diff --git a/providers/aihubmix/models/deepseek-v4-flash-think.toml b/providers/aihubmix/models/alicloud-deepseek-v4-flash.toml
similarity index 74%
rename from providers/aihubmix/models/deepseek-v4-flash-think.toml
rename to providers/aihubmix/models/alicloud-deepseek-v4-flash.toml
index e174bd0b3..21034327f 100644
--- a/providers/aihubmix/models/deepseek-v4-flash-think.toml
+++ b/providers/aihubmix/models/alicloud-deepseek-v4-flash.toml
@@ -1,5 +1,5 @@
-name = "DeepSeek V4 Flash Think"
-family = "deepseek"
+name = "DeepSeek V4 Flash (Alibaba Cloud)"
+family = "deepseek-flash"
 release_date = "2026-04-24"
 last_updated = "2026-04-24"
 attachment = false
@@ -14,9 +14,9 @@ open_weights = true
 field = "reasoning_content"
 
 [cost]
-input = 0.154
-output = 0.308
-cache_read = 0.0308
+input = 0.14
+output = 0.28
+cache_read = 0.028
 
 [limit]
 context = 1_000_000
diff --git a/providers/aihubmix/models/alicloud-deepseek-v4-pro.toml b/providers/aihubmix/models/alicloud-deepseek-v4-pro.toml
new file mode 100644
index 000000000..43bc50c45
--- /dev/null
+++ b/providers/aihubmix/models/alicloud-deepseek-v4-pro.toml
@@ -0,0 +1,27 @@
+name = "DeepSeek V4 Pro (Alibaba Cloud)"
+family = "deepseek-thinking"
+release_date = "2026-04-24"
+last_updated = "2026-04-24"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+knowledge = "2025-05"
+open_weights = true
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 1.69
+output = 3.38
+cache_read = 0.13
+
+[limit]
+context = 1_000_000
+output = 384_000
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/aihubmix/models/alicloud-glm-5.1.toml b/providers/aihubmix/models/alicloud-glm-5.1.toml
new file mode 100644
index 000000000..cac85df8c
--- /dev/null
+++ b/providers/aihubmix/models/alicloud-glm-5.1.toml
@@ -0,0 +1,27 @@
+name = "GLM-5.1 (Alibaba Cloud)"
+family = "glm"
+release_date = "2026-03-27"
+last_updated = "2026-03-27"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = true
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.84
+output = 3.38
+cache_read = 0.169
+cache_write = 1.05625
+
+[limit]
+context = 200_000
+output = 128_000
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/aihubmix/models/claude-opus-4-6-think.toml b/providers/aihubmix/models/claude-opus-4-6-think.toml
index b64a9c52f..88b0ad7ab 100644
--- a/providers/aihubmix/models/claude-opus-4-6-think.toml
+++ b/providers/aihubmix/models/claude-opus-4-6-think.toml
@@ -1,4 +1,4 @@
-name = "Claude Opus 4.6"
+name = "Claude Opus 4.6 Thinking"
 family = "claude-opus"
 release_date = "2026-02-05"
 last_updated = "2026-03-13"
@@ -6,18 +6,29 @@ attachment = true
 reasoning = true
 temperature = true
 tool_call = true
+structured_output = true
 knowledge = "2025-05-31"
 open_weights = false
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
 input = 5
 output = 25
 cache_read = 0.5
 cache_write = 6.25
 
+[[cost.tiers]]
+tier = { size = 200_000 }
+input = 10
+output = 37.5
+cache_read = 1.0
+cache_write = 12.5
+
 [limit]
-context = 200_000
-output = 32_000
+context = 1_000_000
+output = 128_000
 
 [modalities]
 input = ["text", "image", "pdf"]
diff --git a/providers/aihubmix/models/claude-opus-4-6.toml b/providers/aihubmix/models/claude-opus-4-6.toml
index 3fcb380c7..eef0b9a07 100644
--- a/providers/aihubmix/models/claude-opus-4-6.toml
+++ b/providers/aihubmix/models/claude-opus-4-6.toml
@@ -6,15 +6,25 @@ attachment = true
 reasoning = true
 temperature = true
 tool_call = true
+structured_output = true
 knowledge = "2025-05-31"
 open_weights = false
 
+interleaved = true
+
 [cost]
 input = 5
 output = 25
 cache_read = 0.5
 cache_write = 6.25
 
+[[cost.tiers]]
+tier = { size = 200_000 }
+input = 10
+output = 37.5
+cache_read = 1.0
+cache_write = 12.5
+
 [limit]
 context = 1_000_000
 output = 128_000
diff --git a/providers/aihubmix/models/claude-opus-4-7-think.toml b/providers/aihubmix/models/claude-opus-4-7-think.toml
index 930c9a53b..6fea7ec1c 100644
--- a/providers/aihubmix/models/claude-opus-4-7-think.toml
+++ b/providers/aihubmix/models/claude-opus-4-7-think.toml
@@ -10,16 +10,26 @@ structured_output = true
 knowledge = "2026-01-31"
 open_weights = false
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
 input = 5
 output = 25
 cache_read = 0.5
 cache_write = 6.25
 
+[[cost.tiers]]
+tier = { size = 200_000 }
+input = 10
+output = 37.5
+cache_read = 1.0
+cache_write = 12.5
+
 [limit]
-context = 200_000
-output = 32_000
+context = 1_000_000
+output = 128_000
 
 [modalities]
-input = ["text", "image"]
+input = ["text", "image", "pdf"]
 output = ["text"]
diff --git a/providers/aihubmix/models/claude-opus-4-7.toml b/providers/aihubmix/models/claude-opus-4-7.toml
index 28416e128..43acf223d 100644
--- a/providers/aihubmix/models/claude-opus-4-7.toml
+++ b/providers/aihubmix/models/claude-opus-4-7.toml
@@ -6,15 +6,25 @@ attachment = true
 reasoning = true
 temperature = false
 tool_call = true
+structured_output = true
 knowledge = "2026-01-31"
 open_weights = false
 
