Merge pull request #2142 from anomalyco/automation/sync-models-openrouter

chore(sync): update OpenRouter model catalog

providers/openrouter/models/deepseek/deepseek-r1-distill-llama-70b.toml

@@ -11,12 +11,12 @@ knowledge = "2024-07-31"
 open_weights = true
 
 [cost]
-input = 0.7
+input = 0.8
 output = 0.8
 
 [limit]
-context = 131_072
-output = 16_384
+context = 8_192
+output = 8_192
 
 [modalities]
 input = ["text"]

providers/openrouter/models/google/gemma-4-31b-it.toml

@@ -2,12 +2,11 @@ base_model = "google/gemma-4-31b-it"
 
 [cost]
 input = 0.12
-output = 0.36
+output = 0.35
 cache_read = 0.09
 
 [limit]
-context = 256_000
-output = 8_192
+output = 262_144
 
 [modalities]
 input = ["image", "text", "video"]

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

@@ -1,9 +0,0 @@
-base_model = "nvidia/nemotron-nano-9b-v2"
-structured_output = false
-
-[cost]
-input = 0.04
-output = 0.16
-
-[limit]
-output = 16_384

providers/openrouter/models/qwen/qwen3.6-35b-a3b.toml

@@ -1,12 +1,12 @@
 base_model = "alibaba/qwen3.6-35b-a3b"
 
 [cost]
-input = 0.14
+input = 0.15
 output = 1
+cache_read = 0.05
 
 [limit]
-context = 262_140
-output = 262_140
+output = 262_144
 
 [modalities]
 input = ["text", "image", "video"]

providers/openrouter/models/qwen/qwen3.7-plus.toml

@@ -3,10 +3,10 @@ attachment = true
 structured_output = true
 
 [cost]
-input = 0.4
-output = 1.6
-cache_read = 0.08
-cache_write = 0.5
+input = 0.32
+output = 1.28
+cache_read = 0.064
+cache_write = 0.4
 
 [limit]
 output = 65_536