chore: import upstream snapshot with attribution

providers/stackit/models/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8.toml

@@ -0,0 +1,23 @@
+name = "Qwen3-VL 235B"
+description = "Qwen vision-language model for visual reasoning, documents, and agent tasks"
+family = "qwen"
+release_date = "2024-11-01"
+last_updated = "2024-11-01"
+attachment = true
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = false
+open_weights = true
+
+[cost]
+input = 1.76
+output = 2.05
+
+[limit]
+context = 218_000
+output = 16_384
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/stackit/models/Qwen/Qwen3-VL-Embedding-8B.toml

@@ -0,0 +1,23 @@
+name = "Qwen3-VL Embedding 8B"
+description = "Embedding model for semantic search, retrieval, clustering, and ranking pipelines"
+family = "qwen"
+release_date = "2026-02-05"
+last_updated = "2026-02-05"
+attachment = true
+reasoning = false
+temperature = false
+tool_call = false
+structured_output = false
+open_weights = true
+
+[cost]
+input = 0.09
+output = 0.09
+
+[limit]
+context = 32_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/stackit/models/Qwen/Qwen3.6-27B.toml

@@ -0,0 +1,16 @@
+base_model = "alibaba/qwen3.6-27b"
+attachment = false
+reasoning = false
+structured_output = false
+
+[cost]
+input = 0.53
+output = 0.76
+
+[limit]
+context = 262_144
+output = 16_384
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/stackit/models/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic.toml

@@ -0,0 +1,23 @@
+name = "Llama 3.3 70B"
+description = "Open Llama instruction model for multilingual chat, reasoning, and coding"
+family = "llama"
+release_date = "2024-12-05"
+last_updated = "2024-12-05"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = false
+open_weights = true
+
+[cost]
+input = 0.53
+output = 0.76
+
+[limit]
+context = 128_000
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]

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

@@ -0,0 +1,23 @@
+name = "Gemma 3 27B"
+description = "Open Gemma instruction model for efficient chat and self-hosted deployments"
+family = "gemma"
+release_date = "2025-05-17"
+last_updated = "2025-05-17"
+attachment = true
+reasoning = false
+temperature = true
+tool_call = false
+structured_output = false
+open_weights = true
+
+[cost]
+input = 0.53
+output = 0.76
+
+[limit]
+context = 37_000
+output = 4_096
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/stackit/models/intfloat/e5-mistral-7b-instruct.toml

@@ -0,0 +1,23 @@
+name = "E5 Mistral 7B"
+description = "Embedding model for semantic search, retrieval, clustering, and ranking pipelines"
+family = "mistral"
+release_date = "2023-12-11"
+last_updated = "2023-12-11"
+attachment = false
+reasoning = false
+temperature = false
+tool_call = false
+structured_output = false
+open_weights = true
+
+[cost]
+input = 0.02
+output = 0.02
+
+[limit]
+context = 4_096
+output = 4_096
+
+[modalities]
+input = ["text"]
+output = ["text"]

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

@@ -0,0 +1,18 @@
+base_model = "openai/gpt-oss-120b"
+structured_output = false
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high"]
+
+[cost]
+input = 0.53
+output = 0.76
+
+[limit]
+context = 131_000
+output = 8_192
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/stackit/models/openai/gpt-oss-20b.toml

@@ -0,0 +1,10 @@
+base_model = "openai/gpt-oss-20b"
+structured_output = false
+reasoning_options = []
+
+[cost]
+input = 0.18
+output = 0.29
+
+[limit]
+output = 8_192