chore: refresh generated model catalog [skip ci]

models.yaml

@@ -7010,9 +7010,9 @@
   - name: deepseek/deepseek-v4-flash
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.0886
+    input_price: 0.0484
-    output_price: 0.1772
+    output_price: 0.0969
-    cache_read_price: 0.0177
+    cache_read_price: 0.0097
     max_output_tokens: 384000
     supports_function_calling: true
   - name: deepseek/deepseek-v4-flash-0731
@@ -7059,18 +7059,18 @@
   - name: deepseek/deepseek-v4-pro
     type: chat
     max_input_tokens: 1048576
-    input_price: 1.6
+    input_price: 0.6758
-    output_price: 3.2
+    output_price: 1.3516
-    cache_read_price: 0.135
+    cache_read_price: 0.0563
-    max_output_tokens: 393216
+    max_output_tokens: 384000
     supports_function_calling: true
   - name: deepseek/deepseek-v4-pro-0813
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.66
+    input_price: 0.5782
-    output_price: 1.98
+    output_price: 1.7345
-    cache_read_price: 0.022
+    cache_read_price: 0.0184
-    max_output_tokens: 384000
+    max_output_tokens: 393216
     supports_function_calling: true
   - name: deepseek/deepseek-v4-pro-0813:batch
     type: chat
@@ -7691,8 +7691,8 @@
   - name: meta/muse-glimmer-30b
     type: chat
     max_input_tokens: 131072
-    input_price: 0.3
+    input_price: 0.35
-    output_price: 1.1
+    output_price: 1.5
     cache_read_price: 0.04
     max_output_tokens: 117964
     supports_vision: true
@@ -8083,9 +8083,9 @@
   - name: moonshotai/kimi-k3
     type: chat
     max_input_tokens: 1048576
-    input_price: 2.1
+    input_price: 1.95
-    output_price: 10.95
+    output_price: 10.92
-    cache_read_price: 0.23
+    cache_read_price: 0.2262
     max_output_tokens: 943718
     supports_vision: true
     supports_function_calling: true
@@ -8176,10 +8176,10 @@
   - name: nvidia/nemotron-3-ultra-550b-a55b
     type: chat
     max_input_tokens: 262144
-    input_price: 0.625
+    input_price: 0.6
-    output_price: 3.125
+    output_price: 2.4
-    cache_read_price: 0.1875
+    cache_read_price: 0.12
-    max_output_tokens: 32768
+    max_output_tokens: 182520
     supports_function_calling: true
   - name: nvidia/nemotron-3-ultra-550b-a55b:free
     type: chat
@@ -8205,10 +8205,10 @@
   - name: nvidia/nemotron-3.5-lightning
     type: chat
     max_input_tokens: 262144
-    input_price: 0.08
+    input_price: 0.07
     output_price: 0.2
     cache_read_price: 0.04
-    max_output_tokens: 131072
+    max_output_tokens: 235929
     supports_function_calling: true
   - name: nvidia/nemotron-3.5-lightning:free
     type: chat
@@ -9267,6 +9267,14 @@
     output_price: 0.0
     max_output_tokens: 32768
     supports_function_calling: true
+  - name: prism-ml/ternary-bonsai-2-27b
+    type: chat
+    max_input_tokens: 262144
+    input_price: 0.075
+    output_price: 0.5
+    max_output_tokens: 32768
+    supports_vision: true
+    supports_function_calling: true
   - name: qwen/qwen-2.5-72b-instruct
     type: chat
     max_input_tokens: 32768
@@ -9466,8 +9474,8 @@
   - name: qwen/qwen3-vl-30b-a3b-instruct
     type: chat
     max_input_tokens: 262144
-    input_price: 0.13
+    input_price: 0.2
-    output_price: 0.52
+    output_price: 0.7
     max_output_tokens: 32768
     supports_vision: true
     supports_function_calling: true
@@ -10112,10 +10120,10 @@
   - name: z-ai/glm-5.2
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.5625
+    input_price: 0.5544
-    output_price: 1.8
+    output_price: 1.7424
-    cache_read_price: 0.105
+    cache_read_price: 0.103
-    max_output_tokens: 163840
+    max_output_tokens: 131072
     supports_function_calling: true
   - name: z-ai/glm-5.2:batch
     type: chat
@@ -10134,10 +10142,10 @@
   - name: z-ai/glm-5.3
     type: chat
     max_input_tokens: 1310720
-    input_price: 1.4
+    input_price: 0.91
-    output_price: 4.4
+    output_price: 2.86
-    cache_read_price: 0.26
+    cache_read_price: 0.169
-    max_output_tokens: 943717
+    max_output_tokens: 131072
     supports_function_calling: true
   - name: z-ai/glm-5.3-flash
     type: chat
@@ -10217,27 +10225,27 @@
   - name: ~deepseek/deepseek-flash-latest
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.15
+    input_price: 0.135
-    output_price: 0.6
+    output_price: 0.54
-    cache_read_price: 0.015
+    cache_read_price: 0.0041
     max_output_tokens: 943718
     supports_vision: true
     supports_function_calling: true
   - name: ~deepseek/deepseek-pro-latest
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.66
+    input_price: 0.5782
-    output_price: 1.98
+    output_price: 1.7345
-    cache_read_price: 0.022
+    cache_read_price: 0.0184
-    max_output_tokens: 384000
+    max_output_tokens: 393216
     supports_function_calling: true
   - name: ~deepseek/deepseek-v4-flash-latest
     type: chat
     max_input_tokens: 1310720
-    input_price: 0.0558
+    input_price: 0.0515
-    output_price: 0.1767
+    output_price: 0.1544
-    cache_read_price: 0.0088
+    cache_read_price: 0.0016
-    max_output_tokens: 943718
+    max_output_tokens: 384000
     supports_function_calling: true
   - name: ~google/gemini-flash-latest
     type: chat
@@ -10262,9 +10270,9 @@
   - name: ~moonshotai/kimi-latest
     type: chat
     max_input_tokens: 1048576
-    input_price: 2.1
+    input_price: 1.95
-    output_price: 10.95
+    output_price: 10.92
-    cache_read_price: 0.23
+    cache_read_price: 0.2262
     max_output_tokens: 943718
     supports_vision: true
     supports_function_calling: true
@@ -10338,10 +10346,10 @@
   - name: ~z-ai/glm-latest
     type: chat
     max_input_tokens: 1310720
-    input_price: 0.8775
+    input_price: 0.8918
-    output_price: 2.97
+    output_price: 2.8028
-    cache_read_price: 0.1755
+    cache_read_price: 0.1656
-    max_output_tokens: 235929
+    max_output_tokens: 131072
     supports_function_calling: true
 - provider: github
   models: