chore: update models.yaml

1 files changed, 165 insertions, 130 deletions

diff --git a/models.yaml b/models.yaml
index 5ff4e22..a663095 100644
--- a/models.yaml
+++ b/models.yaml
@@ -93,7 +93,7 @@
       system_prompt_prefix: Formatting re-enabled
       patch:
         body:
-          reasoning_effort: high 
+          reasoning_effort: high
           max_tokens: null
           temperature: null
           top_p: null
@@ -131,7 +131,7 @@
       system_prompt_prefix: Formatting re-enabled
       patch:
         body:
-          reasoning_effort: high 
+          reasoning_effort: high
           max_tokens: null
           temperature: null
           top_p: null
@@ -281,7 +281,7 @@
         body:
           temperature: null
           top_p: null
-          thinking: 
+          thinking:
             type: enabled
             budget_tokens: 16000
     - name: claude-3-5-sonnet-20241022
@@ -491,7 +491,7 @@
       supports_function_calling: true
 
 # Links:
-#  - https://docs.perplexity.ai/guides/model-cards
+#  - https://docs.perplexity.ai/models/model-cards
 #  - https://docs.perplexity.ai/guides/pricing
 #  - https://docs.perplexity.ai/api-reference/chat-completions
 - provider: perplexity
@@ -581,7 +581,7 @@
       output_price: 0.6
       supports_vision: true
       supports_function_calling: true
-    - name: gemini-2.5-pro-preview-03-25
+    - name: gemini-2.5-pro-preview-05-06
       max_input_tokens: 1048576
       max_output_tokens: 65536
       input_price: 1.25
@@ -622,7 +622,7 @@
         body:
           temperature: null
           top_p: null
-          thinking: 
+          thinking:
             type: enabled
             budget_tokens: 16000
     - name: claude-3-5-sonnet-v2@20241022
@@ -732,7 +732,7 @@
             temperature: null
             topP: null
           additionalModelRequestFields:
-            thinking: 
+            thinking:
               type: enabled
               budget_tokens: 16000
     - name: anthropic.claude-3-5-sonnet-20241022-v2:0
@@ -783,6 +783,22 @@
       output_price: 1.25
       supports_vision: true
       supports_function_calling: true
+    - name: us.meta.llama4-maverick-17b-instruct-v1:0
+      max_input_tokens: 131072
+      max_output_tokens: 8192
+      require_max_tokens: true
+      input_price: 0.24
+      output_price: 0.97
+      supports_function_calling: true
+      supports_vision: true
+    - name: us.meta.llama4-scout-17b-instruct-v1:0
+      max_input_tokens: 131072
+      max_output_tokens: 8192
+      require_max_tokens: true
+      input_price: 0.17
+      output_price: 0.66
+      supports_function_calling: true
+      supports_vision: true
     - name: us.meta.llama3-3-70b-instruct-v1:0
       max_input_tokens: 131072
       max_output_tokens: 8192
@@ -811,22 +827,11 @@
       input_price: 0.22
       output_price: 0.22
       supports_function_calling: true
-    - name: us.meta.llama3-2-90b-instruct-v1:0
-      max_input_tokens: 131072
-      max_output_tokens: 8192
-      require_max_tokens: true
-      input_price: 0.72
-      output_price: 0.72
-      supports_function_calling: true
-      supports_vision: true
-    - name: us.meta.llama3-2-11b-instruct-v1:0
-      max_input_tokens: 131072
-      max_output_tokens: 8192
-      require_max_tokens: true
-      input_price: 0.16
-      output_price: 0.16
-      supports_function_calling: true
-      supports_vision: true
+    - name: us.amazon.nova-premier-v1:0
