Merge branch 'main' into bot/update-google-vertex-20260625-021011

architkumar-truefoundry · web-flow · commit f279cbbac96d · 2026-06-26T13:07:34.000+05:30
diff --git a/providers/aws-bedrock/amazon.rerank-v1:0.yaml b/providers/aws-bedrock/amazon.rerank-v1:0.yaml
@@ -22,9 +22,12 @@ removeParams:
     - "n"
     - stop
     - stream
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/bedrock/latest/userguide/rerank-supported.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/rerank.html
+    - https://docs.aws.amazon.com/bedrock/latest/userguide/rerank-pricing.html
+    - https://docs.aws.amazon.com/bedrock/latest/userguide/rerank-use.html
 status: active
 supportedModes:
     - rerank
diff --git a/providers/aws-bedrock/apac.amazon.nova-micro-v1:0.yaml b/providers/aws-bedrock/apac.amazon.nova-micro-v1:0.yaml
@@ -50,6 +50,8 @@ params:
       maxValue: 5000
       minValue: 1
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html
diff --git a/providers/aws-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0.yaml b/providers/aws-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0.yaml
@@ -1,5 +1,6 @@
 costs:
     - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
       cache_read_input_token_cost: 3.3e-7
       input_cost_per_token: 0.0000033
       input_cost_per_token_batches: 0.00000165
@@ -21,6 +22,7 @@ costs:
                 from: 200000
           pricing_mode: marginal
     - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
       cache_read_input_token_cost: 3.3e-7
       input_cost_per_token: 0.0000033
       input_cost_per_token_batches: 0.00000165
@@ -42,6 +44,7 @@ costs:
                 from: 200000
           pricing_mode: marginal
     - cache_creation_input_token_cost: 0.000004125
+      cache_creation_input_token_cost_per_hour: 0.0000066
       cache_read_input_token_cost: 3.3e-7
       input_cost_per_token: 0.0000033
       input_cost_per_token_batches: 0.00000165
diff --git a/providers/aws-bedrock/cohere.embed-english-v3.yaml b/providers/aws-bedrock/cohere.embed-english-v3.yaml
@@ -30,7 +30,6 @@ limits:
 modalities:
     input:
         - text
-        - image
     output:
         - embedding
 mode: embedding
diff --git a/providers/aws-bedrock/eu.amazon.nova-micro-v1:0.yaml b/providers/aws-bedrock/eu.amazon.nova-micro-v1:0.yaml
@@ -59,11 +59,11 @@ params:
       maxValue: 5000
       minValue: 1
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html
-    - https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-supported-models-features.html
-    - https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-micro.html
 status: active
 supportedModes:
diff --git a/providers/aws-bedrock/eu.anthropic.claude-sonnet-4-6.yaml b/providers/aws-bedrock/eu.anthropic.claude-sonnet-4-6.yaml
@@ -74,7 +74,7 @@ limits:
     context_window: 1000000
     max_output_tokens: 64000
     max_tokens: 64000
-    tool_use_system_prompt_tokens: 346
+    tool_use_system_prompt_tokens: 497
 modalities:
     input:
         - text
diff --git a/providers/aws-bedrock/global.anthropic.claude-opus-4-8.yaml b/providers/aws-bedrock/global.anthropic.claude-opus-4-8.yaml
@@ -15,6 +15,14 @@ costs:
       output_cost_per_token: 2.5e-5
       output_cost_per_token_batches: 1.25e-5
       region: us-west-1
+    - cache_creation_input_token_cost: 6.25e-6
+      cache_creation_input_token_cost_per_hour: 1e-5
+      cache_read_input_token_cost: 5e-7
+      input_cost_per_token: 5e-6
+      input_cost_per_token_batches: 2.5e-6
+      output_cost_per_token: 2.5e-5
+      output_cost_per_token_batches: 1.25e-5
+      region: us-east-2
     - cache_creation_input_token_cost: 6.25e-6
       cache_creation_input_token_cost_per_hour: 1e-5
       cache_read_input_token_cost: 5e-7
@@ -39,6 +47,22 @@ costs:
       output_cost_per_token: 2.5e-5
       output_cost_per_token_batches: 1.25e-5
       region: mx-central-1
+    - cache_creation_input_token_cost: 6.25e-6
