From e7549d483b28bfcf298591aa7dfa430534693e4d Mon Sep 17 00:00:00 2001
From: Jason Swank <632526+jswank@users.noreply.github.com>
Date: Wed, 14 Jan 2026 13:14:53 -0500
Subject: [PATCH] aichat config

---
 aichat/.config/aichat/config.yaml          |  12 +-
 aichat/.config/aichat/models-override.yaml | 675 ++++-----------------
 2 files changed, 133 insertions(+), 554 deletions(-)

diff --git a/aichat/.config/aichat/config.yaml b/aichat/.config/aichat/config.yaml
index 4aeea3e..d2fb5d9 100644
--- a/aichat/.config/aichat/config.yaml
+++ b/aichat/.config/aichat/config.yaml
@@ -4,13 +4,15 @@
 # environment variables for aichat can be set at ~/.config/aichat/.env
 
 #model: claude:claude-sonnet-4-5-20250929
-model: gemini:gemini-3-flash-preview 
+#model: gemini:gemini-3-flash-preview 
 keybindings: vi
 repl_prelude: role:cloudops
 clients:
+- type: bedrock
+  name: aws
 - type: claude
 - type: gemini
-- type: openai
-- type: openai-compatible
-  name: moonshot
-  api_base: https://api.moonshot.ai/v1
+#- type: openai
+#- type: openai-compatible
+#  name: moonshot
+#  api_base: https://api.moonshot.ai/v1
diff --git a/aichat/.config/aichat/models-override.yaml b/aichat/.config/aichat/models-override.yaml
index 6649a26..7e4a48f 100644
--- a/aichat/.config/aichat/models-override.yaml
+++ b/aichat/.config/aichat/models-override.yaml
@@ -2,19 +2,11 @@ version: 0.30.0
 list:
 - provider: openai
   models:
-  - name: gpt-5.1
+  - name: gpt-5.2
     type: chat
     max_input_tokens: 400000
-    input_price: 1.25
-    output_price: 10.0
-    max_output_tokens: 128000
-    supports_vision: true
-    supports_function_calling: true
-  - name: gpt-5.1-chat-latest
-    type: chat
-    max_input_tokens: 400000
-    input_price: 1.25
-    output_price: 10.0
+    input_price: 1.75
+    output_price: 14.0
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -26,14 +18,6 @@ list:
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
-  - name: gpt-5-chat-latest
-    type: chat
-    max_input_tokens: 400000
-    input_price: 1.25
-    output_price: 10.0
-    max_output_tokens: 128000
-    supports_vision: true
-    supports_function_calling: true
   - name: gpt-5-mini
     type: chat
     max_input_tokens: 400000
@@ -58,22 +42,6 @@ list:
     max_output_tokens: 32768
     supports_vision: true
     supports_function_calling: true
-  - name: gpt-4.1-mini
-    type: chat
-    max_input_tokens: 1047576
-    input_price: 0.4
-    output_price: 1.6
-    max_output_tokens: 32768
-    supports_vision: true
-    supports_function_calling: true
-  - name: gpt-4.1-nano
-    type: chat
-    max_input_tokens: 1047576
-    input_price: 0.1
-    output_price: 0.4
-    max_output_tokens: 32768
-    supports_vision: true
-    supports_function_calling: true
   - name: gpt-4o
     type: chat
     max_input_tokens: 128000
@@ -82,98 +50,6 @@ list:
     max_output_tokens: 16384
     supports_vision: true
     supports_function_calling: true
-  - name: gpt-4o-mini
-    type: chat
-    max_input_tokens: 128000
-    input_price: 0.15
-    output_price: 0.6
-    max_output_tokens: 16384
-    supports_vision: true
-    supports_function_calling: true
-  - name: o4-mini
-    type: chat
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o4-mini-high
-    type: chat
-    real_name: o4-mini
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        reasoning_effort: high
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3
-    type: chat
-    max_input_tokens: 200000
-    input_price: 2.0
-    output_price: 8.0
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3-high
-    type: chat
-    real_name: o3
-    max_input_tokens: 200000
-    input_price: 2.0
-    output_price: 8.0
-    patch:
-      body:
-        reasoning_effort: high
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3-mini
-    type: chat