+interleaved = true
+
 [cost]
 input = 5
 output = 25
 cache_read = 0.5
 cache_write = 6.25
 
+[[cost.tiers]]
+tier = { size = 200_000 }
+input = 10
+output = 37.5
+cache_read = 1.0
+cache_write = 12.5
+
 [limit]
 context = 1_000_000
 output = 128_000
diff --git a/providers/aihubmix/models/claude-sonnet-4-6-think.toml b/providers/aihubmix/models/claude-sonnet-4-6-think.toml
index c957d79ab..f2bf9dcd0 100644
--- a/providers/aihubmix/models/claude-sonnet-4-6-think.toml
+++ b/providers/aihubmix/models/claude-sonnet-4-6-think.toml
@@ -1,14 +1,18 @@
-name = "Claude Sonnet 4.6 Think"
+name = "Claude Sonnet 4.6 Thinking"
 family = "claude-sonnet"
 release_date = "2026-02-17"
-last_updated = "2026-02-17"
+last_updated = "2026-03-13"
 attachment = true
 reasoning = true
 temperature = true
 tool_call = true
+structured_output = true
 knowledge = "2025-08-31"
 open_weights = false
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
 input = 3.00
 output = 15.00
@@ -23,7 +27,7 @@ cache_read = 0.60
 cache_write = 7.50
 
 [limit]
-context = 200_000
+context = 1_000_000
 output = 64_000
 
 [modalities]
diff --git a/providers/aihubmix/models/claude-sonnet-4-6.toml b/providers/aihubmix/models/claude-sonnet-4-6.toml
index 428a55192..475f68272 100644
--- a/providers/aihubmix/models/claude-sonnet-4-6.toml
+++ b/providers/aihubmix/models/claude-sonnet-4-6.toml
@@ -1,14 +1,17 @@
 name = "Claude Sonnet 4.6"
 family = "claude-sonnet"
 release_date = "2026-02-17"
-last_updated = "2026-02-17"
+last_updated = "2026-03-13"
 attachment = true
 reasoning = true
 temperature = true
 tool_call = true
+structured_output = true
 knowledge = "2025-08-31"
 open_weights = false
 
+interleaved = true
+
 [cost]
 input = 3.00
 output = 15.00
@@ -23,7 +26,7 @@ cache_read = 0.60
 cache_write = 7.50
 
 [limit]
-context = 200_000
+context = 1_000_000
 output = 64_000
 
 [modalities]
diff --git a/providers/aihubmix/models/coding-glm-5.1-free.toml b/providers/aihubmix/models/coding-glm-5.1-free.toml
index baea9b0a7..eb69dda30 100644
--- a/providers/aihubmix/models/coding-glm-5.1-free.toml
+++ b/providers/aihubmix/models/coding-glm-5.1-free.toml
@@ -1,5 +1,5 @@
 name = "Coding GLM 5.1 (free)"
-family = "glm"
+family = "glm-free"
 release_date = "2026-04-11"
 last_updated = "2026-04-11"
 attachment = false
@@ -7,7 +7,7 @@ reasoning = true
 temperature = true
 tool_call = true
 structured_output = true
-open_weights = false
+open_weights = true
 
 [interleaved]
 field = "reasoning_content"
@@ -15,10 +15,9 @@ field = "reasoning_content"
 [cost]
 input = 0
 output = 0
-cache_read = 0
 
 [limit]
-context = 204_800
+context = 200_000
 output = 128_000
 
 [modalities]
diff --git a/providers/aihubmix/models/coding-glm-5.1.toml b/providers/aihubmix/models/coding-glm-5.1.toml
index f7bfa7e87..4988317e1 100644
--- a/providers/aihubmix/models/coding-glm-5.1.toml
+++ b/providers/aihubmix/models/coding-glm-5.1.toml
@@ -1,4 +1,4 @@
-name = "Coding-GLM-5.1"
+name = "Coding GLM 5.1"
 family = "glm"
 release_date = "2026-04-11"
 last_updated = "2026-04-11"
@@ -6,7 +6,8 @@ attachment = false
 reasoning = true
 temperature = true
 tool_call = true
-open_weights = false
+structured_output = true
+open_weights = true
 
 [interleaved]
 field = "reasoning_content"
@@ -14,10 +15,11 @@ field = "reasoning_content"
 [cost]
 input = 0.06
 output = 0.22
+cache_read = 0.013
 
 [limit]
-context = 200000
-output = 128000
+context = 200_000
+output = 128_000
 
 [modalities]
 input = ["text"]
diff --git a/providers/aihubmix/models/coding-minimax-m2.7-free.toml b/providers/aihubmix/models/coding-minimax-m2.7-free.toml
index bfce68ece..1fb824b21 100644
--- a/providers/aihubmix/models/coding-minimax-m2.7-free.toml
+++ b/providers/aihubmix/models/coding-minimax-m2.7-free.toml
@@ -1,20 +1,24 @@
-name = "Coding-MiniMax-M2.7-Free"
-family = "minimax"
+name = "Coding MiniMax M2.7 (Free)"
+family = "minimax-free"
 release_date = "2026-03-18"
 last_updated = "2026-03-18"
 attachment = false
 reasoning = true
 temperature = true
 tool_call = true
+structured_output = true
 open_weights = true
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
 input = 0
 output = 0
 