+      cache_creation_input_token_cost_per_hour: 1e-5
+      cache_read_input_token_cost: 5e-7
+      input_cost_per_token: 5e-6
+      input_cost_per_token_batches: 2.5e-6
+      output_cost_per_token: 2.5e-5
+      output_cost_per_token_batches: 1.25e-5
+      region: me-south-1
+    - cache_creation_input_token_cost: 6.25e-6
+      cache_creation_input_token_cost_per_hour: 1e-5
+      cache_read_input_token_cost: 5e-7
+      input_cost_per_token: 5e-6
+      input_cost_per_token_batches: 2.5e-6
+      output_cost_per_token: 2.5e-5
+      output_cost_per_token_batches: 1.25e-5
+      region: me-central-1
     - cache_creation_input_token_cost: 6.25e-6
       cache_creation_input_token_cost_per_hour: 1e-5
       cache_read_input_token_cost: 5e-7
diff --git a/providers/aws-bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0.yaml b/providers/aws-bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0.yaml
@@ -439,6 +439,28 @@ costs:
               - cost_per_token: 0.0000225
                 from: 200000
           pricing_mode: marginal
+    - cache_creation_input_token_cost: 0.00000375
+      cache_creation_input_token_cost_per_hour: 0.000006
+      cache_read_input_token_cost: 3e-7
+      input_cost_per_token: 0.000003
+      input_cost_per_token_batches: 0.0000015
+      output_cost_per_token: 0.000015
+      output_cost_per_token_batches: 0.0000075
+      region: ap-southeast-6
+      tiered_pricing:
+          cache_read:
+              - cost_per_token: 6e-7
+                from: 200000
+          cache_write:
+              - cost_per_token: 0.0000075
+                from: 200000
+          input:
+              - cost_per_token: 0.000006
+                from: 200000
+          output:
+              - cost_per_token: 0.0000225
+                from: 200000
+          pricing_mode: marginal
     - cache_creation_input_token_cost: 0.00000375
       cache_creation_input_token_cost_per_hour: 0.000006
       cache_read_input_token_cost: 3e-7
diff --git a/providers/aws-bedrock/google.gemma-3-27b-it.yaml b/providers/aws-bedrock/google.gemma-3-27b-it.yaml
@@ -20,6 +20,9 @@ costs:
     - input_cost_per_token: 2.7e-7
       output_cost_per_token: 4.5e-7
       region: eu-south-1
+    - input_cost_per_token: 1.7e-7
+      output_cost_per_token: 4.8e-7
+      region: eu-central-1
     - input_cost_per_token: 2.369e-7
       output_cost_per_token: 3.914e-7
       region: ap-southeast-2
@@ -50,6 +53,8 @@ params:
       maxValue: 8192
       minValue: 1
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-27b-pt.html
     - https://ai.google.dev/gemma/docs/core
diff --git a/providers/aws-bedrock/luma.ray-v2:0.yaml b/providers/aws-bedrock/luma.ray-v2:0.yaml
@@ -18,6 +18,7 @@ removeParams:
     - "n"
     - stop
     - stream
+    - reasoning_effort
 sources:
     - https://lumalabs.ai/learning-hub
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-luma.html
diff --git a/providers/aws-bedrock/meta.llama3-70b-instruct-v1:0.yaml b/providers/aws-bedrock/meta.llama3-70b-instruct-v1:0.yaml
@@ -32,6 +32,8 @@ modalities:
 mode: chat
 model: meta.llama3-70b-instruct-v1:0
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
diff --git a/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml b/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml
@@ -20,6 +20,15 @@ costs:
     - input_cost_per_token: 1.2e-7
       output_cost_per_token: 1.2e-7
       region: eu-south-1
+    - input_cost_per_token: 1.2e-7
+      output_cost_per_token: 1.2e-7
+      region: eu-north-1
+    - input_cost_per_token: 1.2e-7
+      output_cost_per_token: 1.2e-7
+      region: eu-central-1
+    - input_cost_per_token: 1.2e-7
+      output_cost_per_token: 1.2e-7
+      region: ap-southeast-3
     - input_cost_per_token: 1.03e-7
       output_cost_per_token: 1.03e-7
       region: ap-southeast-2
diff --git a/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml b/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml
