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"
+display_name = "Arcee AI: Trinity Large Preview"
+tier = "fast"
+context_window = 131000
+max_output_tokens = 16384
+input_cost_per_m = 0.15
+output_cost_per_m = 0.45
+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/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/microsoft.toml

@@ -0,0 +1,28 @@
+# microsoft — auto-generated from OpenRouter API
+
+[provider]
+id = "microsoft"
+display_name = "Microsoft"
+api_key_env = "GITHUB_TOKEN"
+base_url = "https://models.inference.ai.azure.com"
+key_required = true
+
+[[models]]
+id = "phi-4"
+display_name = "Microsoft: Phi 4"
+tier = "fast"
+context_window = 16384
+max_output_tokens = 16384
+input_cost_per_m = 0.065
+output_cost_per_m = 0.14
+supports_streaming = true
+
+[[models]]
+id = "wizardlm-2-8x22b"
+display_name = "WizardLM-2 8x22B"
+tier = "smart"
+context_window = 65535
+max_output_tokens = 8000
+input_cost_per_m = 0.62
+output_cost_per_m = 0.62
+supports_streaming = true

providers/openrouter.toml

@@ -256,3 +256,343 @@ supports_tools = false
 supports_vision = false
 supports_streaming = true
 aliases = []
+
+[[models]]
+id = "openrouter/ai21/jamba-large-1.7"
+display_name = "AI21: Jamba Large 1.7 (OpenRouter)"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 4096
+input_cost_per_m = 2.0
+output_cost_per_m = 8.0
+supports_streaming = true
+
+[[models]]
+id = "openrouter/alibaba/tongyi-deepresearch-30b-a3b"
+display_name = "Tongyi DeepResearch 30B A3B (OpenRouter)"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 131072
+input_cost_per_m = 0.09
+output_cost_per_m = 0.45
+supports_streaming = true
+
+[[models]]
+id = "openrouter/allenai/olmo-3-32b-think"
+display_name = "AllenAI: Olmo 3 32B Think (OpenRouter)"
+tier = "fast"
+context_window = 65536
+max_output_tokens = 65536
+input_cost_per_m = 0.15
+output_cost_per_m = 0.5
+supports_streaming = true
+
+[[models]]
+id = "openrouter/allenai/olmo-3.1-32b-instruct"
+display_name = "AllenAI: Olmo 3.1 32B Instruct (OpenRouter)"
+tier = "fast"
+context_window = 65536
+max_output_tokens = 16384
+input_cost_per_m = 0.2
+output_cost_per_m = 0.6
+supports_streaming = true
+
+[[models]]
+id = "openrouter/amazon/nova-2-lite-v1"
+display_name = "Amazon: Nova 2 Lite (OpenRouter)"
+tier = "fast"
+context_window = 1000000
+max_output_tokens = 65535
+input_cost_per_m = 0.3
+output_cost_per_m = 2.5
+supports_streaming = true
+
+[[models]]
+id = "openrouter/amazon/nova-lite-v1"
+display_name = "Amazon: Nova Lite 1.0 (OpenRouter)"
+tier = "fast"
+context_window = 300000
+max_output_tokens = 5120
+input_cost_per_m = 0.06
+output_cost_per_m = 0.24
+supports_streaming = true
+
+[[models]]
+id = "openrouter/amazon/nova-micro-v1"
+display_name = "Amazon: Nova Micro 1.0 (OpenRouter)"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 5120
+input_cost_per_m = 0.035
+output_cost_per_m = 0.14
+supports_streaming = true
+
+[[models]]
+id = "openrouter/amazon/nova-premier-v1"
+display_name = "Amazon: Nova Premier 1.0 (OpenRouter)"
+tier = "smart"
+context_window = 1000000
+max_output_tokens = 32000
+input_cost_per_m = 2.5
+output_cost_per_m = 12.5
+supports_streaming = true
+
+[[models]]
+id = "openrouter/amazon/nova-pro-v1"
+display_name = "Amazon: Nova Pro 1.0 (OpenRouter)"
+tier = "smart"
+context_window = 300000
