chore: sync model pricing from OpenRouter API

providers/aion-labs.toml

@@ -0,0 +1,48 @@
+# aion-labs — auto-generated from OpenRouter API
+
+[provider]
+id = "aion-labs"
+display_name = "Aion Labs"
+api_key_env = "AION_LABS_API_KEY"
+base_url = "https://api.aionlabs.ai/v1"
+key_required = true
+
+[[models]]
+id = "aion-1.0"
+display_name = "AionLabs: Aion-1.0"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 32768
+input_cost_per_m = 4.0
+output_cost_per_m = 8.0
+supports_streaming = true
+
+[[models]]
+id = "aion-1.0-mini"
+display_name = "AionLabs: Aion-1.0-Mini"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 32768
+input_cost_per_m = 0.7
+output_cost_per_m = 1.4
+supports_streaming = true
+
+[[models]]
+id = "aion-2.0"
+display_name = "AionLabs: Aion-2.0"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 32768
+input_cost_per_m = 0.8
+output_cost_per_m = 1.6
+supports_streaming = true
+
+[[models]]
+id = "aion-rp-llama-3.1-8b"
+display_name = "AionLabs: Aion-RP 1.0 (8B)"
+tier = "smart"
+context_window = 32768
+max_output_tokens = 32768
+input_cost_per_m = 0.8
+output_cost_per_m = 1.6
+supports_streaming = true

providers/arcee-ai.toml

@@ -0,0 +1,78 @@
+# arcee-ai — auto-generated from OpenRouter API
+
+[provider]
+id = "arcee-ai"
+display_name = "Arcee Ai"
+api_key_env = "ARCEE_API_KEY"
+base_url = "https://api.arcee.ai/v1"
+key_required = true
+
+[[models]]
+id = "coder-large"
+display_name = "Arcee AI: Coder Large"
+tier = "smart"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.5
+output_cost_per_m = 0.8
+supports_streaming = true
+
+[[models]]
+id = "maestro-reasoning"
+display_name = "Arcee AI: Maestro Reasoning"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 32000
+input_cost_per_m = 0.9
+output_cost_per_m = 3.3
+supports_streaming = true
+
+[[models]]
+id = "spotlight"
+display_name = "Arcee AI: Spotlight"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 65537
+input_cost_per_m = 0.18
+output_cost_per_m = 0.18
+supports_streaming = true
+
+[[models]]
+id = "trinity-large-preview:free"
+display_name = "Arcee AI: Trinity Large Preview (free)"
+tier = "fast"
+context_window = 131000
+max_output_tokens = 16384
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true
+
+[[models]]
+id = "trinity-large-thinking"
+display_name = "Arcee AI: Trinity Large Thinking"
+tier = "fast"
+context_window = 262144
+max_output_tokens = 262144
+input_cost_per_m = 0.22
+output_cost_per_m = 0.85
+supports_streaming = true
+
+[[models]]
+id = "trinity-mini"
+display_name = "Arcee AI: Trinity Mini"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 131072
+input_cost_per_m = 0.045
+output_cost_per_m = 0.15
+supports_streaming = true
+
+[[models]]
+id = "virtuoso-large"
+display_name = "Arcee AI: Virtuoso Large"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 64000
+input_cost_per_m = 0.75
+output_cost_per_m = 1.2
+supports_streaming = true

providers/deepcogito.toml

@@ -0,0 +1,18 @@
+# deepcogito — auto-generated from OpenRouter API
+
+[provider]
+id = "deepcogito"
+display_name = "Deepcogito"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "cogito-v2.1-671b"
+display_name = "Deep Cogito: Cogito v2.1 671B"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 16384
+input_cost_per_m = 1.25
+output_cost_per_m = 1.25
+supports_streaming = true

providers/essentialai.toml

@@ -0,0 +1,18 @@
+# essentialai — auto-generated from OpenRouter API
+
+[provider]
+id = "essentialai"
+display_name = "Essentialai"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "rnj-1-instruct"
+display_name = "EssentialAI: Rnj 1 Instruct"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.15
+output_cost_per_m = 0.15
+supports_streaming = true

providers/ibm-granite.toml

@@ -0,0 +1,18 @@
+# ibm-granite — auto-generated from OpenRouter API
+
+[provider]
+id = "ibm-granite"
+display_name = "Ibm Granite"
+api_key_env = "WATSONX_API_KEY"
+base_url = "https://us-south.ml.cloud.ibm.com/ml/v1"
+key_required = true
+
+[[models]]
+id = "granite-4.0-h-micro"
+display_name = "IBM: Granite 4.0 Micro"
+tier = "fast"
+context_window = 131000
+max_output_tokens = 16384
+input_cost_per_m = 0.017
+output_cost_per_m = 0.11
+supports_streaming = true