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3-mini-high
-    type: chat
-    real_name: o3-mini
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        reasoning_effort: high
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
   - name: gpt-4-turbo
     type: chat
     max_input_tokens: 128000
@@ -203,22 +79,6 @@ list:
     max_batch_size: 100
 - provider: gemini
   models:
-  - name: gemini-3-flash-preview
-    type: chat
-    max_input_tokens: 1048576
-    input_price: 0.0
-    output_price: 0.0
-    max_output_tokens: 65536
-    supports_vision: true
-    supports_function_calling: true
-  - name: gemini-3-pro-preview
-    type: chat
-    max_input_tokens: 1048576
-    input_price: 0.0
-    output_price: 0.0
-    max_output_tokens: 65536
-    supports_vision: true
-    supports_function_calling: true
   - name: gemini-2.5-flash
     type: chat
     max_input_tokens: 1048576
@@ -243,6 +103,16 @@ list:
     max_output_tokens: 64000
     supports_vision: true
     supports_function_calling: true
+  - name: gemini-3-pro-preview
+    type: chat
+    max_input_tokens: 1048576
+    supports_vision: true
+    supports_function_calling: true
+  - name: gemini-3-flash-preview
+    type: chat
+    max_input_tokens: 1048576
+    supports_vision: true
+    supports_function_calling: true
   - name: gemini-2.0-flash
     type: chat
     max_input_tokens: 1048576
@@ -439,6 +309,13 @@ list:
     supports_function_calling: true
 - provider: mistral
   models:
+  - name: mistral-large-latest
+    type: chat
+    input_price: 0.5
+    output_price: 1.5
+    max_output_tokens: 262144
+    supports_vision: true
+    supports_function_calling: true
   - name: mistral-medium-latest
     type: chat
     max_input_tokens: 131072
@@ -455,32 +332,38 @@ list:
     supports_function_calling: true
   - name: magistral-medium-latest
     type: chat
-    max_input_tokens: 40960
+    max_input_tokens: 131072
     input_price: 2.0
     output_price: 5.0
   - name: magistral-small-latest
     type: chat
-    max_input_tokens: 40960
+    max_input_tokens: 131072
     input_price: 0.5
     output_price: 1.5
   - name: devstral-medium-latest
     type: chat
-    max_input_tokens: 256000
+    max_input_tokens: 262144
     input_price: 0.4
     output_price: 2.0
     supports_function_calling: true
   - name: devstral-small-latest
     type: chat
-    max_input_tokens: 256000
+    max_input_tokens: 262144
     input_price: 0.1
     output_price: 0.3
     supports_function_calling: true
   - name: codestral-latest
     type: chat
-    max_input_tokens: 256000
+    max_input_tokens: 262144
     input_price: 0.3
     output_price: 0.9
     supports_function_calling: true
+  - name: ministral-14b-latest
+    type: chat
+    max_input_tokens: 262144
+    input_price: 0.2
+    output_price: 0.2
+    supports_function_calling: true
   - name: mistral-embed
     type: embedding
     max_input_tokens: 8092
@@ -558,42 +441,24 @@ list:
     max_input_tokens: 4096
 - provider: xai
   models:
-  - name: grok-4
-    type: chat
-    max_input_tokens: 256000
-    input_price: 3.0
-    output_price: 15.0
-    supports_function_calling: true
-  - name: grok-4-fast-non-reasoning
+  - name: grok-4-1-fast-non-reasoning
     type: chat
     max_input_tokens: 2000000
     input_price: 0.2
     output_price: 0.5
     supports_function_calling: true
-  - name: grok-4-fast-reasoning
+  - name: grok-4-1-fast-reasoning
     type: chat
     max_input_tokens: 2000000
     input_price: 0.2
     output_price: 0.5
     supports_function_calling: true
-  - name: grok-code-fast
+  - name: grok-code-fast-1
     type: chat
     max_input_tokens: 256000
     input_price: 0.2
     output_price: 1.5
     supports_function_calling: true
-  - name: grok-3
-    type: chat
-    max_input_tokens: 131072