+max_output_tokens = 5120
+input_cost_per_m = 0.8
+output_cost_per_m = 3.2
+supports_streaming = true
+
+[[models]]
+id = "openrouter/bytedance/ui-tars-1.5-7b"
+display_name = "ByteDance: UI-TARS 7B  (OpenRouter)"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 2048
+input_cost_per_m = 0.1
+output_cost_per_m = 0.2
+supports_streaming = true
+
+[[models]]
+id = "openrouter/deepcogito/cogito-v2.1-671b"
+display_name = "Deep Cogito: Cogito v2.1 671B (OpenRouter)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 16384
+input_cost_per_m = 1.25
+output_cost_per_m = 1.25
+supports_streaming = true
+
+[[models]]
+id = "openrouter/essentialai/rnj-1-instruct"
+display_name = "EssentialAI: Rnj 1 Instruct (OpenRouter)"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.15
+output_cost_per_m = 0.15
+supports_streaming = true
+
+[[models]]
+id = "openrouter/inclusionai/ling-2.6-1t:free"
+display_name = "inclusionAI: Ling-2.6-1T (free) (OpenRouter)"
+tier = "fast"
+context_window = 262144
+max_output_tokens = 32768
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true
+
+[[models]]
+id = "openrouter/inclusionai/ling-2.6-flash:free"
+display_name = "inclusionAI: Ling-2.6-flash (free) (OpenRouter)"
+tier = "fast"
+context_window = 262144
+max_output_tokens = 32768
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_streaming = true
+
+[[models]]
+id = "openrouter/inflection/inflection-3-pi"
+display_name = "Inflection: Inflection 3 Pi (OpenRouter)"
+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 = "openrouter/inflection/inflection-3-productivity"
+display_name = "Inflection: Inflection 3 Productivity (OpenRouter)"
+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 = "openrouter/liquid/lfm-2-24b-a2b"
+display_name = "LiquidAI: LFM2-24B-A2B (OpenRouter)"
+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 = "openrouter/liquid/lfm-2.5-1.2b-instruct:free"
+display_name = "LiquidAI: LFM2.5-1.2B-Instruct (free) (OpenRouter)"
+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 = "openrouter/liquid/lfm-2.5-1.2b-thinking:free"
+display_name = "LiquidAI: LFM2.5-1.2B-Thinking (free) (OpenRouter)"
+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 = "openrouter/nex-agi/deepseek-v3.1-nex-n1"
+display_name = "Nex AGI: DeepSeek V3.1 Nex N1 (OpenRouter)"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 163840
+input_cost_per_m = 0.135
+output_cost_per_m = 0.5
+supports_streaming = true
+
+[[models]]
+id = "openrouter/nousresearch/hermes-2-pro-llama-3-8b"
+display_name = "NousResearch: Hermes 2 Pro - Llama-3 8B (OpenRouter)"
+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 = "openrouter/nousresearch/hermes-3-llama-3.1-405b"
+display_name = "Nous: Hermes 3 405B Instruct (OpenRouter)"
+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 = "openrouter/nousresearch/hermes-3-llama-3.1-405b:free"
+display_name = "Nous: Hermes 3 405B Instruct (free) (OpenRouter)"
+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 = "openrouter/nousresearch/hermes-3-llama-3.1-70b"
+display_name = "Nous: Hermes 3 70B Instruct (OpenRouter)"
+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 = "openrouter/nousresearch/hermes-4-405b"
+display_name = "Nous: Hermes 4 405B (OpenRouter)"
+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 = "openrouter/nousresearch/hermes-4-70b"
