chore: sync model pricing from OpenRouter API

providers/deepseek.toml

@@ -14,8 +14,8 @@ display_name = "DeepSeek V3"
 tier = "smart"
 context_window = 64000
 max_output_tokens = 8192
-input_cost_per_m = 0.15
+input_cost_per_m = 0.32
-output_cost_per_m = 0.75
+output_cost_per_m = 0.89
 supports_tools = true
 supports_vision = false
 supports_streaming = true

providers/moonshot.toml

@@ -53,8 +53,8 @@ display_name = "Kimi K2"
 tier = "frontier"
 context_window = 131072
 max_output_tokens = 16384
-input_cost_per_m = 0.44999999999999996
+input_cost_per_m = 0.57
-output_cost_per_m = 2.2
+output_cost_per_m = 2.3
 supports_tools = true
 supports_vision = true
 supports_streaming = true

providers/nvidia-nim.toml

@@ -16,8 +16,8 @@ display_name = "Nemotron Ultra 253B"
 tier = "frontier"
 context_window = 128000
 max_output_tokens = 4096
-input_cost_per_m = 3.00
+input_cost_per_m = 0.6
-output_cost_per_m = 5.00
+output_cost_per_m = 1.8
 supports_tools = true
 supports_vision = false
 supports_streaming = true
@@ -29,7 +29,7 @@ display_name = "Nemotron Super 49B v1.5"
 tier = "smart"
 context_window = 128000
 max_output_tokens = 4096
-input_cost_per_m = 0.40
+input_cost_per_m = 0.1
 output_cost_per_m = 0.40
 supports_tools = true
 supports_vision = false
@@ -42,8 +42,8 @@ display_name = "Nemotron 70B"
 tier = "balanced"
 context_window = 128000
 max_output_tokens = 4096
-input_cost_per_m = 0.10
+input_cost_per_m = 1.2
-output_cost_per_m = 0.10
+output_cost_per_m = 1.2
 supports_tools = true
 supports_vision = false
 supports_streaming = true
@@ -232,8 +232,8 @@ display_name = "Qwen 3.5 397B MoE"
 tier = "frontier"
 context_window = 128000
 max_output_tokens = 8192
-input_cost_per_m = 0.60
+input_cost_per_m = 0.39
-output_cost_per_m = 2.40
+output_cost_per_m = 2.34
 supports_tools = true
 supports_vision = false
 supports_streaming = true
@@ -258,8 +258,8 @@ display_name = "QWQ 32B"
 tier = "balanced"
 context_window = 128000
 max_output_tokens = 16384
-input_cost_per_m = 0.10
+input_cost_per_m = 0.15
-output_cost_per_m = 0.10
+output_cost_per_m = 0.58
 supports_tools = false
 supports_vision = false
 supports_streaming = true
@@ -273,8 +273,8 @@ display_name = "Gemma 3 27B"
 tier = "balanced"
 context_window = 128000
 max_output_tokens = 4096
-input_cost_per_m = 0.10
+input_cost_per_m = 0.08
-output_cost_per_m = 0.10
+output_cost_per_m = 0.16
 supports_tools = false
 supports_vision = false
 supports_streaming = true

providers/openai.toml

@@ -80,8 +80,8 @@ display_name = "o3"
 tier = "frontier"
 context_window = 200000
 max_output_tokens = 100000
-input_cost_per_m = 10.0
+input_cost_per_m = 2.0
-output_cost_per_m = 40.0
+output_cost_per_m = 8.0
 supports_tools = true
 supports_vision = true
 supports_streaming = true
@@ -106,8 +106,8 @@ display_name = "o4-mini"
 tier = "smart"
 context_window = 200000
 max_output_tokens = 100000
-input_cost_per_m = 2.0
+input_cost_per_m = 1.1
-output_cost_per_m = 8.0
+output_cost_per_m = 4.4
 supports_tools = true
 supports_vision = true
 supports_streaming = true
@@ -132,8 +132,8 @@ display_name = "GPT-3.5 Turbo"
 tier = "fast"
 context_window = 16385
 max_output_tokens = 4096
-input_cost_per_m = 1.0
+input_cost_per_m = 0.5
-output_cost_per_m = 2.0
+output_cost_per_m = 1.5
 supports_tools = true
 supports_vision = false
 supports_streaming = true
@@ -145,8 +145,8 @@ display_name = "GPT-5"
 tier = "frontier"
 context_window = 400000
 max_output_tokens = 128000
-input_cost_per_m = 0.19999999999999998
+input_cost_per_m = 1.25
-output_cost_per_m = 1.25
+output_cost_per_m = 10.0
 supports_tools = true
 supports_vision = true
 supports_streaming = true

providers/qwen.toml

@@ -99,8 +99,8 @@ display_name = "Qwen3 235B"
 tier = "frontier"
 context_window = 131072
 max_output_tokens = 8192
-input_cost_per_m = 0.14950000000000002
+input_cost_per_m = 0.455
-output_cost_per_m = 1.495
+output_cost_per_m = 1.82
 supports_tools = true
 supports_vision = false
 supports_streaming = true
@@ -113,7 +113,7 @@ tier = "fast"
 context_window = 131072
 max_output_tokens = 8192
 input_cost_per_m = 0.08
-output_cost_per_m = 0.39999999999999997
+output_cost_per_m = 0.28
 supports_tools = true
 supports_vision = false
 supports_streaming = true

providers/stepfun.toml

@@ -14,8 +14,8 @@ display_name = "Step 3.5 Flash"
 tier = "smart"
 context_window = 256000
 max_output_tokens = 256000
-input_cost_per_m = 0.0
+input_cost_per_m = 0.1
-output_cost_per_m = 0.0
+output_cost_per_m = 0.3
 supports_tools = true
 supports_vision = false
 supports_streaming = true
@@ -27,8 +27,8 @@ display_name = "Step 3"
 tier = "frontier"
 context_window = 65536
 max_output_tokens = 16384
-input_cost_per_m = 0.0
+input_cost_per_m = 0.1
-output_cost_per_m = 0.0
+output_cost_per_m = 0.3
 supports_tools = true
 supports_vision = true
 supports_streaming = true

providers/venice.toml

@@ -27,8 +27,8 @@ display_name = "Llama 3.3 70B (Venice)"
 tier = "balanced"
 context_window = 128000
 max_output_tokens = 8192
-input_cost_per_m = 0.0
+input_cost_per_m = 0.1
-output_cost_per_m = 0.0
+output_cost_per_m = 0.32
 supports_tools = true
 supports_vision = false
 supports_streaming = true

providers/xai.toml

@@ -79,8 +79,8 @@ display_name = "Grok 3"
 tier = "frontier"
 context_window = 131072
 max_output_tokens = 32768
-input_cost_per_m = 0.3
+input_cost_per_m = 3.0
-output_cost_per_m = 0.5
+output_cost_per_m = 15.0
 supports_tools = true
 supports_vision = true
 supports_streaming = true

providers/zhipu.toml

@@ -79,8 +79,8 @@ display_name = "GLM-4.7"
 tier = "smart"
 context_window = 131072
 max_output_tokens = 16384
-input_cost_per_m = 0.06
+input_cost_per_m = 0.39
-output_cost_per_m = 0.39999999999999997
+output_cost_per_m = 1.75
 supports_tools = true
 supports_vision = true
 supports_streaming = true