-    input_price: 3.0
-    output_price: 15.0
-    supports_function_calling: true
-  - name: grok-3-mini
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.3
-    output_price: 0.5
-    supports_function_calling: true
 - provider: perplexity
   models:
   - name: sonar-pro
@@ -611,11 +476,6 @@ list:
     max_input_tokens: 128000
     input_price: 2.0
     output_price: 8.0
-  - name: sonar-reasoning
-    type: chat
-    max_input_tokens: 128000
-    input_price: 1.0
-    output_price: 5.0
   - name: sonar-deep-research
     type: chat
     max_input_tokens: 128000
@@ -702,6 +562,16 @@ list:
     max_output_tokens: 65536
     supports_vision: true
     supports_function_calling: true
+  - name: gemini-3-pro-preview
+    type: chat
+    max_input_tokens: 1048576
+    supports_vision: true
+    supports_function_calling: true
+  - name: gemini-3-flash-preview
+    type: chat
+    max_input_tokens: 1048576
+    supports_vision: true
+    supports_function_calling: true
   - name: gemini-2.0-flash-001
     type: chat
     max_input_tokens: 1048576
@@ -877,18 +747,6 @@ list:
     require_max_tokens: true
     supports_vision: true
     supports_function_calling: true
-  - name: mistral-small-2503
-    type: chat
-    max_input_tokens: 32000
-    input_price: 0.1
-    output_price: 0.3
-    supports_function_calling: true
-  - name: codestral-2501
-    type: chat
-    max_input_tokens: 256000
-    input_price: 0.3
-    output_price: 0.9
-    supports_function_calling: true
   - name: text-embedding-005
     type: embedding
     max_input_tokens: 20000
@@ -1336,32 +1194,23 @@ list:
     max_batch_size: 10
 - provider: hunyuan
   models:
-  - name: hunyuan-turbos-latest
+  - name: hunyuan-2.0-instruct-20251111
     type: chat
-    max_input_tokens: 28000
+    max_input_tokens: 131072
     input_price: 0.112
     output_price: 0.28
     supports_function_calling: true
-  - name: hunyuan-t1-latest
+  - name: hunyuan-2.0-thinking-20251109
     type: chat
-    max_input_tokens: 28000
+    max_input_tokens: 131072
     input_price: 0.14
     output_price: 0.56
-  - name: hunyuan-lite
-    type: chat
-    max_input_tokens: 250000
-    input_price: 0.0
-    output_price: 0.0
     supports_function_calling: true
-  - name: hunyuan-turbos-vision
+  - name: hunyuan-vision-1.5-instruct
     type: chat
-    max_input_tokens: 6144
+    max_input_tokens: 24576
     input_price: 0.42
-    output_price: 0.84
-    supports_vision: true
-  - name: hunyuan-t1-vision
-    type: chat
-    max_input_tokens: 24000
+    output_price: 1.26
     supports_vision: true
   - name: hunyuan-embedding
     type: embedding
@@ -1414,65 +1263,29 @@ list:
     max_output_tokens: 32768
 - provider: zhipuai
   models:
-  - name: glm-4.6
+  - name: glm-4.7
     type: chat
     max_input_tokens: 202752
-    input_price: 0.28
-    output_price: 1.12
-    supports_function_calling: true
-  - name: glm-4.5
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.28
-    output_price: 1.12
-  - name: glm-4.5-x
-    type: chat
-    max_input_tokens: 131072
-    input_price: 1.12
-    output_price: 4.48
-    supports_function_calling: true
-  - name: glm-4.5-air
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.084
-    output_price: 0.56
-  - name: glm-4.5-airx
-    type: chat
-    max_input_tokens: 131072
     input_price: 0.56
     output_price: 2.24
     supports_function_calling: true
-  - name: glm-4.5-flash
+  - name: glm-4.7:instruct
     type: chat
-    max_input_tokens: 131072
-    input_price: 0.0
-    output_price: 0.0
-  - name: glm-4.5v
+    real_name: glm-4.7
+    max_input_tokens: 202752
+    input_price: 0.56
+    output_price: 2.24
+    patch:
+      body:
+        thinking:
+          type: disabled
+    supports_function_calling: true
+  - name: glm-4.6v
     type: chat
     max_input_tokens: 65536