 [limit]
 context = 204_800
-output = 13_100
+output = 128_100
 
 [modalities]
 input = ["text"]
diff --git a/providers/aihubmix/models/coding-minimax-m2.7-highspeed.toml b/providers/aihubmix/models/coding-minimax-m2.7-highspeed.toml
index 4cca7b62f..1d997a3dc 100644
--- a/providers/aihubmix/models/coding-minimax-m2.7-highspeed.toml
+++ b/providers/aihubmix/models/coding-minimax-m2.7-highspeed.toml
@@ -9,13 +9,16 @@ tool_call = true
 structured_output = true
 open_weights = true
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
 input = 0.2
 output = 0.2
 
 [limit]
 context = 204_800
-output = 13_100
+output = 128_100
 
 [modalities]
 input = ["text"]
diff --git a/providers/aihubmix/models/coding-minimax-m2.7.toml b/providers/aihubmix/models/coding-minimax-m2.7.toml
index 734be69b7..e79263a41 100644
--- a/providers/aihubmix/models/coding-minimax-m2.7.toml
+++ b/providers/aihubmix/models/coding-minimax-m2.7.toml
@@ -9,13 +9,16 @@ tool_call = true
 structured_output = true
 open_weights = true
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
 input = 0.2
 output = 0.2
 
 [limit]
 context = 204_800
-output = 13_100
+output = 128_100
 
 [modalities]
 input = ["text"]
diff --git a/providers/aihubmix/models/coding-xiaomi-mimo-v2.5-pro.toml b/providers/aihubmix/models/coding-xiaomi-mimo-v2.5-pro.toml
new file mode 100644
index 000000000..2f0df7af9
--- /dev/null
+++ b/providers/aihubmix/models/coding-xiaomi-mimo-v2.5-pro.toml
@@ -0,0 +1,17 @@
+name = "Coding Xiaomi MiMo-V2.5-Pro"
+family = "mimo-v2.5-pro"
+last_updated = "2026-05-13"
+
+[extends]
+from = "xiaomi/mimo-v2.5-pro"
+
+[cost]
+input = 0.20
+output = 0.60
+cache_read = 0.04
+
+[[cost.tiers]]
+tier = { size = 256_000 }
+input = 0.40
+output = 1.20
+cache_read = 0.08
diff --git a/providers/aihubmix/models/coding-xiaomi-mimo-v2.5.toml b/providers/aihubmix/models/coding-xiaomi-mimo-v2.5.toml
new file mode 100644
index 000000000..63805399e
--- /dev/null
+++ b/providers/aihubmix/models/coding-xiaomi-mimo-v2.5.toml
@@ -0,0 +1,17 @@
+name = "Coding Xiaomi MiMo-V2.5"
+family = "mimo-v2.5"
+last_updated = "2026-05-13"
+
+[extends]
+from = "xiaomi/mimo-v2.5"
+
+[cost]
+input = 0.08
+output = 0.40
+cache_read = 0.016
+
+[[cost.tiers]]
+tier = { size = 256_000 }
+input = 0.16
+output = 0.80
+cache_read = 0.032
diff --git a/providers/aihubmix/models/deepseek-v4-flash.toml b/providers/aihubmix/models/deep-deepseek-v4-flash.toml
similarity index 91%
rename from providers/aihubmix/models/deepseek-v4-flash.toml
rename to providers/aihubmix/models/deep-deepseek-v4-flash.toml
index 34b9bb3c6..4fd8563f5 100644
--- a/providers/aihubmix/models/deepseek-v4-flash.toml
+++ b/providers/aihubmix/models/deep-deepseek-v4-flash.toml
@@ -1,4 +1,4 @@
-name = "DeepSeek V4 Flash"
+name = "DeepSeek V4 Flash (DeepSeek)"
 family = "deepseek-flash"
 release_date = "2026-04-24"
 last_updated = "2026-04-24"
diff --git a/providers/aihubmix/models/deepseek-v4-pro.toml b/providers/aihubmix/models/deep-deepseek-v4-pro.toml
similarity index 92%
rename from providers/aihubmix/models/deepseek-v4-pro.toml
rename to providers/aihubmix/models/deep-deepseek-v4-pro.toml
index f01543ccc..24e56e4fb 100644
--- a/providers/aihubmix/models/deepseek-v4-pro.toml
+++ b/providers/aihubmix/models/deep-deepseek-v4-pro.toml
@@ -1,4 +1,4 @@
-name = "DeepSeek V4 Pro"
+name = "DeepSeek V4 Pro (DeepSeek)"
 family = "deepseek-thinking"
 release_date = "2026-04-24"
 last_updated = "2026-04-24"
diff --git a/providers/aihubmix/models/doubao-seed-2-0-code-preview.toml b/providers/aihubmix/models/doubao-seed-2-0-code-preview.toml
new file mode 100644
index 000000000..dcbeaea99
--- /dev/null
+++ b/providers/aihubmix/models/doubao-seed-2-0-code-preview.toml
@@ -0,0 +1,38 @@
+name = "Doubao Seed 2.0 Code Preview"
+family = "seed"
+release_date = "2026-02-14"
+last_updated = "2026-02-14"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.48
+output = 2.41
+cache_read = 0.09644
+
+[[cost.tiers]]
+tier = { size = 32_000 }
+input = 0.72
+output = 3.62
+cache_read = 0.144656
+
+[[cost.tiers]]
+tier = { size = 128_000 }
+input = 1.45
+output = 7.23
+cache_read = 0.28932
+
+[limit]
+context = 256_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "video"]
+output = ["text"]
diff --git a/providers/aihubmix/models/doubao-seed-2-0-lite-260428.toml b/providers/aihubmix/models/doubao-seed-2-0-lite-260428.toml
new file mode 100644
index 000000000..90889231a
--- /dev/null
+++ b/providers/aihubmix/models/doubao-seed-2-0-lite-260428.toml
@@ -0,0 +1,41 @@
+name = "Doubao Seed 2.0 Lite 260428"
+family = "seed"
+release_date = "2026-04-28"
+last_updated = "2026-04-28"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.08
+output = 0.51
+cache_read = 0.01692
+input_audio = 1.269
+
+[[cost.tiers]]
+tier = { size = 32_000 }
+input = 0.13
+output = 0.76
+cache_read = 0.02536
+input_audio = 1.902
+
+[[cost.tiers]]
+tier = { size = 128_000 }
+input = 0.25
+output = 1.52
+cache_read = 0.05072
+input_audio = 3.804
+
+[limit]
+context = 256_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "video"]
+output = ["text"]
diff --git a/providers/aihubmix/models/doubao-seed-2-0-mini-260428.toml b/providers/aihubmix/models/doubao-seed-2-0-mini-260428.toml
new file mode 100644
index 000000000..c5d470777
--- /dev/null
+++ b/providers/aihubmix/models/doubao-seed-2-0-mini-260428.toml
@@ -0,0 +1,41 @@
+name = "Doubao Seed 2.0 Mini 260428"
+family = "seed"
+release_date = "2026-04-28"
+last_updated = "2026-04-28"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.03
+output = 0.28
+cache_read = 0.00564
+input_audio = 0.423
+
+[[cost.tiers]]
+tier = { size = 32_000 }
+input = 0.06
+output = 0.56
+cache_read = 0.01128
+input_audio = 0.846
+
+[[cost.tiers]]
+tier = { size = 128_000 }
+input = 0.11
+output = 1.13
+cache_read = 0.02256
+input_audio = 1.692
+
+[limit]
+context = 256_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "video"]
+output = ["text"]
diff --git a/providers/aihubmix/models/doubao-seed-2-0-pro.toml b/providers/aihubmix/models/doubao-seed-2-0-pro.toml
new file mode 100644
index 000000000..d2e6937b0
--- /dev/null
+++ b/providers/aihubmix/models/doubao-seed-2-0-pro.toml
@@ -0,0 +1,38 @@
+name = "Doubao Seed 2.0 Pro"
+family = "seed"
+release_date = "2026-02-14"
+last_updated = "2026-02-14"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+open_weights = false
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0.48
+output = 2.41
+cache_read = 0.09644
+
+[[cost.tiers]]
+tier = { size = 32_000 }
+input = 0.72
+output = 3.62
+cache_read = 0.144656
+
+[[cost.tiers]]
+tier = { size = 128_000 }
+input = 1.45
+output = 7.23
+cache_read = 0.28932
+
+[limit]
+context = 256_000
+output = 128_000
+
+[modalities]
+input = ["text", "image", "video"]
+output = ["text"]
diff --git a/providers/aihubmix/models/gemini-2.5-flash.toml b/providers/aihubmix/models/gemini-2.5-flash.toml
index c20cdaeb5..a79daef68 100644
--- a/providers/aihubmix/models/gemini-2.5-flash.toml
+++ b/providers/aihubmix/models/gemini-2.5-flash.toml
@@ -12,8 +12,9 @@ open_weights = false
 
