Merge branch 'sst:dev' into dev

providers/google-vertex/models/openai/gpt-oss-120b-maas.toml

@@ -0,0 +1,20 @@
+name = "GPT OSS 120B"
+release_date = "2025-08-05"
+last_updated = "2025-08-05"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.09
+output = 0.36
+
+[limit]
+context = 131_072
+output = 32_768
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/google-vertex/models/openai/gpt-oss-20b-maas.toml

@@ -0,0 +1,20 @@
+name = "GPT OSS 20B"
+release_date = "2025-08-05"
+last_updated = "2025-08-05"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.07
+output = 0.25
+
+[limit]
+context = 131_072
+output = 32_768
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/mistral/models/devstral-medium-latest.toml

@@ -0,0 +1,21 @@
+name = "Devstral 2"
+release_date = "2025-12-02"
+last_updated = "2025-12-02"
+attachment = false
+reasoning = false
+temperature = true
+knowledge = "2025-12"
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.4
+output = 2
+
+[limit]
+context = 262_144
+output = 262_144
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/sap-ai-core/provider.toml

@@ -1,4 +1,4 @@
 name = "SAP AI Core"
-env = ["SAP_AI_SERVICE_KEY"]
+env = ["AICORE_SERVICE_KEY"]
 npm = "@mymediset/sap-ai-provider"
 doc = "https://help.sap.com/docs/sap-ai-core"

providers/venice/models/deepseek-r1-671b.toml

@@ -1,21 +0,0 @@
-name = "DeepSeek R1 671B"
-attachment = false
-reasoning = true
-tool_call = false
-temperature = true
-knowledge = "2023-10"
-release_date = "2025-06-05"
-last_updated = "2025-06-05"
-open_weights = true
-
-[cost]
-input = 3.5
-output = 14.0
-
-[limit]
-context = 131_072
-output = 8_192
-
-[modalities]
-input = ["text"]
-output = ["text"]

providers/venice/models/deepseek-v3.2.toml

@@ -0,0 +1,21 @@
+name = "DeepSeek V3.2"
+attachment = false
+reasoning = false
+tool_call = false
+temperature = true
+knowledge = "2025-10"
+release_date = "2025-10-05"
+last_updated = "2025-10-05"
+open_weights = true
+
+[cost]
+input = 0.4
+output = 1
+
+[limit]
+context = 163_840
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/venice/models/dolphin-2.9.2-qwen2-72b.toml

@@ -1,21 +0,0 @@
-name = "Dolphin 72B"
-attachment = false
-reasoning = false
-tool_call = false
-temperature = true
-knowledge = "2021-09"
-release_date = "2025-05-21"
-last_updated = "2025-05-21"
-open_weights = true
-
-[cost]
-input = 0.7
-output = 2.8
-
-[limit]
-context = 32_768
-output = 8_192
-
-[modalities]
-input = ["text"]
-output = ["text"]

providers/venice/models/google-gemma-3-27b-it.toml

@@ -0,0 +1,21 @@
+name = "Google Gemma 3 27B Instruct"
+attachment = true
+reasoning = false
+tool_call = true
+temperature = true
+knowledge = "2025-07"
+release_date = "2025-07-27"
+last_updated = "2025-07-27"
+open_weights = true
+
+[cost]
+input = 0.12
+output = 0.2
+
+[limit]
+context = 202_752
+output = 8_192
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/venice/models/hermes-3-llama-3.1-405b.toml

@@ -1,16 +1,16 @@
-name = "DeepSeek Coder V2 Lite"
+name = "Hermes 3 Llama 3.1 405b"
 attachment = false
 reasoning = false
 tool_call = false
 temperature = true
-knowledge = "2021-09"
-release_date = "2025-06-22"
-last_updated = "2025-06-22"
+knowledge = "2024-04"
+release_date = "2024-04-15"
+last_updated = "2024-04-15"
 open_weights = true
 
 [cost]
-input = 0.5
-output = 2.0
+input = 1.1
+output = 3.0
 
 [limit]
 context = 131_072
@@ -18,4 +18,4 @@ output = 8_192
 
 [modalities]
 input = ["text"]
-output = ["text"]
+output = ["text"]

providers/venice/models/llama-3.1-405b.toml

@@ -1,21 +0,0 @@
-name = "Llama 3.1 405B"
-attachment = false
-reasoning = false
-tool_call = false
-temperature = true
-knowledge = "2023-12"
-release_date = "2025-06-30"
-last_updated = "2025-06-30"
-open_weights = true
-
-[cost]
-input = 1.5
-output = 6.0
-
-[limit]
-context = 65_536
-output = 8_192
-
-[modalities]
-input = ["text"]
-output = ["text"]

providers/venice/models/mistral-31-24b.toml

@@ -1,11 +1,11 @@
 name = "Venice Medium"
-attachment = false
+attachment = true
 reasoning = false
 tool_call = true
 temperature = true
 knowledge = "2023-10"
 release_date = "2025-07-15"
-last_updated = "2025-07-15"
+last_updated = "2025-12-09"
 open_weights = true
 