@@ -70,6 +70,8 @@ params:
       maxValue: 1
       minValue: 0
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.mistral.ai/models/ministral-3-8b-25-12
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-ministral-3-8b.html
diff --git a/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml b/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml
@@ -30,6 +30,7 @@ features:
     - structured_output
     - system_messages
     - prompt_caching
+    - assistant_prefill
 limits:
     context_window: 256000
     max_output_tokens: 32000
diff --git a/providers/aws-bedrock/mistral.mistral-small-2402-v1:0.yaml b/providers/aws-bedrock/mistral.mistral-small-2402-v1:0.yaml
@@ -4,6 +4,8 @@ costs:
       region: us-east-1
 features:
     - function_calling
+    - tool_choice
+    - system_messages
 limits:
     context_window: 32000
     max_input_tokens: 32000
diff --git a/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml b/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml
@@ -23,6 +23,15 @@ costs:
     - input_cost_per_token: 7e-8
       output_cost_per_token: 2.8e-7
       region: eu-south-1
+    - input_cost_per_token: 1.8e-7
+      output_cost_per_token: 7.8e-7
+      region: eu-north-1
+    - input_cost_per_token: 1.8e-7
+      output_cost_per_token: 7.8e-7
+      region: eu-central-1
+    - input_cost_per_token: 1.8e-7
+      output_cost_per_token: 7.8e-7
+      region: ap-southeast-3
     - input_cost_per_token: 6.18e-8
       output_cost_per_token: 2.472e-7
       region: ap-southeast-2
diff --git a/providers/aws-bedrock/qwen.qwen3-coder-30b-a3b-v1:0.yaml b/providers/aws-bedrock/qwen.qwen3-coder-30b-a3b-v1:0.yaml
@@ -29,8 +29,8 @@ costs:
     - input_cost_per_token: 1.6e-7
       output_cost_per_token: 6.2e-7
       region: ap-southeast-3
-    - input_cost_per_token: 1.5e-7
-      output_cost_per_token: 6e-7
+    - input_cost_per_token: 1.545e-7
+      output_cost_per_token: 6.18e-7
       region: ap-southeast-2
     - input_cost_per_token: 1.8e-7
       output_cost_per_token: 7.1e-7
@@ -57,6 +57,8 @@ params:
       maxValue: 16000
       minValue: 1
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html
 status: active
diff --git a/providers/aws-bedrock/qwen.qwen3-coder-480b-a35b-v1:0.yaml b/providers/aws-bedrock/qwen.qwen3-coder-480b-a35b-v1:0.yaml
@@ -5,12 +5,15 @@ costs:
     - input_cost_per_token: 4.5e-7
       output_cost_per_token: 0.0000018
       region: us-east-2
+    - region: us-east-1 # not found in official docs
+    - region: sa-east-1 # not found in official docs
     - input_cost_per_token: 7e-7
       output_cost_per_token: 0.00000279
       region: eu-west-2
     - input_cost_per_token: 4.5e-7
       output_cost_per_token: 0.0000018
       region: eu-north-1
+    - region: ap-southeast-4 # not found in official docs
     - input_cost_per_token: 4.7e-7
       output_cost_per_token: 0.00000187
       region: ap-southeast-3
@@ -41,6 +44,8 @@ params:
       maxValue: 16000
       minValue: 1
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html
 status: active
diff --git a/providers/aws-bedrock/us.amazon.nova-2-lite-v1:0.yaml b/providers/aws-bedrock/us.amazon.nova-2-lite-v1:0.yaml
@@ -60,7 +60,6 @@ params:
 provisioning: serverless
 sources:
     - https://docs.aws.amazon.com/nova/latest/nova2-userguide/what-is-nova-2.html
-    - https://docs.aws.amazon.com/nova/latest/nova2-userguide/extended-thinking.html
     - https://docs.aws.amazon.com/nova/latest/nova2-userguide/using-multimodal-models.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-lite.html
diff --git a/providers/aws-bedrock/us.anthropic.claude-opus-4-6-v1.yaml b/providers/aws-bedrock/us.anthropic.claude-opus-4-6-v1.yaml
@@ -49,10 +49,13 @@ costs:
       region: ca-central-1
 features:
     - function_calling
+    - parallel_function_calling
     - prompt_caching
     - tool_choice
     - structured_output
     - system_messages