 [cost]
 input = 0.3
-output = 2.499
+output = 2.50
 cache_read = 0.03
+input_audio = 1.00
 
 [limit]
 context = 1_048_576
diff --git a/providers/aihubmix/models/gemini-2.5-pro.toml b/providers/aihubmix/models/gemini-2.5-pro.toml
index 917e3a821..8e08808ba 100644
--- a/providers/aihubmix/models/gemini-2.5-pro.toml
+++ b/providers/aihubmix/models/gemini-2.5-pro.toml
@@ -15,6 +15,12 @@ input = 1.25
 output = 10
 cache_read = 0.125
 
+[[cost.tiers]]
+tier = { size = 200_000 }
+input = 2.50
+output = 15.00
+cache_read = 0.25
+
 [limit]
 context = 1_048_576
 output = 65_536
diff --git a/providers/aihubmix/models/gemini-3-flash-preview.toml b/providers/aihubmix/models/gemini-3-flash-preview.toml
index c9f36e7e7..dcf1eeedc 100644
--- a/providers/aihubmix/models/gemini-3-flash-preview.toml
+++ b/providers/aihubmix/models/gemini-3-flash-preview.toml
@@ -15,6 +15,12 @@ input = 0.5
 output = 3
 cache_read = 0.05
 
+[[cost.tiers]]
+tier = { size = 200_000 }
+input = 0.50
+output = 3.00
+cache_read = 0.05
+
 [limit]
 context = 1_048_576
 output = 65_536
diff --git a/providers/aihubmix/models/gemini-3.1-flash-lite.toml b/providers/aihubmix/models/gemini-3.1-flash-lite.toml
index 605d8063e..22f8728bc 100644
--- a/providers/aihubmix/models/gemini-3.1-flash-lite.toml
+++ b/providers/aihubmix/models/gemini-3.1-flash-lite.toml
@@ -1,7 +1,7 @@
 name = "Gemini 3.1 Flash Lite"
 family = "gemini-flash-lite"
-release_date = "2026-03-03"
-last_updated = "2026-03-03"
+release_date = "2026-05-07"
+last_updated = "2026-05-07"
 attachment = true
 reasoning = true
 temperature = true
@@ -13,7 +13,8 @@ open_weights = false
 [cost]
 input = 0.25
 output = 1.5
-cache_read = 0.25
+cache_read = 0.025
+cache_write = 1.00
 
 [limit]
 context = 1_048_576
diff --git a/providers/aihubmix/models/gemini-3.1-pro-preview.toml b/providers/aihubmix/models/gemini-3.1-pro-preview.toml
index 578ffc3f7..fe7bee35a 100644
--- a/providers/aihubmix/models/gemini-3.1-pro-preview.toml
+++ b/providers/aihubmix/models/gemini-3.1-pro-preview.toml
@@ -15,6 +15,12 @@ input = 2
 output = 12
 cache_read = 0.2
 