providers/inception.toml

@@ -0,0 +1,18 @@
+# inception — auto-generated from OpenRouter API
+
+[provider]
+id = "inception"
+display_name = "Inception"
+api_key_env = "INCEPTION_API_KEY"
+base_url = "https://api.inceptionlabs.ai/v1"
+key_required = true
+
+[[models]]
+id = "mercury-2"
+display_name = "Inception: Mercury 2"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 50000
+input_cost_per_m = 0.25
+output_cost_per_m = 0.75
+supports_streaming = true

providers/inflection.toml

@@ -0,0 +1,28 @@
+# inflection — auto-generated from OpenRouter API
+
+[provider]
+id = "inflection"
+display_name = "Inflection"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "inflection-3-pi"
+display_name = "Inflection: Inflection 3 Pi"
+tier = "smart"
+context_window = 8000
+max_output_tokens = 1024
+input_cost_per_m = 2.5
+output_cost_per_m = 10.0
+supports_streaming = true
+
+[[models]]
+id = "inflection-3-productivity"
+display_name = "Inflection: Inflection 3 Productivity"
+tier = "smart"
+context_window = 8000
+max_output_tokens = 1024
+input_cost_per_m = 2.5
+output_cost_per_m = 10.0
+supports_streaming = true

providers/kwaipilot.toml

@@ -0,0 +1,18 @@
+# kwaipilot — auto-generated from OpenRouter API
+
+[provider]
+id = "kwaipilot"
+display_name = "Kwaipilot"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "kat-coder-pro-v2"
+display_name = "Kwaipilot: KAT-Coder-Pro V2"
+tier = "fast"
+context_window = 256000
+max_output_tokens = 80000
+input_cost_per_m = 0.3
+output_cost_per_m = 1.2
+supports_streaming = true

providers/liquid.toml

@@ -0,0 +1,38 @@
+# liquid — auto-generated from OpenRouter API
+
+[provider]
+id = "liquid"
+display_name = "Liquid"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "lfm-2-24b-a2b"
+display_name = "LiquidAI: LFM2-24B-A2B"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.03
+output_cost_per_m = 0.12
+supports_streaming = true
+
+[[models]]
+id = "lfm-2.5-1.2b-instruct:free"
+display_name = "LiquidAI: LFM2.5-1.2B-Instruct (free)"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true
+
+[[models]]
+id = "lfm-2.5-1.2b-thinking:free"
+display_name = "LiquidAI: LFM2.5-1.2B-Thinking (free)"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true

providers/meta-llama.toml

@@ -34,8 +34,8 @@ display_name = "Meta: Llama 3.3 70B Instruct"
 tier = "fast"
 context_window = 131072
 max_output_tokens = 16384
-input_cost_per_m = 0.48
+input_cost_per_m = 0.1
-output_cost_per_m = 0.03
+output_cost_per_m = 0.32
 supports_streaming = true
 
 [[models]]

providers/morph.toml

@@ -0,0 +1,28 @@
+# morph — auto-generated from OpenRouter API
+
+[provider]
+id = "morph"
+display_name = "Morph"
+api_key_env = "MORPH_API_KEY"
+base_url = "https://api.morphllm.com/v1"
+key_required = true
+
+[[models]]
+id = "morph-v3-fast"
+display_name = "Morph: Morph V3 Fast"
+tier = "smart"
+context_window = 81920
+max_output_tokens = 38000
+input_cost_per_m = 0.8
+output_cost_per_m = 1.2
+supports_streaming = true
+
+[[models]]
+id = "morph-v3-large"
+display_name = "Morph: Morph V3 Large"
+tier = "smart"
+context_window = 262144
+max_output_tokens = 131072
+input_cost_per_m = 0.9
+output_cost_per_m = 1.9
+supports_streaming = true

providers/nex-agi.toml

@@ -0,0 +1,18 @@
+# nex-agi — auto-generated from OpenRouter API
+
+[provider]
+id = "nex-agi"
+display_name = "Nex Agi"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "deepseek-v3.1-nex-n1"
+display_name = "Nex AGI: DeepSeek V3.1 Nex N1"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 163840
+input_cost_per_m = 0.135
+output_cost_per_m = 0.5
+supports_streaming = true