+    - cache_control
+    - assistant_prefill
 limits:
     context_window: 1000000
     max_input_tokens: 1000000
diff --git a/providers/aws-bedrock/us.anthropic.claude-opus-4-8.yaml b/providers/aws-bedrock/us.anthropic.claude-opus-4-8.yaml
@@ -77,6 +77,15 @@ params:
       minValue: 1
     - key: thinking
       type: json
+    - defaultValue: high
+      key: reasoning_effort
+      supportedValues:
+          - low
+          - medium
+          - high
+          - xhigh
+          - max
+      type: string
 provisioning: serverless
 removeParams:
     - temperature
diff --git a/providers/aws-bedrock/us.anthropic.claude-sonnet-4-6.yaml b/providers/aws-bedrock/us.anthropic.claude-sonnet-4-6.yaml
@@ -60,7 +60,7 @@ limits:
     max_input_tokens: 1000000
     max_output_tokens: 64000
     max_tokens: 64000
-    tool_use_system_prompt_tokens: 346
+    tool_use_system_prompt_tokens: 497
 modalities:
     input:
         - text
diff --git a/providers/aws-bedrock/us.meta.llama3-1-70b-instruct-v1:0.yaml b/providers/aws-bedrock/us.meta.llama3-1-70b-instruct-v1:0.yaml
@@ -35,6 +35,8 @@ params:
       maxValue: 4096
       minValue: 1
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html
diff --git a/providers/aws-bedrock/us.mistral.pixtral-large-2502-v1:0.yaml b/providers/aws-bedrock/us.mistral.pixtral-large-2502-v1:0.yaml
@@ -12,7 +12,6 @@ features:
     - function_calling
     - tool_choice
     - system_messages
-    - json_output
 limits:
     context_window: 128000
     max_input_tokens: 128000
@@ -32,6 +31,8 @@ params:
       maxValue: 16384
       minValue: 1
 provisioning: serverless
+removeParams:
+    - reasoning_effort
 sources:
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-mistral-pixtral-large.html
     - https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.html
diff --git a/providers/deepinfra/FastVideo/LTX-2.3-Distilled-Diffusers.yaml b/providers/deepinfra/FastVideo/LTX-2.3-Distilled-Diffusers.yaml
@@ -0,0 +1,19 @@
+costs:
+    - output_cost_per_second: 0.035
+      region: "*"
+modalities:
+    input:
+        - text
+        - image
+    output:
+        - video
+mode: video
+model: FastVideo/LTX-2.3-Distilled-Diffusers
+provisioning: serverless
+removeParams:
+    - reasoning_effort
+sources:
+    - https://deepinfra.com/FastVideo/LTX-2.3-Distilled-Diffusers
+status: active
+supportedModes:
+    - video
diff --git a/providers/google-gemini/gemini-3-pro-image.yaml b/providers/google-gemini/gemini-3-pro-image.yaml
@@ -16,6 +16,7 @@ modalities:
     input:
         - text
         - image
+        - video
     output:
         - text
         - image
diff --git a/providers/google-gemini/gemini-3.1-flash-image.yaml b/providers/google-gemini/gemini-3.1-flash-image.yaml
@@ -19,6 +19,7 @@ modalities:
         - text
         - image
         - video
+        - audio
     output:
         - text
         - image
diff --git a/providers/google-vertex/anthropic/claude-opus-4-8.yaml b/providers/google-vertex/anthropic/claude-opus-4-8.yaml
diff --git a/providers/mistral-ai/ministral-14b-latest.yaml b/providers/mistral-ai/ministral-14b-latest.yaml
diff --git a/providers/together-ai/ByteDance-Seed/Seedream-5.0-lite.yaml b/providers/together-ai/ByteDance-Seed/Seedream-5.0-lite.yaml
diff --git a/providers/together-ai/google/gemma-3-1b-pt.yaml b/providers/together-ai/google/gemma-3-1b-pt.yaml
diff --git a/providers/together-ai/google/medgemma-27b-text-it.yaml b/providers/together-ai/google/medgemma-27b-text-it.yaml
diff --git a/providers/together-ai/mistralai/Voxtral-Mini-3B-2507.yaml b/providers/together-ai/mistralai/Voxtral-Mini-3B-2507.yaml
diff --git a/providers/together-ai/openai/gpt-image-2.yaml b/providers/together-ai/openai/gpt-image-2.yaml
diff --git a/providers/together-ai/rime-labs/rime-mist-v3-omni.yaml b/providers/together-ai/rime-labs/rime-mist-v3-omni.yaml
diff --git a/providers/wafer/GLM-5.2.yaml b/providers/wafer/GLM-5.2.yaml