+[[cost.tiers]]
+tier = { size = 200_000 }
+input = 4.00
+output = 18.00
+cache_read = 0.40
+
 [limit]
 context = 1_048_576
 output = 65_536
diff --git a/providers/aihubmix/models/glm-5v-turbo.toml b/providers/aihubmix/models/glm-5v-turbo.toml
index 7fafd7d21..0a2a754e6 100644
--- a/providers/aihubmix/models/glm-5v-turbo.toml
+++ b/providers/aihubmix/models/glm-5v-turbo.toml
@@ -1,5 +1,5 @@
 name = "GLM 5 Vision Turbo"
-family = "glm"
+family = "glmv"
 release_date = "2026-05-09"
 last_updated = "2026-05-09"
 attachment = true
diff --git a/providers/aihubmix/models/gpt-4.1-mini.toml b/providers/aihubmix/models/gpt-4.1-mini.toml
deleted file mode 100644
index 5fb3e3b9a..000000000
--- a/providers/aihubmix/models/gpt-4.1-mini.toml
+++ /dev/null
@@ -1,23 +0,0 @@
-name = "GPT-4.1 mini"
-family = "gpt-mini"
-release_date = "2025-04-14"
-last_updated = "2025-04-14"
-attachment = true
-reasoning = false
-temperature = true
-knowledge = "2024-04"
-tool_call = true
-open_weights = false
-
-[cost]
-input = 0.40
-output = 1.60
-cache_read = 0.10
-
-[limit]
-context = 1_047_576
-output = 32_768
-
-[modalities]
-input = ["text", "image"]
-output = ["text"]
diff --git a/providers/aihubmix/models/gpt-4.1.toml b/providers/aihubmix/models/gpt-4.1.toml
deleted file mode 100644
index d02038bf0..000000000
--- a/providers/aihubmix/models/gpt-4.1.toml
+++ /dev/null
@@ -1,23 +0,0 @@
-name = "GPT-4.1"
-family = "gpt"
-release_date = "2025-04-14"
-last_updated = "2025-04-14"
-attachment = true
-reasoning = false
-temperature = true
-knowledge = "2024-04"
-tool_call = true
-open_weights = false
-
-[cost]
-input = 2.00
-output = 8.00
-cache_read = 0.50
-
-[limit]
-context = 1_047_576
-output = 32_768
-
-[modalities]
-input = ["text", "image"]
-output = ["text"]
diff --git a/providers/aihubmix/models/gpt-5.1-codex-mini.toml b/providers/aihubmix/models/gpt-5.1-codex-mini.toml
index 4bfee8743..276c2219d 100644
--- a/providers/aihubmix/models/gpt-5.1-codex-mini.toml
+++ b/providers/aihubmix/models/gpt-5.1-codex-mini.toml
@@ -5,20 +5,20 @@ last_updated = "2025-11-13"
 attachment = true
 reasoning = true
 temperature = false
+knowledge = "2024-09-30"
 tool_call = true
 structured_output = true
-knowledge = "2024-09-30"
 open_weights = false
 
 [cost]
 input = 0.25
-output = 2
+output = 2.00
 cache_read = 0.025
 
 [limit]
 context = 400_000
-output = 128_000
 input = 272_000
+output = 128_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/aihubmix/models/gpt-5.1-codex.toml b/providers/aihubmix/models/gpt-5.1-codex.toml
index 176cf35d7..9c1bd825e 100644
--- a/providers/aihubmix/models/gpt-5.1-codex.toml
+++ b/providers/aihubmix/models/gpt-5.1-codex.toml
@@ -5,20 +5,20 @@ last_updated = "2025-11-13"
 attachment = true
 reasoning = true
 temperature = false
+knowledge = "2024-09-30"
 tool_call = true
 structured_output = true
-knowledge = "2024-09-30"
 open_weights = false
 
 [cost]
 input = 1.25
-output = 10
+output = 10.00
 cache_read = 0.125
 
 [limit]
 context = 400_000
-output = 128_000
 input = 272_000
+output = 128_000
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/aihubmix/models/gpt-5.1.toml b/providers/aihubmix/models/gpt-5.1.toml
index 04b94a5a4..35698079f 100644
--- a/providers/aihubmix/models/gpt-5.1.toml
+++ b/providers/aihubmix/models/gpt-5.1.toml
@@ -1,21 +1,23 @@
 name = "GPT-5.1"
 family = "gpt"
-release_date = "2025-11-15"
-last_updated = "2025-11-15"
+release_date = "2025-11-13"
+last_updated = "2025-11-13"
 attachment = true
 reasoning = true
-temperature = true
+temperature = false
+knowledge = "2024-09-30"
 tool_call = true
-knowledge = "2025-11"
+structured_output = true
 open_weights = false
 
 [cost]
 input = 1.25
 output = 10.00
-cache_read = 0.125
+cache_read = 0.13
 
 [limit]
 context = 400_000
+input = 272_000
 output = 128_000
 
 [modalities]
diff --git a/providers/aihubmix/models/gpt-5.2-codex.toml b/providers/aihubmix/models/gpt-5.2-codex.toml
index 2f50fc1ee..d40e33be6 100644
--- a/providers/aihubmix/models/gpt-5.2-codex.toml
+++ b/providers/aihubmix/models/gpt-5.2-codex.toml
@@ -1,9 +1,10 @@
-name = "GPT-5.2-Codex"
+name = "GPT-5.2 Codex"
 family = "gpt-codex"
-release_date = "2026-01-14"
-last_updated = "2026-01-14"
+release_date = "2025-12-11"
+last_updated = "2025-12-11"
 attachment = true
 reasoning = true
+temperature = false
 knowledge = "2025-08-31"
 tool_call = true
 structured_output = true
@@ -16,8 +17,9 @@ cache_read = 0.175
 