-    input_price: 0.56
-    output_price: 1.68
+    input_price: 0.28
+    output_price: 0.84
     supports_vision: true
-  - name: glm-z1-air
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.07
-    output_price: 0.07
-  - name: glm-z1-airx
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.7
-    output_price: 0.7
-  - name: glm-z1-flashx
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.014
-    output_price: 0.014
-  - name: glm-z1-flash
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.0
-    output_price: 0.0
   - name: embedding-3
     type: embedding
     max_input_tokens: 8192
@@ -1485,27 +1298,25 @@ list:
     input_price: 0.112
 - provider: minimax
   models:
-  - name: minimax-m2
+  - name: minimax-m2.1
     type: chat
     max_input_tokens: 204800
     input_price: 0.294
     output_price: 1.176
     supports_function_calling: true
+  - name: minimax-m2.1-lightning
+    type: chat
+    max_input_tokens: 204800
+    input_price: 0.294
+    output_price: 2.352
+    supports_function_calling: true
 - provider: openrouter
   models:
-  - name: openai/gpt-5.1
+  - name: openai/gpt-5.2
     type: chat
     max_input_tokens: 400000
-    input_price: 1.25
-    output_price: 10.0
-    max_output_tokens: 128000
-    supports_vision: true
-    supports_function_calling: true
-  - name: openai/gpt-5.1-chat
-    type: chat
-    max_input_tokens: 400000
-    input_price: 1.25
-    output_price: 10.0
+    input_price: 1.75
+    output_price: 14.0
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -1517,14 +1328,6 @@ list:
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
-  - name: openai/gpt-5-chat
-    type: chat
-    max_input_tokens: 400000
-    input_price: 1.25
-    output_price: 10.0
-    max_output_tokens: 128000
-    supports_vision: true
-    supports_function_calling: true
   - name: openai/gpt-5-mini
     type: chat
     max_input_tokens: 400000
@@ -1549,22 +1352,6 @@ list:
     max_output_tokens: 32768
     supports_vision: true
     supports_function_calling: true
-  - name: openai/gpt-4.1-mini
-    type: chat
-    max_input_tokens: 1047576
-    input_price: 0.4
-    output_price: 1.6
-    max_output_tokens: 32768
-    supports_vision: true
-    supports_function_calling: true
-  - name: openai/gpt-4.1-nano
-    type: chat
-    max_input_tokens: 1047576
-    input_price: 0.1
-    output_price: 0.4
-    max_output_tokens: 32768
-    supports_vision: true
-    supports_function_calling: true
   - name: openai/gpt-4o
     type: chat
     max_input_tokens: 128000
@@ -1572,91 +1359,6 @@ list:
     output_price: 10.0
     supports_vision: true
     supports_function_calling: true
-  - name: openai/gpt-4o-mini
-    type: chat
-    max_input_tokens: 128000
-    input_price: 0.15
-    output_price: 0.6
-    supports_vision: true
-    supports_function_calling: true
-  - name: openai/o4-mini
-    type: chat
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: openai/o4-mini-high
-    type: chat
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        reasoning_effort: high
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: openai/o3
-    type: chat
-    max_input_tokens: 200000
-    input_price: 2.0
-    output_price: 8.0
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: openai/o3-high
-    type: chat
-    real_name: openai/o3
-    max_input_tokens: 200000
-    input_price: 2.0
-    output_price: 8.0
-    patch:
-      body:
-        reasoning_effort: high
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: openai/o3-mini
-    type: chat
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: openai/o3-mini-high
-    type: chat
-    max_input_tokens: 200000
-    input_price: 1.1
-    output_price: 4.4
-    patch:
-      body:
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
   - name: openai/gpt-oss-120b
