feat(together-ai): add new models [bot] (#932)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

Author: harshiv-26

providers/together-ai/Qwen/Qwen3.6-Plus.yaml

@@ -0,0 +1,10 @@
+costs:
+    - input_cost_per_token: 5e-7
+      output_cost_per_token: 3e-6
+      region: "*"
+limits:
+    context_window: 1000000
+mode: unknown
+model: Qwen/Qwen3.6-Plus
+supportedModes:
+    - chat

providers/together-ai/deepseek-ai/DeepSeek-V4-Pro.yaml

@@ -0,0 +1,11 @@
+costs:
+    - cache_read_input_token_cost: 2e-7
+      input_cost_per_token: 2.1e-6
+      output_cost_per_token: 4.4e-6
+      region: "*"
+limits:
+    context_window: 512000
+mode: unknown
+model: deepseek-ai/DeepSeek-V4-Pro
+supportedModes:
+    - chat

providers/together-ai/mistralai/Voxtral-Mini-3B-2507.yaml

@@ -0,0 +1,8 @@
+costs:
+    - input_cost_per_token: 2.7e-7
+      output_cost_per_token: 8.5e-7
+      region: "*"
+mode: unknown
+model: mistralai/Voxtral-Mini-3B-2507
+supportedModes:
+    - audio_transcription

providers/together-ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-fp8.yaml

@@ -0,0 +1,10 @@
+costs:
+    - input_cost_per_token: 0.0
+      output_cost_per_token: 0.0
+      region: "*"
+limits:
+    context_window: 131072
+mode: unknown
+model: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-fp8
+supportedModes:
+    - chat