+      max_input_tokens: 300000
+      max_output_tokens: 5120
+      input_price: 2.5
+      output_price: 12.5
     - name: us.amazon.nova-pro-v1:0
       max_input_tokens: 300000
       max_output_tokens: 5120
@@ -849,6 +854,11 @@
       input_price: 2
       output_price: 6
       supports_function_calling: true
+    - name: us.mistral.pixtral-large-2502-v1:0
+      max_input_tokens: 128000
+      input_price: 2
+      output_price: 6
+      supports_vision: true
     - name: cohere.command-r-plus-v1:0
       max_input_tokens: 128000
       input_price: 3
@@ -948,42 +958,23 @@
 
 # Links:
 #  - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Wm9cvy6rl
-#  - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
+#  - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Qm9cw2s7m
 - provider: ernie
   models:
-    - name: ernie-4.5-8k-preview
-      max_input_tokens: 8192
-      input_price: 0.56
-      output_price: 2.24
+    - name: ernie-4.5-turbo-128k
+      max_input_tokens: 131072
+      input_price: 0.112
+      output_price: 0.448
       supports_function_calling: true
-    - name: ernie-x1-32k-preview
+    - name: ernie-4.5-turbo-vl-32k
       max_input_tokens: 32768
-      input_price: 0.28
-      output_price: 1.12
-    - name: ernie-4.0-turbo-8k-latest
-      max_input_tokens: 8192
       input_price: 0.42
       output_price: 1.26
-      supports_function_calling: true
-    - name: ernie-4.0-turbo-128k
-      max_input_tokens: 128000
-      input_price: 0.42
-      output_price: 1.26
-      supports_function_calling: true
-    - name: ernie-4.0-8k-latest
-      max_input_tokens: 8192
-      input_price: 0.56
-      output_price: 2.24
-      supports_function_calling: true
-    - name: ernie-3.5-128k
-      max_input_tokens: 128000
-      input_price: 0.112
-      output_price: 0.28
-      supports_function_calling: true
-    - name: ernie-speed-pro-128k
-      max_input_tokens: 128000
-      input_price: 0.042
-      output_price: 0.084
+      supports_vision: true
+    - name: ernie-x1-turbo-32k
+      max_input_tokens: 32768
+      input_price: 0.14
+      output_price: 0.56
     - name: deepseek-v3
       max_input_tokens: 131072
       input_price: 0.112
@@ -992,6 +983,14 @@
       max_input_tokens: 131072
       input_price: 0.28
       output_price: 1.12
+    - name: qwen3-235b-a22b
+      max_input_tokens: 131072
+      input_price: 0.56
+      output_price: 1.68
+    - name: qwen3-30b-a3b
+      max_input_tokens: 131072
+      input_price: 0.21
+      output_price: 0.84
     - name: qwq-32b
       max_input_tokens: 131072
       input_price: 0.28
@@ -1048,9 +1047,9 @@
     - name: qwq-plus-latest
       max_input_tokens: 131072
       max_output_tokens: 8192
-    - name: qwq-32b
-      max_input_tokens: 131072
-      max_output_tokens: 8192
+      input_price: 0.224
+      output_price: 0.56
+
     - name: qwen-vl-max-latest
       max_input_tokens: 30720
       max_output_tokens: 2048
@@ -1063,13 +1062,33 @@
       input_price: 0.21
       output_price: 0.63
       supports_vision: true
+    - name: qwen3-235b-a22b
+      max_input_tokens: 131072
+      max_output_tokens: 8192
+      input_price: 0.56
+      output_price: 1.68
+    - name: qwen3-30b-a3b
+      max_input_tokens: 131072
+      max_output_tokens: 8192
+      input_price: 0.21
+      output_price: 0.84
+    - name: qwen3-32b
+      max_input_tokens: 131072
+      max_output_tokens: 8192
+      input_price: 0.28
+      output_price: 1.12