     type: chat
     max_input_tokens: 131072
@@ -1790,6 +1492,12 @@ list:
     max_input_tokens: 131072
     input_price: 0.12
     output_price: 0.3
+  - name: mistralai/mistral-large-2512
+    type: chat
+    max_input_tokens: 262144
+    input_price: 0.5
+    output_price: 1.5
+    supports_function_calling: true
   - name: mistralai/mistral-medium-3.1
     type: chat
     max_input_tokens: 131072
@@ -1803,26 +1511,11 @@ list:
     input_price: 0.1
     output_price: 0.3
     supports_vision: true
-  - name: mistralai/magistral-medium-2506
+  - name: mistralai/devstral-2512
     type: chat
-    max_input_tokens: 40960
-    input_price: 2.0
-    output_price: 5.0
-  - name: mistralai/magistral-medium-2506:thinking
-    type: chat
-    max_input_tokens: 40960
-    input_price: 2.0
-    output_price: 5.0
-  - name: mistralai/magistral-small-2506
-    type: chat
-    max_input_tokens: 40960
+    max_input_tokens: 262144
     input_price: 0.5
-    output_price: 1.5
-  - name: mistralai/devstral-medium
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.4
-    output_price: 2.0
+    output_price: 0.22
     supports_function_calling: true
   - name: mistralai/devstral-small
     type: chat
@@ -1836,6 +1529,12 @@ list:
     input_price: 0.3
     output_price: 0.9
     supports_function_calling: true
+  - name: mistralai/ministral-14b-2512
+    type: chat
+    max_input_tokens: 262144
+    input_price: 0.2
+    output_price: 0.2
+    supports_function_calling: true
   - name: ai21/jamba-large-1.7
     type: chat
     max_input_tokens: 256000
@@ -1860,29 +1559,11 @@ list:
     input_price: 0.0375
     output_price: 0.15
     max_output_tokens: 4096
-  - name: deepseek/deepseek-v3.2-exp
+  - name: deepseek/deepseek-v3.2
     type: chat
     max_input_tokens: 163840
-    input_price: 0.27
-    output_price: 0.4
-  - name: deepseek/deepseek-v3.1-terminus
-    type: chat
-    max_input_tokens: 163840
-    input_price: 0.23
-    output_price: 0.9
-  - name: deepseek/deepseek-chat-v3.1
-    type: chat
-    max_input_tokens: 163840
-    input_price: 0.2
-    output_price: 0.8
-  - name: deepseek/deepseek-r1-0528
-    type: chat
-    max_input_tokens: 128000
-    input_price: 0.5
-    output_price: 2.15
-    patch:
-      body:
-        include_reasoning: true
+    input_price: 0.25
+    output_price: 0.38
   - name: qwen/qwen3-max
     type: chat
     max_input_tokens: 262144
@@ -1982,13 +1663,7 @@ list:
     input_price: 0.29
     output_price: 1.15
     supports_function_calling: true
-  - name: x-ai/grok-4
-    type: chat
-    max_input_tokens: 256000
-    input_price: 3.0
-    output_price: 15.0
-    supports_function_calling: true
-  - name: x-ai/grok-4-fast
+  - name: x-ai/grok-4.1-fast
     type: chat
     max_input_tokens: 2000000
     input_price: 0.2
@@ -2044,14 +1719,6 @@ list:
     patch:
       body:
         include_reasoning: true
-  - name: perplexity/sonar-reasoning
-    type: chat
-    max_input_tokens: 127000
-    input_price: 1.0
-    output_price: 5.0
-    patch:
-      body:
-        include_reasoning: true
   - name: perplexity/sonar-deep-research
     type: chat
     max_input_tokens: 200000
@@ -2060,17 +1727,24 @@ list:
     patch:
       body:
         include_reasoning: true
-  - name: minimax/minimax-m2
+  - name: minimax/minimax-m2.1
     type: chat
     max_input_tokens: 196608
-    input_price: 0.15
-    output_price: 0.45
-  - name: z-ai/glm-4.6
+    input_price: 0.12
+    output_price: 0.48
+    supports_function_calling: true
+  - name: z-ai/glm-4.7
     type: chat
     max_input_tokens: 202752
-    input_price: 0.5
-    output_price: 1.75
+    input_price: 0.16
+    output_price: 0.8
     supports_function_calling: true
+  - name: z-ai/glm-4.6v
+    type: chat
+    max_input_tokens: 131072
+    input_price: 0.3
+    output_price: 0.9