 [limit]
 context = 400_000
+input = 272_000
 output = 128_000
 
 [modalities]
-input = ["text", "image"]
+input = ["text", "image", "pdf"]
 output = ["text"]
diff --git a/providers/aihubmix/models/gpt-5.2.toml b/providers/aihubmix/models/gpt-5.2.toml
index 30b2c49cb..68874e272 100644
--- a/providers/aihubmix/models/gpt-5.2.toml
+++ b/providers/aihubmix/models/gpt-5.2.toml
@@ -7,6 +7,7 @@ reasoning = true
 temperature = false
 knowledge = "2025-08-31"
 tool_call = true
+structured_output = true
 open_weights = false
 
 [cost]
@@ -16,6 +17,7 @@ cache_read = 0.175
 
 [limit]
 context = 400_000
+input = 272_000
 output = 128_000
 
 [modalities]
diff --git a/providers/aihubmix/models/gpt-5.3-codex.toml b/providers/aihubmix/models/gpt-5.3-codex.toml
index 99c4809db..0eae309f5 100644
--- a/providers/aihubmix/models/gpt-5.3-codex.toml
+++ b/providers/aihubmix/models/gpt-5.3-codex.toml
@@ -5,20 +5,20 @@ last_updated = "2026-02-05"
 attachment = true
 reasoning = true
 temperature = false
+knowledge = "2025-08-31"
 tool_call = true
 structured_output = true
-knowledge = "2025-08-31"
 open_weights = false
 
 [cost]
 input = 1.75
-output = 14
+output = 14.00
 cache_read = 0.175
 
 [limit]
 context = 400_000
-output = 128_000
 input = 272_000
+output = 128_000
 
 [modalities]
 input = ["text", "image", "pdf"]
diff --git a/providers/aihubmix/models/gpt-5.4-mini.toml b/providers/aihubmix/models/gpt-5.4-mini.toml
index fbf3952c5..0cbdf9444 100644
--- a/providers/aihubmix/models/gpt-5.4-mini.toml
+++ b/providers/aihubmix/models/gpt-5.4-mini.toml
@@ -1,13 +1,14 @@
-name = "GPT-5.4-Mini"
+name = "GPT-5.4 mini"
 family = "gpt-mini"
-release_date = "2026-03-11"
-last_updated = "2026-03-11"
+release_date = "2026-03-17"
+last_updated = "2026-03-17"
 attachment = true
-reasoning = false
+reasoning = true
 temperature = false
+knowledge = "2025-08-31"
 tool_call = true
-open_weights = false
 structured_output = true
+open_weights = false
 
 [cost]
 input = 0.75
@@ -16,8 +17,13 @@ cache_read = 0.075
 
 [limit]
 context = 400_000
+input = 272_000
 output = 128_000
 
 [modalities]
 input = ["text", "image"]
 output = ["text"]
+
+[experimental.modes.fast]
+cost = { input = 1.50, output = 9.00, cache_read = 0.15 }
+provider = { body = { service_tier = "priority" } }
diff --git a/providers/aihubmix/models/gpt-5.4.toml b/providers/aihubmix/models/gpt-5.4.toml
index 0ceaaa811..aeecc03de 100644
--- a/providers/aihubmix/models/gpt-5.4.toml
+++ b/providers/aihubmix/models/gpt-5.4.toml
@@ -1,23 +1,35 @@
 name = "GPT-5.4"
 family = "gpt"
-release_date = "2026-03-11"
-last_updated = "2026-03-11"
+release_date = "2026-03-05"
+last_updated = "2026-03-05"
 attachment = true
 reasoning = true
 temperature = false
+knowledge = "2025-08-31"
 tool_call = true
-open_weights = false
 structured_output = true
+open_weights = false
 
 [cost]
 input = 2.50
 output = 15.00
 cache_read = 0.25
 
+[[cost.tiers]]
+tier = { size = 272_000 }
+input = 5.00
+output = 22.50
+cache_read = 0.50
+
 [limit]
-context = 400_000
+context = 1_050_000
+input = 922_000
 output = 128_000
 
 [modalities]
-input = ["text", "image"]
+input = ["text", "image", "pdf"]
 output = ["text"]
+
+[experimental.modes.fast]
+cost = { input = 5.00, output = 30.00, cache_read = 0.50 }
+provider = { body = { service_tier = "priority" } }
diff --git a/providers/aihubmix/models/gpt-5.5.toml b/providers/aihubmix/models/gpt-5.5.toml
index 362b22e20..9f53fa802 100644
--- a/providers/aihubmix/models/gpt-5.5.toml
+++ b/providers/aihubmix/models/gpt-5.5.toml
@@ -5,20 +5,31 @@ last_updated = "2026-04-23"
 attachment = true
 reasoning = true
 temperature = false
+knowledge = "2025-12-01"
 tool_call = true
 structured_output = true
-knowledge = "2025-12-01"
 open_weights = false
 
 [cost]
-input = 5
-output = 30
-cache_read = 0.5
+input = 5.00
+output = 30.00
+cache_read = 0.50
+
+[[cost.tiers]]
+tier = { size = 272_000 }
+input = 10.00
+output = 45.00
+cache_read = 1.00
 
