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 +1,26 @@
+name = "Claude Haiku 4.5"
+description = "Fast Claude model for responsive assistance, classification, and lightweight agents"
+family = "claude-haiku"
+release_date = "2025-10-15"
+last_updated = "2025-10-15"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "budget_tokens", min = 1_024 }]
+temperature = true
+tool_call = true
+knowledge = "2025-02-28"
+open_weights = false
+
+[cost]
+input = 1
+output = 5
+cache_read = 0.1
+cache_write = 1.25
+
+[limit]
+context = 200_000
+output = 64_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]
@@ -0,0 +1,29 @@
+name = "Claude Opus 4.6"
+description = "Flagship Claude model for deep reasoning, coding, and long-horizon agents"
+family = "claude-opus"
+release_date = "2026-02-05"
+last_updated = "2026-02-05"
+attachment = true
+reasoning = true
+reasoning_options = [
+  { type = "effort", values = ["low", "medium", "high"] },
+  { type = "budget_tokens", min = 1_024 },
+]
+temperature = true
+tool_call = true
+knowledge = "2025-05-31"
+open_weights = false
+
+[cost]
+input = 5
+output = 25
+cache_read = 0.5
+cache_write = 6.25
+
+[limit]
+context = 200_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]
@@ -0,0 +1,26 @@
+name = "Claude Opus 4.7"
+description = "Flagship Claude model for deep reasoning, coding, and long-horizon agents"
+family = "claude-opus"
+release_date = "2026-04-16"
+last_updated = "2026-04-16"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = false
+tool_call = true
+knowledge = "2026-01-31"
+open_weights = false
+
+[cost]
+input = 5
+output = 25
+cache_read = 0.5
+cache_write = 6.25
+
+[limit]
+context = 200_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]
@@ -0,0 +1,29 @@
+name = "Claude Sonnet 4.6"
+description = "Balanced Claude model for coding, analysis, agent workflows, and cost control"
+family = "claude-sonnet"
+release_date = "2026-02-17"
+last_updated = "2026-02-17"
+attachment = true
+reasoning = true
+reasoning_options = [
+  { type = "effort", values = ["low", "medium", "high"] },
+  { type = "budget_tokens", min = 1_024 },
+]
+temperature = true
+tool_call = true
+knowledge = "2025-08-31"
+open_weights = false
+
+[cost]
+input = 3
+output = 15
+cache_read = 0.3
+cache_write = 3.75
+
+[limit]
+context = 200_000
+output = 64_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "DeepSeek v4 Pro"
+description = "Flagship DeepSeek model for coding, reasoning, and agentic work"
+family = "deepseek"
+release_date = "2026-04-24"
+last_updated = "2026-04-24"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2026-01"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 1.74
+output = 3.48
+cache_read= 0.14
+
+[limit]
+context = 128_000
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]
@@ -0,0 +1,25 @@
+name = "Gemini 2.5 Flash"
+description = "Fast Gemini model balancing multimodal reasoning, tool use, and cost"
+family = "gemini-flash"
+release_date = "2025-07-17"
+last_updated = "2025-07-17"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "budget_tokens", min = 0, max = 24_576 }]
+temperature = true
+knowledge = "2025-01"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 0.3
+output = 2.5
+cache_read = 0.075
+
+[limit]
+context = 1_048_576
+output = 65_536
+
+[modalities]
+input = ["text", "image", "audio", "video", "pdf"]
+output = ["text"]
@@ -0,0 +1,25 @@
+name = "Gemini 2.5 Pro"
+description = "Advanced Gemini model for complex reasoning, coding, and multimodal analysis"
+family = "gemini-pro"
+release_date = "2025-03-20"
+last_updated = "2025-06-05"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "budget_tokens", min = 128, max = 32_768 }]
+temperature = true
+knowledge = "2025-01"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.31
+
+[limit]
+context = 1_048_576
+output = 65_536
+
+[modalities]
+input = ["text", "image", "audio", "video", "pdf"]
+output = ["text"]
@@ -0,0 +1,26 @@
+name = "Gemini 3.1 Pro Preview"
+description = "Advanced Gemini model for complex reasoning, coding, and multimodal analysis"
+family = "gemini-pro"
+release_date = "2026-02-18"
+last_updated = "2026-02-18"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = true