+display_name = "Nous: Hermes 4 70B (OpenRouter)"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.13
+output_cost_per_m = 0.4
+supports_streaming = true
+
+[[models]]
+id = "openrouter/prime-intellect/intellect-3"
+display_name = "Prime Intellect: INTELLECT-3 (OpenRouter)"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 131072
+input_cost_per_m = 0.2
+output_cost_per_m = 1.1
+supports_streaming = true
+
+[[models]]
+id = "openrouter/rekaai/reka-edge"
+display_name = "Reka Edge (OpenRouter)"
+tier = "fast"
+context_window = 16384
+max_output_tokens = 16384
+input_cost_per_m = 0.1
+output_cost_per_m = 0.1
+supports_streaming = true
+
+[[models]]
+id = "openrouter/rekaai/reka-flash-3"
+display_name = "Reka Flash 3 (OpenRouter)"
+tier = "fast"
+context_window = 65536
+max_output_tokens = 65536
+input_cost_per_m = 0.1
+output_cost_per_m = 0.2
+supports_streaming = true
+
+[[models]]
+id = "openrouter/relace/relace-apply-3"
+display_name = "Relace: Relace Apply 3 (OpenRouter)"
+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 = "openrouter/relace/relace-search"
+display_name = "Relace: Relace Search (OpenRouter)"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 128000
+input_cost_per_m = 1.0
+output_cost_per_m = 3.0
+supports_streaming = true
+
+[[models]]
+id = "openrouter/switchpoint/router"
+display_name = "Switchpoint Router (OpenRouter)"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.85
+output_cost_per_m = 3.4
+supports_streaming = true
+
+[[models]]
+id = "openrouter/tngtech/deepseek-r1t2-chimera"
+display_name = "TNG: DeepSeek R1T2 Chimera (OpenRouter)"
+tier = "fast"
+context_window = 163840
+max_output_tokens = 163840
+input_cost_per_m = 0.3
+output_cost_per_m = 1.1
+supports_streaming = true
+
+[[models]]
+id = "openrouter/writer/palmyra-x5"
+display_name = "Writer: Palmyra X5 (OpenRouter)"
+tier = "smart"
+context_window = 1040000
+max_output_tokens = 8192
+input_cost_per_m = 0.6
+output_cost_per_m = 6.0
+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/xiaomi.toml

@@ -0,0 +1,58 @@
+# xiaomi — auto-generated from OpenRouter API
+
+[provider]
+id = "xiaomi"
+display_name = "Xiaomi"
+api_key_env = "XIAOMI_ACCESS_KEY_ID"
+base_url = "https://cnbj3-cloud-ml.api.xiaomi.net"
+key_required = true
+
+[[models]]
+id = "mimo-v2-flash"
+display_name = "Xiaomi: MiMo-V2-Flash"
+tier = "fast"
+context_window = 262144
+max_output_tokens = 65536
+input_cost_per_m = 0.09
+output_cost_per_m = 0.29
+supports_streaming = true
+
+[[models]]
+id = "mimo-v2-omni"
+display_name = "Xiaomi: MiMo-V2-Omni"
+tier = "fast"
+context_window = 262144
+max_output_tokens = 65536
+input_cost_per_m = 0.4
+output_cost_per_m = 2.0
+supports_streaming = true
+
+[[models]]
+id = "mimo-v2-pro"
+display_name = "Xiaomi: MiMo-V2-Pro"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 131072
+input_cost_per_m = 1.0
+output_cost_per_m = 3.0
+supports_streaming = true
+
+[[models]]
+id = "mimo-v2.5"
+display_name = "Xiaomi: MiMo-V2.5"
+tier = "fast"
+context_window = 1048576
+max_output_tokens = 131072
+input_cost_per_m = 0.4
+output_cost_per_m = 2.0
+supports_streaming = true
+
+[[models]]
+id = "mimo-v2.5-pro"
+display_name = "Xiaomi: MiMo-V2.5-Pro"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 131072
+input_cost_per_m = 1.0
+output_cost_per_m = 3.0
+supports_streaming = true