+    supports_vision: true
 - provider: github
   models:
   - name: gpt-5
@@ -2079,12 +1753,6 @@ list:
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
-  - name: gpt-5-chat
-    type: chat
-    max_input_tokens: 400000
-    max_output_tokens: 128000
-    supports_vision: true
-    supports_function_calling: true
   - name: gpt-5-mini
     type: chat
     max_input_tokens: 400000
@@ -2103,100 +1771,11 @@ list:
     max_output_tokens: 32768
     supports_vision: true
     supports_function_calling: true
-  - name: gpt-4.1-mini
-    type: chat
-    max_input_tokens: 1047576
-    max_output_tokens: 32768
-    supports_vision: true
-    supports_function_calling: true
-  - name: gpt-4.1-nano
-    type: chat
-    max_input_tokens: 1047576
-    max_output_tokens: 32768
-    supports_vision: true
-    supports_function_calling: true
   - name: gpt-4o
     type: chat
     max_input_tokens: 128000
     max_output_tokens: 16384
     supports_function_calling: true
-  - name: gpt-4o-mini
-    type: chat
-    max_input_tokens: 128000
-    max_output_tokens: 16384
-    supports_function_calling: true
-  - name: o4-mini
-    type: chat
-    max_input_tokens: 200000
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o4-mini-high
-    type: chat
-    real_name: o4-mini
-    max_input_tokens: 200000
-    patch:
-      body:
-        reasoning_effort: high
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3
-    type: chat
-    max_input_tokens: 200000
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3-high
-    type: chat
-    real_name: o3
-    max_input_tokens: 200000
-    patch:
-      body:
-        reasoning_effort: high
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3-mini
-    type: chat
-    max_input_tokens: 200000
-    patch:
-      body:
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
-  - name: o3-mini-high
-    type: chat
-    real_name: o3-mini
-    max_input_tokens: 200000
-    patch:
-      body:
-        reasoning_effort: high
-        max_tokens: null
-        temperature: null
-        top_p: null
-    supports_vision: true
-    supports_function_calling: true
-    system_prompt_prefix: Formatting re-enabled
   - name: text-embedding-3-large
     type: embedding
     max_tokens_per_chunk: 8191
@@ -2338,26 +1917,12 @@ list:
     input_price: 0.18
     output_price: 0.69
     supports_vision: true
-  - name: deepseek-ai/DeepSeek-V3.2-Exp
+  - name: deepseek-ai/DeepSeek-V3.2
     type: chat
     max_input_tokens: 163840
-    input_price: 0.27
-    output_price: 0.4
-  - name: deepseek-ai/DeepSeek-V3.1-Terminus
-    type: chat
-    max_input_tokens: 163840
-    input_price: 0.27
-    output_price: 1.0
-  - name: deepseek-ai/DeepSeek-V3.1
-    type: chat
-    max_input_tokens: 163840
-    input_price: 0.3
-    output_price: 1.0
-  - name: deepseek-ai/DeepSeek-R1-0528
-    type: chat
-    max_input_tokens: 163840
-    input_price: 0.5
-    output_price: 2.15
+    input_price: 0.26
+    output_price: 0.39
+    supports_function_calling: true
   - name: google/gemma-3-27b-it
     type: chat
     max_input_tokens: 131072
@@ -2380,12 +1945,24 @@ list:
     input_price: 0.55
     output_price: 2.5
     supports_function_calling: true
-  - name: zai-org/GLM-4.6
+  - name: MiniMaxAI/MiniMax-M2.1
+    type: chat
+    max_input_tokens: 262144
+    input_price: 0.28
+    output_price: 1.2
+    supports_function_calling: true
+  - name: zai-org/GLM-4.7
     type: chat
     max_input_tokens: 202752
-    input_price: 0.6
-    output_price: 1.9
+    input_price: 0.43
+    output_price: 1.75
     supports_function_calling: true
+  - name: zai-org/GLM-4.6V
+    type: chat
+    max_input_tokens: 131072
+    input_price: 0.3
+    output_price: 0.9
+    supports_vision: true
   - name: BAAI/bge-large-en-v1.5
     type: embedding
     input_price: 0.01