providers/nousresearch.toml

@@ -0,0 +1,68 @@
+# nousresearch — auto-generated from OpenRouter API
+
+[provider]
+id = "nousresearch"
+display_name = "Nousresearch"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "hermes-2-pro-llama-3-8b"
+display_name = "NousResearch: Hermes 2 Pro - Llama-3 8B"
+tier = "fast"
+context_window = 8192
+max_output_tokens = 8192
+input_cost_per_m = 0.14
+output_cost_per_m = 0.14
+supports_streaming = true
+
+[[models]]
+id = "hermes-3-llama-3.1-405b"
+display_name = "Nous: Hermes 3 405B Instruct"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 1.0
+output_cost_per_m = 1.0
+supports_streaming = true
+
+[[models]]
+id = "hermes-3-llama-3.1-405b:free"
+display_name = "Nous: Hermes 3 405B Instruct (free)"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true
+
+[[models]]
+id = "hermes-3-llama-3.1-70b"
+display_name = "Nous: Hermes 3 70B Instruct"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.3
+output_cost_per_m = 0.3
+supports_streaming = true
+
+[[models]]
+id = "hermes-4-405b"
+display_name = "Nous: Hermes 4 405B"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 1.0
+output_cost_per_m = 3.0
+supports_streaming = true
+
+[[models]]
+id = "hermes-4-70b"
+display_name = "Nous: Hermes 4 70B"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.13
+output_cost_per_m = 0.4
+supports_streaming = true

providers/ollama.toml

@@ -42,8 +42,8 @@ display_name = "Qwen 3"
 tier = "local"
 context_window = 40960
 max_output_tokens = 8192
-input_cost_per_m = 0.0
+input_cost_per_m = 0.325
-output_cost_per_m = 0.0
+output_cost_per_m = 1.95
 supports_tools = true
 supports_vision = false
 supports_streaming = true
@@ -56,8 +56,8 @@ display_name = "QwQ"
 tier = "local"
 context_window = 40960
 max_output_tokens = 8192
-input_cost_per_m = 0.0
+input_cost_per_m = 0.15
-output_cost_per_m = 0.0
+output_cost_per_m = 0.58
 supports_tools = true
 supports_vision = false
 supports_streaming = true

providers/prime-intellect.toml

@@ -0,0 +1,18 @@
+# prime-intellect — auto-generated from OpenRouter API
+
+[provider]
+id = "prime-intellect"
+display_name = "Prime Intellect"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "intellect-3"
+display_name = "Prime Intellect: INTELLECT-3"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 131072
+input_cost_per_m = 0.2
+output_cost_per_m = 1.1
+supports_streaming = true

providers/relace.toml

@@ -0,0 +1,28 @@
+# relace — auto-generated from OpenRouter API
+
+[provider]
+id = "relace"
+display_name = "Relace"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "relace-apply-3"
+display_name = "Relace: Relace Apply 3"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 128000
+input_cost_per_m = 0.85
+output_cost_per_m = 1.25
+supports_streaming = true
+
+[[models]]
+id = "relace-search"
+display_name = "Relace: Relace Search"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 128000
+input_cost_per_m = 1.0
+output_cost_per_m = 3.0
+supports_streaming = true

providers/switchpoint.toml

@@ -0,0 +1,18 @@
+# switchpoint — auto-generated from OpenRouter API
+
+[provider]
+id = "switchpoint"
+display_name = "Switchpoint"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "router"
+display_name = "Switchpoint Router"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.85
+output_cost_per_m = 3.4
+supports_streaming = true

providers/tngtech.toml

@@ -0,0 +1,18 @@
+# tngtech — auto-generated from OpenRouter API
+
+[provider]
+id = "tngtech"
+display_name = "Tngtech"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "deepseek-r1t2-chimera"
+display_name = "TNG: DeepSeek R1T2 Chimera"
+tier = "fast"
+context_window = 163840
+max_output_tokens = 163840
+input_cost_per_m = 0.3
+output_cost_per_m = 1.1
+supports_streaming = true

providers/upstage.toml

@@ -0,0 +1,18 @@
+# upstage — auto-generated from OpenRouter API
+
+[provider]
+id = "upstage"
+display_name = "Upstage"
+api_key_env = "UPSTAGE_API_KEY"
+base_url = "https://api.upstage.ai/v1"
+key_required = true
+
+[[models]]
+id = "solar-pro-3"
+display_name = "Upstage: Solar Pro 3"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 16384
+input_cost_per_m = 0.15
+output_cost_per_m = 0.6
+supports_streaming = true

providers/writer.toml

@@ -0,0 +1,18 @@
+# writer — auto-generated from OpenRouter API
+
+[provider]
+id = "writer"
+display_name = "Writer"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "palmyra-x5"
+display_name = "Writer: Palmyra X5"
+tier = "smart"
+context_window = 1040000
+max_output_tokens = 8192
+input_cost_per_m = 0.6
+output_cost_per_m = 6.0
+supports_streaming = true