Merge pull request #348 from wojons/dev

Updating Nvidia provider with qwen and nemotron

Author: rekram1-node

providers/nvidia/models/nvidia/nvidia-nemotron-nano-9b-v2.toml

@@ -0,0 +1,22 @@
+name = "nvidia-nemotron-nano-9b-v2"
+
+release_date = "2025-08-18"
+last_updated = "2025-08-18"
+attachment = false
+reasoning = true
+temperature = true
+knowledge = "2024-09"
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 131_072
+output = 131_072
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/nvidia/models/qwen/qwen3-next-80b-a3b-instruct.toml

@@ -0,0 +1,21 @@
+name = "Qwen3-Next-80B-A3B-Instruct"
+release_date = "2024-12-01"
+last_updated = "2025-09-05"
+attachment = false
+reasoning = false
+temperature = true
+knowledge = "2024-12"
+tool_call = true
+open_weights = false
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 262_144
+output = 16_384
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/nvidia/models/qwen/qwen3-next-80b-a3b-thinking.toml

@@ -0,0 +1,21 @@
+name = "Qwen3-Next-80B-A3B-Thinking"
+release_date = "2024-12-01"
+last_updated = "2025-09-05"
+attachment = false
+reasoning = true
+temperature = true
+knowledge = "2024-12"
+tool_call = true
+open_weights = true
+
+[cost]
+input = 0.0
+output = 0.0
+
+[limit]
+context = 262_144
+output = 16_384
+
+[modalities]
+input = ["text"]
+output = ["text"]