+tool_call = true
+structured_output = true
+knowledge = "2026-01"
+open_weights = false
+
+[cost]
+input = 2
+output = 12
+cache_read = 0.2
+
+[limit]
+context = 1_000_000
+output = 64_000
+
+[modalities]
+input = ["text", "image", "video", "audio", "pdf"]
+output = ["text"]
@@ -0,0 +1,26 @@
+name = "Gemini 3 Flash Preview"
+description = "Fast Gemini model balancing multimodal reasoning, tool use, and cost"
+family = "gemini-flash"
+release_date = "2025-12-17"
+last_updated = "2025-12-17"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = true
+tool_call = true
+structured_output = true
+knowledge = "2025-01"
+open_weights = false
+
+[cost]
+input = 0.5
+output = 3
+cache_read = 0.05
+
+[limit]
+context = 1_048_576
+output = 65_536
+
+[modalities]
+input = ["text", "image", "video", "audio", "pdf"]
+output = ["text"]
@@ -0,0 +1,25 @@
+name = "GPT-4o"
+description = "GPT model for general reasoning, writing, coding, and tool-assisted tasks"
+family = "gpt"
+release_date = "2024-05-13"
+last_updated = "2024-08-06"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2023-09"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 2.5
+output = 10
+cache_read = 1.25
+
+[limit]
+context = 128_000
+output = 16_384
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,25 @@
+name = "GPT-5.3 Codex"
+description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work"
+family = "gpt"
+release_date = "2026-02-15"
+last_updated = "2026-02-15"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = false
+knowledge = "2026-01-31"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 1.75
+output = 14
+cache_read = 0.175
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,26 @@
+name = "GPT-5.4 Mini"
+description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "gpt-mini"
+release_date = "2026-03-17"
+last_updated = "2026-03-17"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 0.75
+output = 4.5
+cache_read = 0.075
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,26 @@
+name = "GPT-5.4 Nano"
+description = "Compact GPT model for low-latency assistance and high-volume workloads"
+family = "gpt-nano"
+release_date = "2025-08-07"
+last_updated = "2025-08-07"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = false
+knowledge = "2024-05-30"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 0.2
+output = 1.25
+cache_read = 0.02
+
+[limit]
+context = 400_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,25 @@
+name = "GPT-5.5"
+description = "Frontier GPT model for professional reasoning, coding, and multimodal work"
+family = "gpt"
+release_date = "2026-03-05"
+last_updated = "2026-03-05"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = false
+knowledge = "2025-08-31"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 2.5
+output = 15
+cache_read = 0.25
+
+[limit]
+context = 272_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "GPT OSS 120B"
+description = "Open-weight GPT model for self-hosted reasoning and instruction-following workloads"
+family = "gpt-oss"
+release_date = "1970-01-01"
+last_updated = "1970-01-01"
+attachment = false
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = true
+
+[cost]
+input = 0.15
+output = 0.6
+
+[limit]
+context = 131_072
+output = 32_768
+
+[modalities]
+input = ["text"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "GPT OSS 20B"
+description = "Open-weight GPT model for self-hosted reasoning and instruction-following workloads"
+family = "gpt-oss"
+release_date = "1970-01-01"
+last_updated = "1970-01-01"
+attachment = false
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = true
+
+[cost]
+input = 0.07
+output = 0.2
+
+[limit]
+context = 131_072
+output = 32_768
+
+[modalities]
+input = ["text"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "Grok 4.1 Fast (Non-Reasoning)"
+description = "Fast Grok model for responsive chat, reasoning, and tool-assisted work"
+family = "grok"
+release_date = "2025-11-25"
+last_updated = "2025-11-25"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2025-11"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 0.2
+output = 0.5
+cache_read = 0.05
+