 [limit]
 context = 1_050_000
+input = 922_000
 output = 128_000
 
 [modalities]
 input = ["text", "image", "pdf"]
 output = ["text"]
+
+[experimental.modes.fast]
+cost = { input = 12.50, output = 75.00, cache_read = 1.25 }
+provider = { body = { service_tier = "priority" } }
diff --git a/providers/aihubmix/models/kimi-k2-thinking b/providers/aihubmix/models/kimi-k2-thinking
deleted file mode 100644
index e546856d5..000000000
--- a/providers/aihubmix/models/kimi-k2-thinking
+++ /dev/null
@@ -1,23 +0,0 @@
-name = "Kimi-K2-Thinking"
-family = "kimi"
-release_date = "2025-11-06"
-last_updated = "2025-11-06"
-attachment = false
-reasoning = true
-temperature = true
-knowledge = "2025-11"
-tool_call = true
-open_weights = true
-
-[cost]
-input = 0.55
-output = 2.19
-cache_read = 0.14
-
-[limit]
-context = 128_000
-output = 64_000
-
-[modalities]
-input = ["text"]
-output = ["text"]
diff --git a/providers/aihubmix/models/kimi-k2.5.toml b/providers/aihubmix/models/kimi-k2.5.toml
index 2e4a3c05c..1cba47c26 100644
--- a/providers/aihubmix/models/kimi-k2.5.toml
+++ b/providers/aihubmix/models/kimi-k2.5.toml
@@ -2,7 +2,7 @@ name = "Kimi K2.5"
 family = "kimi-k2.5"
 release_date = "2026-01"
 last_updated = "2026-01"
-attachment = false
+attachment = true
 reasoning = true
 temperature = false
 tool_call = true
@@ -16,11 +16,11 @@ field = "reasoning_content"
 [cost]
 input = 0.6
 output = 3
-cache_read = 0.105
+cache_read = 0.10
 
 [limit]
-context = 256_000
-output = 0
+context = 262_144
+output = 32_768
 
 [modalities]
 input = ["text", "image", "video"]
diff --git a/providers/aihubmix/models/kimi-k2.6.toml b/providers/aihubmix/models/kimi-k2.6.toml
index 5d91d8f1f..5844eea31 100644
--- a/providers/aihubmix/models/kimi-k2.6.toml
+++ b/providers/aihubmix/models/kimi-k2.6.toml
@@ -4,7 +4,7 @@ release_date = "2026-04-21"
 last_updated = "2026-04-21"
 attachment = true
 reasoning = true
-temperature = true
+temperature = false
 tool_call = true
 structured_output = true
 knowledge = "2025-01"
@@ -15,12 +15,12 @@ field = "reasoning_content"
 
 [cost]
 input = 0.95
-output = 3.9995
-cache_read = 0.160835
+output = 4
+cache_read = 0.16
 
 [limit]
 context = 262_144
-output = 262_144
+output = 32_768
 
 [modalities]
 input = ["text", "image", "video"]
diff --git a/providers/aihubmix/models/minimax-m2.7.toml b/providers/aihubmix/models/minimax-m2.7.toml
index 69dc1d386..dbcf1e5fd 100644
--- a/providers/aihubmix/models/minimax-m2.7.toml
+++ b/providers/aihubmix/models/minimax-m2.7.toml
@@ -1,4 +1,4 @@
-name = "MiniMax-M2.7"
+name = "MiniMax M2.7"
 family = "minimax"
 release_date = "2026-03-18"
 last_updated = "2026-03-18"
@@ -6,15 +6,20 @@ attachment = false
 reasoning = true
 temperature = true
 tool_call = true
+structured_output = true
 open_weights = true
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
-input = 0.2958
-output = 1.1832
-cache_read = 0.05916
+input = 0.3
+output = 1.2
+cache_read = 0.06
+cache_write = 0.375
 
 [limit]
-context = 200_000
+context = 204_800
 output = 128_000
 
 [modalities]
diff --git a/providers/aihubmix/models/o4-mini.toml b/providers/aihubmix/models/o4-mini.toml
deleted file mode 100644
index 7cd4ab461..000000000
--- a/providers/aihubmix/models/o4-mini.toml
+++ /dev/null
@@ -1,24 +0,0 @@
-name = "o4-mini"
-family = "o-mini"
-release_date = "2025-04-16"
-last_updated = "2025-04-16"
-attachment = true
-reasoning = true
-temperature = false
-tool_call = true
-structured_output = true
-knowledge = "2024-05"
-open_weights = false
-
-[cost]
-input = 1.1
-output = 4.4
-cache_read = 0.275
-
-[limit]
-context = 200_000
-output = 100_000
-
-[modalities]
-input = ["text", "image"]
-output = ["text"]
diff --git a/providers/aihubmix/models/qwen3.6-flash.toml b/providers/aihubmix/models/qwen3.6-flash.toml
index c2676f3d6..f96ff7389 100644
--- a/providers/aihubmix/models/qwen3.6-flash.toml
+++ b/providers/aihubmix/models/qwen3.6-flash.toml
@@ -1,5 +1,5 @@
 name = "Qwen3.6 Flash"
-family = "qwen"
+family = "qwen3.6"
 release_date = "2026-04-02"
 last_updated = "2026-04-02"
 attachment = true
@@ -10,12 +10,22 @@ structured_output = true
 knowledge = "2025-04"
 open_weights = false
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
-input = 0.169
-output = 1.014
+input = 0.17
+output = 1.01
 cache_read = 0.0169
 cache_write = 0.21125
 
+[[cost.tiers]]
+tier = { size = 256_000 }
+input = 0.68
+output = 4.06
+cache_read = 0.0676
+cache_write = 0.845
+
 [limit]
 context = 991_000
 output = 64_000
diff --git a/providers/aihubmix/models/qwen3.6-max-preview.toml b/providers/aihubmix/models/qwen3.6-max-preview.toml
index 9a76d18dd..d06ea5b7c 100644
--- a/providers/aihubmix/models/qwen3.6-max-preview.toml
+++ b/providers/aihubmix/models/qwen3.6-max-preview.toml
@@ -1,5 +1,5 @@
 name = "Qwen3.6 Max Preview"
-family = "qwen"
+family = "qwen3.6"
 release_date = "2026-05-09"
 last_updated = "2026-05-09"
 attachment = false
@@ -10,12 +10,22 @@ structured_output = true
 knowledge = "2025-04"
 open_weights = false
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
-input = 1.268
-output = 7.608
+input = 1.27
+output = 7.61
 cache_read = 0.1268
 cache_write = 1.585
 