+    - name: qwq-32b
+      max_input_tokens: 131072
+      max_output_tokens: 8192
+      input_price: 0.28
+      output_price: 0.84
     - name: qwen2.5-72b-instruct
       max_input_tokens: 129024
       max_output_tokens: 8192
       input_price: 0.56
       output_price: 1.68
       supports_function_calling: true
-    - name: qwen2.5-vl-72b-instruct 
+    - name: qwen2.5-vl-72b-instruct
       max_input_tokens: 129024
       max_output_tokens: 8192
       input_price: 2.24
@@ -1081,11 +1100,11 @@
       input_price: 0.49
       output_price: 0.98
       supports_function_calling: true
-    - name: deepseek-v3 
+    - name: deepseek-v3
       max_input_tokens: 65792
       input_price: 0.14
       output_price: 0.56
-    - name: deepseek-r1 
+    - name: deepseek-r1
       max_input_tokens: 65792
       input_price: 0.28
       output_price: 1.12
@@ -1119,24 +1138,12 @@
       max_output_tokens: 64000
       input_price: 0.14
       output_price: 0.56
-    - name: hunyuan-turbo-latest
-      max_input_tokens: 28000
-      max_output_tokens: 4096
-      input_price: 0.336
-      output_price: 1.344
-      supports_function_calling: true
     - name: hunyuan-large
       max_input_tokens: 28000
       max_output_tokens: 4096
       input_price: 0.56
       output_price: 1.68
       supports_function_calling: true
-    - name: hunyuan-large-longcontext
-      max_input_tokens: 128000
-      max_output_tokens: 6144
-      input_price: 0.84
-      output_price: 2.52
-      supports_function_calling: true
     - name: hunyuan-standard
       max_input_tokens: 30000
       max_output_tokens: 2048
@@ -1155,11 +1162,11 @@
       input_price: 0
       output_price: 0
       supports_function_calling: true
-    - name: hunyuan-turbo-vision
+    - name: hunyuan-turbos-vision
       max_input_tokens: 6144
       max_output_tokens: 2048
-      input_price: 11.2
-      output_price: 11.2
+      input_price: 0.42
+      output_price: 0.84
       supports_vision: true
     - name: hunyuan-vision
       max_input_tokens: 6144
@@ -1180,8 +1187,16 @@
 - provider: moonshot
   models:
     - name: kimi-latest
+      max_input_tokens: 131072
+      input_price: 1.4
+      output_price: 4.2
       supports_vision: true
       supports_function_calling: true
+    - name: kimi-thinking-preview
+      max_input_tokens: 131072
+      input_price: 28
+      output_price: 28
+      supports_vision: true
     - name: moonshot-v1-8k
       max_input_tokens: 8192
       input_price: 1.68
@@ -1236,16 +1251,14 @@
 - provider: zhipuai
   models:
     - name: glm-4-plus
-      max_input_tokens: 128000
-      max_output_tokens: 4096
-      input_price: 7
-      output_price: 7
+      max_input_tokens: 131072
+      input_price: 0.7
+      output_price: 0.7
       supports_function_calling: true
-    - name: glm-4-alltools
-      max_input_tokens: 128000
-      max_output_tokens: 4096
-      input_price: 14
-      output_price: 14
+    - name: glm-4-air
+      max_input_tokens: 131072
+      input_price: 0.07
+      output_price: 0.07
       supports_function_calling: true
     - name: glm-4-long
       max_input_tokens: 1000000
@@ -1253,13 +1266,12 @@
       input_price: 0.14
       output_price: 0.14
       supports_function_calling: true
-    - name: glm-4-flash
-      max_input_tokens: 128000
-      max_output_tokens: 4096
+    - name: glm-4-flash-250414
+      max_input_tokens: 131072
       input_price: 0
       output_price: 0
