feat(aixy): expand gateway catalog (2/2)

providers/aixy/.catalog-sync-enabled

@@ -0,0 +1 @@
+The complete reviewed first-class provider catalog is present; hourly Aixy sync may own it.

providers/aixy/models/alibaba/deepseek-v4-flash-0731.toml

@@ -0,0 +1,23 @@
+# Sources (accessed 2026-08-08):
+# https://www.alibabacloud.com/help/en/model-studio/deepseek-api
+# https://www.alibabacloud.com/help/en/model-studio/model-pricing (Singapore list)
+# https://www.qwencloud.com/models/deepseek-v4-flash-0731 (implicit cache price)
+# Pay-as-you-go on DashScope international, not Token Plan only.
+# Toggle: enable_thinking true|false
+# Effort: reasoning_effort = high (default) | max; low/medium map to high, xhigh maps to max
+base_model = "deepseek/deepseek-v4-flash-0731"
+
+[interleaved]
+field = "reasoning_content"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "effort"
+values = ["high", "max"]
+
+[cost]
+input = 0.2
+output = 0.4
+cache_read = 0.04

providers/aixy/models/alibaba/glm-5.2.toml

@@ -0,0 +1,20 @@
+# Sources (accessed 2026-08-08):
+# https://www.alibabacloud.com/help/en/model-studio/glm
+# https://www.alibabacloud.com/help/en/model-studio/model-pricing (Singapore list)
+# https://www.qwencloud.com/models/glm-5.2 (implicit cache price)
+# Effort: reasoning_effort = none|minimal|low|medium|high|xhigh|max
+# (none disables reasoning, so a separate toggle is not needed).
+base_model = "zhipuai/glm-5.2"
+
+[interleaved]
+field = "reasoning_content"
+
+[[reasoning_options]]
+type = "effort"
+values = ["none", "minimal", "low", "medium", "high", "xhigh", "max"]
+
+[cost]
+input = 1.4
+output = 4.4
+cache_read = 0.28
+cache_write = 0

providers/aixy/models/alibaba/qwen-flash.toml

@@ -0,0 +1,14 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen-flash.toml.
+base_model = "alibaba/qwen-flash"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.05
+output = 0.4

providers/aixy/models/alibaba/qwen-max.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen-max"
+
+[cost]
+input = 1.6
+output = 6.4

providers/aixy/models/alibaba/qwen-plus.toml

@@ -0,0 +1,15 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen-plus.toml.
+base_model = "alibaba/qwen-plus"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.4
+output = 1.2
+reasoning = 4

providers/aixy/models/alibaba/qwen-turbo.toml

@@ -0,0 +1,15 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen-turbo.toml.
+base_model = "alibaba/qwen-turbo"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.05
+output = 0.2
+reasoning = 0.5

providers/aixy/models/alibaba/qwen-vl-max.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen-vl-max"
+
+[cost]
+input = 0.8
+output = 3.2

providers/aixy/models/alibaba/qwen-vl-plus.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen-vl-plus"
+
+[cost]
+input = 0.21
+output = 0.63

providers/aixy/models/alibaba/qwen2-5-vl-72b-instruct.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen2-5-vl-72b-instruct"
+
+[cost]
+input = 2.8
+output = 8.4

providers/aixy/models/alibaba/qwen3-235b-a22b.toml

@@ -0,0 +1,15 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3-235b-a22b.toml.
+base_model = "alibaba/qwen3-235b-a22b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.7
+output = 2.8
+reasoning = 8.4

providers/aixy/models/alibaba/qwen3-32b.toml

@@ -0,0 +1,15 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3-32b.toml.
+base_model = "alibaba/qwen3-32b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.7
+output = 2.8
+reasoning = 8.4

providers/aixy/models/alibaba/qwen3-coder-30b-a3b-instruct.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen3-coder-30b-a3b-instruct"
+
+[cost]
+input = 0.45
+output = 2.25

providers/aixy/models/alibaba/qwen3-coder-480b-a35b-instruct.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen3-coder-480b-a35b-instruct"
+
+[cost]
+input = 1.5
+output = 7.5