 [cost]

providers/venice/models/openai-gpt-oss-120b.toml

@@ -0,0 +1,21 @@
+name = "OpenAI GPT OSS 120B"
+attachment = false
+reasoning = false
+tool_call = true
+temperature = true
+knowledge = "2025-07"
+release_date = "2025-07-27"
+last_updated = "2025-07-27"
+open_weights = true
+
+[cost]
+input = 0.07
+output = 0.3
+
+[limit]
+context = 131_072
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/venice/models/qwen-2.5-coder-32b.toml

@@ -1,21 +0,0 @@
-name = "Qwen 2.5 Coder 32B"
-attachment = false
-reasoning = false
-tool_call = false
-temperature = true
-knowledge = "2023-10"
-release_date = "2025-06-14"
-last_updated = "2025-06-14"
-open_weights = true
-
-[cost]
-input = 0.5
-output = 2.0
-
-[limit]
-context = 32_768
-output = 8_192
-
-[modalities]
-input = ["text"]
-output = ["text"]

providers/venice/models/qwen-2.5-qwq-32b.toml

@@ -1,21 +0,0 @@
-name = "Venice Reasoning"
-attachment = false
-reasoning = true
-tool_call = false
-temperature = true
-knowledge = "2023-10"
-release_date = "2025-07-08"
-last_updated = "2025-07-08"
-open_weights = true
-
-[cost]
-input = 0.5
-output = 2.0
-
-[limit]
-context = 32_768
-output = 8_192
-
-[modalities]
-input = ["text"]
-output = ["text"]

providers/venice/models/qwen-2.5-vl.toml

@@ -1,21 +0,0 @@
-name = "Qwen 2.5 VL 72B"
-attachment = false
-reasoning = false
-tool_call = false
-temperature = true
-knowledge = "2023-10"
-release_date = "2025-06-09"
-last_updated = "2025-06-09"
-open_weights = true
-
-[cost]
-input = 0.7
-output = 2.8
-
-[limit]
-context = 32_768
-output = 8_192
-
-[modalities]
-input = ["text", "image"]
-output = ["text"]

providers/venice/models/qwen3-235b-a22b-instruct-2507.toml

@@ -0,0 +1,21 @@
+name = "Qwen 3 235B A22B Instruct 2507"
+attachment = false
+reasoning = false
+tool_call = true
+temperature = true
+knowledge = "2025-07"
+release_date = "2025-07-27"
+last_updated = "2025-07-27"
+open_weights = true
+
+[cost]
+input = 0.15
+output = 0.75
+
+[limit]
+context = 131_072
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/venice/models/qwen3-235b-a22b-thinking-2507.toml

@@ -0,0 +1,21 @@
+name = "Qwen 3 235B A22B Thinking 2507"
+attachment = false
+reasoning = true
+tool_call = true
+temperature = true
+knowledge = "2025-07"
+release_date = "2025-07-27"
+last_updated = "2025-07-27"
+open_weights = true
+
+[cost]
+input = 0.45
+output = 3.5
+
+[limit]
+context = 131_072
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/venice/models/qwen3-235b.toml

@@ -1,16 +1,16 @@
-name = "Venice Large"
+name = "Venice Large 1.1"
 attachment = false
 reasoning = true
 tool_call = true
 temperature = true
 knowledge = "2024-10"
 release_date = "2025-07-27"
-last_updated = "2025-07-27"
+last_updated = "2025-12-09"
 open_weights = true
 
 [cost]
-input = 1.5
-output = 6.0
+input = 0.45
+output = 3.5
 
 [limit]
 context = 131_072

providers/venice/models/qwen3-4b.toml

@@ -5,12 +5,12 @@ tool_call = true
 temperature = true
 knowledge = "2024-07"
 release_date = "2025-07-27"
-last_updated = "2025-07-27"
+last_updated = "2025-12-09"
 open_weights = true
 
 [cost]
-input = 0.15
-output = 0.6
+input = 0.05
+output = 0.15
 
 [limit]
 context = 32_768

providers/venice/models/qwen3-coder-480b-a35b-instruct.toml

@@ -0,0 +1,21 @@
+name = "Qwen 3 Coder 480b"
+attachment = false
+reasoning = false
+tool_call = true
+temperature = true
+knowledge = "2025-07"
+release_date = "2025-07-27"
+last_updated = "2025-07-27"
+open_weights = true
+
+[cost]
+input = 0.75
+output = 3
+
+[limit]
+context = 262_144
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/venice/models/qwen3-next-80b.toml

@@ -0,0 +1,21 @@
+name = "Qwen 3 Next 80b"
+attachment = false
+reasoning = false
+tool_call = true
+temperature = true
+knowledge = "2025-07"
+release_date = "2025-07-27"
+last_updated = "2025-07-27"
+open_weights = true
+
+[cost]
+input = 0.35
+output = 1.9
+
+[limit]
+context = 262_144
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/venice/models/venice-uncensored.toml

@@ -5,12 +5,12 @@ tool_call = false
 temperature = true
 knowledge = "2023-10"
 release_date = "2025-07-15"
-last_updated = "2025-07-15"
+last_updated = "2025-12-09"
 open_weights = true
 
 [cost]
-input = 0.5
-output = 2.0
+input = 0.2
+output = 0.9
 
 [limit]
 context = 32_768