       supports_function_calling: true
-    - name: glm-4v-plus
+    - name: glm-4v-plus-0111
       max_input_tokens: 8192
       input_price: 0.56
       output_price: 0.56
@@ -1269,10 +1281,14 @@
       input_price: 0
       output_price: 0
       supports_vision: true
-    - name: glm-zero-preview
-      max_input_tokens: 16384
-      input_price: 1.4
-      output_price: 1.4
+    - name: glm-z1-air
+      max_input_tokens: 131072
+      input_price: 0.7
+      output_price: 0.7
+    - name: glm-z1-flash
+      max_input_tokens: 131072
+      input_price: 0
+      output_price: 0
     - name: embedding-3
       type: embedding
       max_input_tokens: 8192
@@ -1409,7 +1425,7 @@
       system_prompt_prefix: Formatting re-enabled
       patch:
         body:
-          reasoning_effort: high 
+          reasoning_effort: high
           max_tokens: null
           temperature: null
           top_p: null
@@ -1491,7 +1507,7 @@
       supports_vision: true
       supports_function_calling: true
     - name: google/gemini-2.0-flash-lite-001
-      max_input_tokens: 1048576 
+      max_input_tokens: 1048576
       input_price: 0.075
       output_price: 0.3
       supports_vision: true
@@ -1507,7 +1523,7 @@
       input_price: 0.15
       output_price: 0.6
       supports_vision: true
-    - name: google/gemini-2.5-pro-preview-03-25
+    - name: google/gemini-2.5-pro-preview
       max_input_tokens: 1048576
       input_price: 1.25
       output_price: 10
@@ -1600,7 +1616,7 @@
       supports_vision: true
       supports_function_calling: true
     - name: meta-llama/llama-4-scout
-      max_input_tokens: 327680 
+      max_input_tokens: 327680
       input_price: 0.08
       output_price: 0.3
       supports_vision: true
@@ -1623,16 +1639,6 @@
       max_input_tokens: 131072
       input_price: 0.02
       output_price: 0.05
-    - name: meta-llama/llama-3.2-90b-vision-instruct
-      max_input_tokens: 131072
-      input_price: 0.9
-      output_price: 0.9
-      supports_vision: true
-    - name: meta-llama/llama-3.2-11b-vision-instruct
-      max_input_tokens: 131072
-      input_price: 0.055
-      output_price: 0.055
-      supports_vision: true
     - name: mistralai/mistral-large-2411
       max_input_tokens: 128000
       input_price: 2
@@ -1732,6 +1738,18 @@
       input_price: 0.21
       output_price: 0.63
       supports_vision: true
+    - name: qwen/qwen3-235b-a22b
+      max_input_tokens: 40960
+      input_price: 0.15
+      output_price: 0.6
+    - name: qwen/qwen3-30b-a3b
+      max_input_tokens: 40960
+      input_price: 0.1
+      output_price: 0.3
+    - name: qwen/qwen3-32b
+      max_input_tokens: 40960
+      input_price: 0.1
+      output_price: 0.3
     - name: qwen/qwq-32b
       max_input_tokens: 128000
       input_price: 0.29
@@ -1827,7 +1845,18 @@
       max_input_tokens: 1000192
       input_price: 0.2
       output_price: 1.1
-
+    - name: thudm/glm-4-32b
+      max_input_tokens: 32000
+      input_price: 0.24
+      output_price: 0.24
+    - name: thudm/glm-z1-32b
+      max_input_tokens: 32000
+      input_price: 0.24
+      output_price: 0.24
+    - name: microsoft/phi-4-reasoning-plus
+      max_input_tokens: 32768
+      input_price: 0.07
+      output_price: 0.35
 
 # Links:
 #  - https://github.com/marketplace?type=models
@@ -1943,7 +1972,7 @@
       max_input_tokens: 1048576
       supports_vision: true
     - name: llama-4-scout-17b-16e-instruct
-      max_input_tokens: 327680 