providers/aixy/models/alibaba/qwen3-coder-flash.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen3-coder-flash"
+
+[cost]
+input = 0.3
+output = 1.5

providers/aixy/models/alibaba/qwen3-coder-plus.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen3-coder-plus"
+
+[cost]
+input = 1
+output = 5

providers/aixy/models/alibaba/qwen3-max.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen3-max"
+
+[cost]
+input = 1.2
+output = 6

providers/aixy/models/alibaba/qwen3-next-80b-a3b-instruct.toml

@@ -0,0 +1,5 @@
+base_model = "alibaba/qwen3-next-80b-a3b-instruct"
+
+[cost]
+input = 0.5
+output = 2

providers/aixy/models/alibaba/qwen3-next-80b-a3b-thinking.toml

@@ -0,0 +1,8 @@
+base_model = "alibaba/qwen3-next-80b-a3b-thinking"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.5
+output = 6

providers/aixy/models/alibaba/qwen3-vl-plus.toml

@@ -0,0 +1,15 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3-vl-plus.toml.
+base_model = "alibaba/qwen3-vl-plus"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.2
+output = 1.6
+reasoning = 4.8

providers/aixy/models/alibaba/qwen3.5-122b-a10b.toml

@@ -0,0 +1,14 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.5-122b-a10b.toml.
+base_model = "alibaba/qwen3.5-122b-a10b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.4
+output = 3.2

providers/aixy/models/alibaba/qwen3.5-27b.toml

@@ -0,0 +1,14 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.5-27b.toml.
+base_model = "alibaba/qwen3.5-27b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.3
+output = 2.4

providers/aixy/models/alibaba/qwen3.5-35b-a3b.toml

@@ -0,0 +1,14 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.5-35b-a3b.toml.
+base_model = "alibaba/qwen3.5-35b-a3b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.25
+output = 2

providers/aixy/models/alibaba/qwen3.5-397b-a17b.toml

@@ -0,0 +1,14 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.5-397b-a17b.toml.
+base_model = "alibaba/qwen3.5-397b-a17b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.6
+output = 3.6

providers/aixy/models/alibaba/qwen3.5-plus.toml

@@ -0,0 +1,15 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.5-plus.toml.
+base_model = "alibaba/qwen3.5-plus"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.4
+output = 2.4
+reasoning = 2.4

providers/aixy/models/alibaba/qwen3.6-27b.toml

@@ -0,0 +1,14 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.6-27b.toml.
+base_model = "alibaba/qwen3.6-27b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.6
+output = 3.6

providers/aixy/models/alibaba/qwen3.6-35b-a3b.toml

@@ -0,0 +1,14 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.6-35b-a3b.toml.
+base_model = "alibaba/qwen3.6-35b-a3b"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.248
+output = 1.485

providers/aixy/models/alibaba/qwen3.6-flash.toml

@@ -0,0 +1,15 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.6-flash.toml.
+base_model = "alibaba/qwen3.6-flash"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 0.1875
+output = 1.125
+cache_write = 0.234375

providers/aixy/models/alibaba/qwen3.6-max-preview.toml

@@ -0,0 +1,16 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.6-max-preview.toml.
+base_model = "alibaba/qwen3.6-max-preview"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 1.3
+output = 7.8
+cache_read = 0.13
+cache_write = 1.625

providers/aixy/models/alibaba/qwen3.6-plus.toml

@@ -0,0 +1,24 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.6-plus.toml.
+base_model = "alibaba/qwen3.6-plus"
+attachment = false
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[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

providers/aixy/models/alibaba/qwen3.7-max.toml

@@ -0,0 +1,16 @@
+# Toggle: enable_thinking = true|false
+# Aixy forwards this route to alibaba without translating the model payload.
+# Reasoning controls mirror providers/alibaba/models/qwen3.7-max.toml.
+base_model = "alibaba/qwen3.7-max"
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "budget_tokens"
+
+[cost]
+input = 2.5
+output = 7.5
+cache_read = 0.5
+cache_write = 3.125