Merge branch 'main' into bot/add-wafer-Kimi-K2.6-20260624-093511

Author: harshiv-26

providers/google-gemini/gemini-3-pro-image.yaml

@@ -16,6 +16,7 @@ modalities:
     input:
         - text
         - image
+        - video
     output:
         - text
         - image

providers/google-gemini/gemini-3.1-flash-image.yaml

@@ -19,6 +19,7 @@ modalities:
         - text
         - image
         - video
+        - audio
     output:
         - text
         - image

providers/google-vertex/anthropic/claude-opus-4-8.yaml

@@ -47,10 +47,12 @@ params:
 provisioning: serverless
 removeParams:
     - temperature
+    - top_p
 sources:
     - https://platform.claude.com/docs/en/about-claude/models/overview
     - https://platform.claude.com/docs/en/about-claude/pricing
     - https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai
+    - https://platform.claude.com/docs/en/about-claude/model-deprecations
 status: active
 supportedModes:
     - chat

providers/mistral-ai/ministral-14b-latest.yaml

@@ -1,13 +1,17 @@
 costs:
     - input_cost_per_token: 2e-7
+      input_cost_per_token_batches: 1e-7
       output_cost_per_token: 2e-7
+      output_cost_per_token_batches: 1e-7
       region: "*"
 features:
     - function_calling
     - parallel_function_calling
     - tool_choice
     - structured_output
     - json_output
+    - system_messages
+    - assistant_prefill
 limits:
     context_window: 262144
 modalities:

providers/wafer/GLM-5.1.yaml

@@ -0,0 +1,29 @@
+costs:
+    - cache_read_input_token_cost: 1e-7
+      input_cost_per_token: 1e-6
+      output_cost_per_token: 3.2e-6
+      region: "*"
+features:
+    - function_calling
+    - parallel_function_calling
+    - tool_choice
+    - json_output
+    - structured_output
+    - prompt_caching
+    - system_messages
+limits:
+    context_window: 202752
+modalities:
+    input:
+        - text
+    output:
+        - text
+mode: chat
+model: GLM-5.1
+provisioning: serverless
+sources:
+    - https://pass.wafer.ai/v1/models
+status: active
+supportedModes:
+    - chat
+thinking: true

providers/wafer/GLM-5.2.yaml

@@ -0,0 +1,29 @@
+costs:
+    - cache_read_input_token_cost: 2e-7
+      input_cost_per_token: 1.2e-6
+      output_cost_per_token: 4.1e-6
+      region: "*"
+features:
+    - function_calling
+    - tool_choice
+    - structured_output
+    - json_output
+    - prompt_caching
+    - system_messages
+limits:
+    context_window: 1048576
+modalities:
+    input:
+        - text
+    output:
+        - text
+mode: chat
+model: GLM-5.2
+provisioning: serverless
+sources:
+    - https://pass.wafer.ai/v1/models
+status: active
+supportedModes:
+    - chat
+    - responses
+thinking: true