From 310c03b1e607f947c9c05756b9beba57308f6b9c Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Wed, 25 Mar 2026 14:50:12 +0000 Subject: [PATCH] chore: sync model pricing from OpenRouter API --- providers/deepseek.toml | 4 ++-- providers/moonshot.toml | 4 ++-- providers/nvidia-nim.toml | 22 +++++++++++----------- providers/openai.toml | 16 ++++++++-------- providers/qwen.toml | 6 +++--- providers/stepfun.toml | 8 ++++---- providers/venice.toml | 4 ++-- providers/xai.toml | 4 ++-- providers/zhipu.toml | 4 ++-- 9 files changed, 36 insertions(+), 36 deletions(-) diff --git a/providers/deepseek.toml b/providers/deepseek.toml index ea0aab6..40f6574 100644 --- a/providers/deepseek.toml +++ b/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 -output_cost_per_m = 0.75 +input_cost_per_m = 0.32 +output_cost_per_m = 0.89 supports_tools = true supports_vision = false supports_streaming = true diff --git a/providers/moonshot.toml b/providers/moonshot.toml index 622154a..147d6d6 100644 --- a/providers/moonshot.toml +++ b/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 -output_cost_per_m = 2.2 +input_cost_per_m = 0.57 +output_cost_per_m = 2.3 supports_tools = true supports_vision = true supports_streaming = true diff --git a/providers/nvidia-nim.toml b/providers/nvidia-nim.toml index 522be58..3b2059d 100644 --- a/providers/nvidia-nim.toml +++ b/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 -output_cost_per_m = 5.00 +input_cost_per_m = 0.6 +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 -output_cost_per_m = 0.10 +input_cost_per_m = 1.2 +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 -output_cost_per_m = 2.40 +input_cost_per_m = 0.39 +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 -output_cost_per_m = 0.10 +input_cost_per_m = 0.15 +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 -output_cost_per_m = 0.10 +input_cost_per_m = 0.08 +output_cost_per_m = 0.16 supports_tools = false supports_vision = false supports_streaming = true diff --git a/providers/openai.toml b/providers/openai.toml index 74df6a5..d47a449 100644 --- a/providers/openai.toml +++ b/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 -output_cost_per_m = 40.0 +input_cost_per_m = 2.0 +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 -output_cost_per_m = 8.0 +input_cost_per_m = 1.1 +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 -output_cost_per_m = 2.0 +input_cost_per_m = 0.5 +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 -output_cost_per_m = 1.25 +input_cost_per_m = 1.25 +output_cost_per_m = 10.0 supports_tools = true supports_vision = true supports_streaming = true diff --git a/providers/qwen.toml b/providers/qwen.toml index 6d68987..a8b3354 100644 --- a/providers/qwen.toml +++ b/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 -output_cost_per_m = 1.495 +input_cost_per_m = 0.455 +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 diff --git a/providers/stepfun.toml b/providers/stepfun.toml index 7716392..20b2bac 100644 --- a/providers/stepfun.toml +++ b/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 -output_cost_per_m = 0.0 +input_cost_per_m = 0.1 +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 -output_cost_per_m = 0.0 +input_cost_per_m = 0.1 +output_cost_per_m = 0.3 supports_tools = true supports_vision = true supports_streaming = true diff --git a/providers/venice.toml b/providers/venice.toml index 16a1e1e..bcba2d7 100644 --- a/providers/venice.toml +++ b/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 -output_cost_per_m = 0.0 +input_cost_per_m = 0.1 +output_cost_per_m = 0.32 supports_tools = true supports_vision = false supports_streaming = true diff --git a/providers/xai.toml b/providers/xai.toml index a7704f7..39a1485 100644 --- a/providers/xai.toml +++ b/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 -output_cost_per_m = 0.5 +input_cost_per_m = 3.0 +output_cost_per_m = 15.0 supports_tools = true supports_vision = true supports_streaming = true diff --git a/providers/zhipu.toml b/providers/zhipu.toml index 266b5ef..6477137 100644 --- a/providers/zhipu.toml +++ b/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 -output_cost_per_m = 0.39999999999999997 +input_cost_per_m = 0.39 +output_cost_per_m = 1.75 supports_tools = true supports_vision = true supports_streaming = true