+      max_input_tokens: 327680
       supports_vision: true
     - name: llama-3.3-70b-instruct
       max_input_tokens: 131072
@@ -1953,12 +1982,6 @@
       max_input_tokens: 131072
     - name: meta-llama-3.1-8b-instruct
       max_input_tokens: 131072
-    - name: llama-3.2-90b-vision-instruct
-      max_input_tokens: 131072
-      supports_vision: true
-    - name: llama-3.2-11b-vision-instruct
-      max_input_tokens: 131072
-      supports_vision: true
     - name: mistral-large-2411
       max_input_tokens: 128000
       supports_function_calling: true
@@ -2002,7 +2025,11 @@
     - name: phi-4
       max_input_tokens: 16384
     - name: phi-4-mini-instruct
-      max_input_tokens: 128000
+      max_input_tokens: 131072
+    - name: phi-4-reasoning
+      max_input_tokens: 33792
+    - name: phi-4-mini-reasoning
+      max_input_tokens: 131072
 
 # Links:
 #  - https://deepinfra.com/models
@@ -2015,7 +2042,7 @@
       output_price: 0.6
       supports_vision: true
     - name: meta-llama/Llama-4-Scout-17B-16E-Instruct
-      max_input_tokens: 327680 
+      max_input_tokens: 327680
       input_price: 0.08
       output_price: 0.3
       supports_vision: true
@@ -2038,23 +2065,27 @@
       input_price: 0.03
       output_price: 0.05
       supports_function_calling: true
-    - name: meta-llama/Llama-3.2-90B-Vision-Instruct
-      max_input_tokens: 131072
-      input_price: 0.35
-      output_price: 0.4
-    - name: meta-llama/Llama-3.2-11B-Vision-Instruct
+    - name: Qwen/Qwen3-235B-A22B
+      max_input_tokens: 40960
+      input_price: 0.15
+      output_price: 0.6
+    - name: Qwen/Qwen3-30B-A3B
+      max_input_tokens: 40960
+      input_price: 0.1
+      output_price: 0.3
+    - name: Qwen/Qwen3-32B
+      max_input_tokens: 40960
+      input_price: 0.1
+      output_price: 0.3
+    - name: Qwen/QwQ-32B
       max_input_tokens: 131072
-      input_price: 0.055
-      output_price: 0.055
+      input_price: 0.12
+      output_price: 0.18
     - name: Qwen/Qwen2.5-72B-Instruct
       max_input_tokens: 32768
       input_price: 0.23
       output_price: 0.40
       supports_function_calling: true
-    - name: Qwen/QwQ-32B
-      max_input_tokens: 131072
-      input_price: 0.12
-      output_price: 0.18
     - name: Qwen/Qwen2.5-Coder-32B-Instruct
       max_input_tokens: 32768
       input_price: 0.07
@@ -2079,6 +2110,10 @@
       max_input_tokens: 131072
       input_price: 0.035
       output_price: 0.08
+    - name: microsoft/phi-4-reasoning-plus
+      max_input_tokens: 32768
+      input_price: 0.07
+      output_price: 0.35
     - name: BAAI/bge-large-en-v1.5
       type: embedding
       input_price: 0.01
@@ -2121,23 +2156,23 @@
       max_tokens_per_chunk: 8192
       default_chunk_size: 2000
       max_batch_size: 100
-    - name: jina-colbert-v2
+    - name: jina-clip-v2
       type: embedding
       input_price: 0
       max_tokens_per_chunk: 8192
       default_chunk_size: 1500
       max_batch_size: 100
-    - name: jina-clip-v2
+    - name: jina-colbert-v2
       type: embedding
       input_price: 0
       max_tokens_per_chunk: 8192
       default_chunk_size: 1500
       max_batch_size: 100
-    - name: jina-colbert-v2
+    - name: jina-reranker-v2-base-multilingual
       type: reranker
       max_input_tokens: 8192
       input_price: 0
-    - name: jina-reranker-v2-base-multilingual
+    - name: jina-colbert-v2
       type: reranker
       max_input_tokens: 8192
       input_price: 0