+[[cost.tiers]]
+tier = { size = 128_000 }
+input = 2.11
+output = 12.67
+cache_read = 0.2112
+cache_write = 2.64
+
 [limit]
 context = 240_000
 output = 64_000
diff --git a/providers/aihubmix/models/qwen3.6-plus.toml b/providers/aihubmix/models/qwen3.6-plus.toml
index bc4e3689d..065a2ada1 100644
--- a/providers/aihubmix/models/qwen3.6-plus.toml
+++ b/providers/aihubmix/models/qwen3.6-plus.toml
@@ -1,5 +1,5 @@
 name = "Qwen3.6 Plus"
-family = "qwen"
+family = "qwen3.6"
 release_date = "2026-05-09"
 last_updated = "2026-05-09"
 attachment = true
@@ -10,12 +10,22 @@ structured_output = true
 knowledge = "2025-04"
 open_weights = false
 
+[interleaved]
+field = "reasoning_content"
+
 [cost]
-input = 0.282
-output = 1.692
+input = 0.28
+output = 1.69
 cache_read = 0.0282
 cache_write = 0.3525
 
+[[cost.tiers]]
+tier = { size = 256_000 }
+input = 1.13
+output = 6.77
+cache_read = 0.1128
+cache_write = 1.41
+
 [limit]
 context = 991_000
 output = 64_000
diff --git a/providers/aihubmix/models/xiaomi-mimo-v2.5-free.toml b/providers/aihubmix/models/xiaomi-mimo-v2.5-free.toml
new file mode 100644
index 000000000..74c527876
--- /dev/null
+++ b/providers/aihubmix/models/xiaomi-mimo-v2.5-free.toml
@@ -0,0 +1,16 @@
+name = "Xiaomi MiMo-V2.5 (free)"
+family = "mimo-v2.5"
+last_updated = "2026-05-13"
+
+[extends]
+from = "xiaomi/mimo-v2.5"
+omit = ["cost.context_over_200k", "cost.tiers"]
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+
+[limit]
+context = 1_048_576
+output = 131_072
diff --git a/providers/aihubmix/models/xiaomi-mimo-v2.5-pro-free.toml b/providers/aihubmix/models/xiaomi-mimo-v2.5-pro-free.toml
new file mode 100644
index 000000000..785f68786
--- /dev/null
+++ b/providers/aihubmix/models/xiaomi-mimo-v2.5-pro-free.toml
@@ -0,0 +1,16 @@
+name = "Xiaomi MiMo-V2.5-Pro (free)"
+family = "mimo-v2.5-pro"
+last_updated = "2026-05-13"
+
+[extends]
+from = "xiaomi/mimo-v2.5-pro"
+omit = ["cost.context_over_200k", "cost.tiers"]
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+
+[limit]
+context = 1_048_576
+output = 131_072
diff --git a/providers/aihubmix/models/xiaomi-mimo-v2.5-pro.toml b/providers/aihubmix/models/xiaomi-mimo-v2.5-pro.toml
new file mode 100644
index 000000000..7bff36e93
--- /dev/null
+++ b/providers/aihubmix/models/xiaomi-mimo-v2.5-pro.toml
@@ -0,0 +1,17 @@
+name = "Xiaomi MiMo-V2.5-Pro"
+family = "mimo-v2.5-pro"
+last_updated = "2026-05-13"
+
+[extends]
+from = "xiaomi/mimo-v2.5-pro"
+
+[cost]
+input = 1.10
+output = 3.30
+cache_read = 0.22
+
+[[cost.tiers]]
+tier = { size = 256_000 }
+input = 2.20
+output = 6.60
+cache_read = 0.44
diff --git a/providers/aihubmix/models/xiaomi-mimo-v2.5.toml b/providers/aihubmix/models/xiaomi-mimo-v2.5.toml
new file mode 100644
index 000000000..588984ecb
--- /dev/null
+++ b/providers/aihubmix/models/xiaomi-mimo-v2.5.toml
@@ -0,0 +1,17 @@
+name = "Xiaomi MiMo-V2.5"
+family = "mimo-v2.5"
+last_updated = "2026-05-13"
+
+[extends]
+from = "xiaomi/mimo-v2.5"
+
+[cost]
+input = 0.44
+output = 2.20
+cache_read = 0.088
+
+[[cost.tiers]]
+tier = { size = 256_000 }
+input = 0.88
+output = 4.40
+cache_read = 0.176
diff --git a/providers/aihubmix/models/glm-5.1.toml b/providers/aihubmix/models/zai-glm-5.1.toml
similarity index 89%
rename from providers/aihubmix/models/glm-5.1.toml
rename to providers/aihubmix/models/zai-glm-5.1.toml
index d43be1dae..8b7d49e2e 100644
--- a/providers/aihubmix/models/glm-5.1.toml
+++ b/providers/aihubmix/models/zai-glm-5.1.toml
@@ -1,4 +1,4 @@
-name = "GLM-5.1"
+name = "GLM-5.1 (Z.ai)"
 family = "glm"
 release_date = "2026-03-27"
 last_updated = "2026-03-27"
@@ -7,7 +7,7 @@ reasoning = true
 temperature = true
 tool_call = true
 structured_output = true
-open_weights = false
+open_weights = true
 
 [interleaved]
 field = "reasoning_content"