+[limit]
+context = 2_000_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,25 @@
+name = "Grok 4.1 Fast (Reasoning)"
+description = "Fast Grok model for responsive chat, reasoning, and tool-assisted work"
+family = "grok"
+release_date = "2025-11-25"
+last_updated = "2025-11-25"
+attachment = true
+reasoning = true
+reasoning_options = []
+temperature = true
+knowledge = "2025-11"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 0.2
+output = 0.5
+cache_read = 0.05
+
+[limit]
+context = 2_000_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,26 @@
+name = "Grok 4.3"
+description = "Grok model for agentic tool use, reasoning, coding, and live assistance"
+family = "grok"
+release_date = "2026-04-30"
+last_updated = "2026-04-30"
+attachment = true
+reasoning = true
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+temperature = true
+knowledge = "2024-11"
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 1.25
+output = 2.50
+cache_read = 0.20
+
+[limit]
+context = 1_000_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "video"]
+output = ["text"]
@@ -0,0 +1,25 @@
+name = "Grok 4.1 Fast (Reasoning)"
+description = "Fast Grok model for responsive chat, reasoning, and tool-assisted work"
+family = "grok"
+release_date = "2025-08-28"
+last_updated = "2025-08-28"
+attachment = false
+reasoning = true
+reasoning_options = []
+temperature = true
+knowledge = "2023-10"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 0.2
+output = 1.5
+cache_read = 0.02
+
+[limit]
+context = 256_000
+output = 128_000
+
+[modalities]
+input = ["text"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "Kimi-K2.6"
+description = "Kimi multimodal agent model for visual understanding, coding, and planning"
+release_date = "1970-01-01"
+last_updated = "1970-01-01"
+attachment = false
+reasoning = true
+reasoning_options = []
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 0.95
+output = 4.0
+cache_read = 0.16
+
+[limit]
+context = 256_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "Kimi-K2.5"
+description = "Kimi multimodal agent model for visual understanding, coding, and planning"
+release_date = "1970-01-01"
+last_updated = "1970-01-01"
+attachment = false
+reasoning = true
+reasoning_options = []
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[cost]
+input = 0.6
+output = 3.0
+cache_read = 0.1
+
+[limit]
+context = 256_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "MiniMax-M2.5"
+description = "MiniMax model for chat, coding, office work, and agentic tasks"
+family = "minimax"
+release_date = "2025-01-15"
+last_updated = "2025-02-22"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2024-09"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 0.3
+output = 1.2
+cache_read = 0.03
+
+[limit]
+context = 192_000
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "MiniMax-M2.7"
+description = "MiniMax model for chat, coding, office work, and agentic tasks"
+family = "minimax"
+release_date = "2026-03-18"
+last_updated = "2026-03-18"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2024-09"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 0.3
+output = 1.2
+cache_read = 0.06
+
+[limit]
+context = 192_000
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "Qwen 3.6 Plus"
+description = "Qwen vision-language model for visual reasoning, documents, and agent tasks"
+family = "qwen"
+attachment = true
+reasoning = true
+reasoning_options = []
+tool_call = true
+temperature = true
+release_date = "2026-04-02"
+last_updated = "2026-04-03"
+open_weights = false
+
+[cost]
+input = 0.5
+output = 3
+cache_read = 0.1
+
+[limit]
+context = 1_000_000
+output = 64_000
+
+[modalities]
+input = ["text", "image", "pdf"]
+output = ["text"]
@@ -0,0 +1,24 @@
+name = "Z.AI GLM-5.1"
+description = "Flagship GLM model for hybrid reasoning, coding, and agentic engineering"
+family = "glm"
+release_date = "2025-01-20"
+last_updated = "2025-02-22"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2024-10"
+tool_call = true
+open_weights = true
+
+[cost]
+input = 1.4
+output = 4.4
+cache_read = 0.26
+
+[limit]
+context = 198_000
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]