+cache_read = 0.2
+cache_write = 2.5
@@ -0,0 +1,8 @@
+base_model = "zhipuai/glm-4.5-air"
+reasoning_options = []
+
+[cost]
+input = 0.2
+output = 1.1
+cache_read = 0.03
+cache_write = 0
@@ -0,0 +1,8 @@
+base_model = "zhipuai/glm-4.5"
+reasoning_options = []
+
+[cost]
+input = 0.6
+output = 2.2
+cache_read = 0.11
+cache_write = 0
@@ -0,0 +1,8 @@
+base_model = "zhipuai/glm-4.6"
+reasoning_options = []
+
+[cost]
+input = 0.6
+output = 2.2
+cache_read = 0.11
+cache_write = 0
@@ -0,0 +1,11 @@
+base_model = "zhipuai/glm-4.7"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.6
+output = 2.2
+cache_read = 0.11
+cache_write = 0
@@ -0,0 +1,11 @@
+base_model = "zhipuai/glm-5.1"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 1.4
+output = 4.4
+cache_read = 0.26
+cache_write = 0
@@ -0,0 +1,11 @@
+base_model = "zhipuai/glm-5"
+reasoning_options = []
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 1
+output = 3.2
+cache_read = 0.2
+cache_write = 0