stack-free-models.stack.json json {
"osr" : "1" ,
"kind" : "stack" ,
"name" : "Free models" ,
"description" : "Every request routed among hosted models that cost nothing per token; quality decides." ,
"targets" : [
{
"ocm" : "1" ,
"id" : "model-nvidia-nemotron-3-5-super-vl-free" ,
"kind" : "llm" ,
"name" : "Nemotron 3.5 Super VL (free)" ,
"description" : "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video..." ,
"publisher" : "NVIDIA" ,
"version" : "1.0.0" ,
"capabilities" : {
"domains" : [
"coding" ,
"math"
],
"tags" : [
"llm" ,
"nvidia" ,
"openrouter" ,
"open-weights" ,
"reasoning" ,
"free" ,
"tool-calling" ,
"image" ,
"video" ,
"models"
],
"languages" : [
"en"
],
"modalities" : [
"text" ,
"image" ,
"video"
],
"supports_tools" : true ,
"supports_streaming" : true ,
"context_window" : 1000000
},
"quality_prior" : 0.265 ,
"examples" : [
"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video..."
],
"primary" : false ,
"metadata" : {
"source" : {
"provider" : "models" ,
"ref" : "1792076662" ,
"url" : "https://openrouter.ai/nvidia/nemotron-3.5-super-vl:free" ,
"key" : "nvidia/nemotron-3.5-super-vl:free" ,
"catalogue" : "https://openrouter.ai/api/v1"
},
"model" : "nvidia/nemotron-3.5-super-vl:free" ,
"pricing" : {
"input_usd_per_1m" : 0 ,
"output_usd_per_1m" : 0
},
"max_output_tokens" : 131072 ,
"output_modalities" : [
"text"
],
"hugging_face_id" : "nvidia/NVIDIA-Nemotron-3.5-Super-VL" ,
"reasoning" : true ,
"created" : 1792076662 ,
"benchmarks" : {
"intelligence_index" : 26.5 ,
"osr_index" : 35.9 ,
"osr_coverage" : 0.4
}
},
"cost" : {
"usd_per_1k_tokens" : 0
},
"endpoints" : [
{
"protocol" : "openai" ,
"url" : "https://openrouter.ai/api/v1"
}
]
},
{
"ocm" : "1" ,
"id" : "model-thinkingmachines-inkling-small-free" ,
"kind" : "llm" ,
"name" : "Inkling Small (free)" ,
"description" : "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of..." ,
"publisher" : "Thinking Machines" ,
"version" : "1.0.0" ,
"capabilities" : {
"domains" : [
"coding" ,
"math"
],
"tags" : [
"llm" ,
"thinkingmachines" ,
"openrouter" ,
"open-weights" ,
"reasoning" ,
"free" ,
"tool-calling" ,
"image" ,
"audio" ,
"models"
],
"languages" : [
"en"
],
"modalities" : [
"text" ,
"image" ,
"audio"
],
"supports_tools" : true ,
"supports_streaming" : true ,
"context_window" : 1048576
},
"quality_prior" : 0.257 ,
"examples" : [
"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of..."
],
"primary" : false ,
"metadata" : {
"source" : {
"provider" : "models" ,
"ref" : "1785443117" ,
"url" : "https://openrouter.ai/thinkingmachines/inkling-small:free" ,
"key" : "thinkingmachines/inkling-small:free" ,
"catalogue" : "https://openrouter.ai/api/v1"
},
"model" : "thinkingmachines/inkling-small:free" ,
"pricing" : {
"input_usd_per_1m" : 0 ,
"output_usd_per_1m" : 0
},
"max_output_tokens" : 262144 ,
"output_modalities" : [
"text"
],
"hugging_face_id" : "thinkingmachines/Inkling-Small" ,
"reasoning" : true ,
"created" : 1785443117 ,
"benchmarks" : {
"intelligence_index" : 25.7 ,
"coding_index" : 52.9 ,
"agentic_index" : 23.5 ,
"osr_index" : 35.5 ,
"osr_coverage" : 0.4
}
},
"cost" : {
"usd_per_1k_tokens" : 0
},
"endpoints" : [
{
"protocol" : "openai" ,
"url" : "https://openrouter.ai/api/v1"
}
]
},
{
"ocm" : "1" ,
"id" : "model-thinkingmachines-inkling-free" ,
"kind" : "llm" ,
"name" : "Inkling (free)" ,
"description" : "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,..." ,
"publisher" : "Thinking Machines" ,
"version" : "1.0.0" ,
"capabilities" : {
"domains" : [
"coding" ,
"math"
],
"tags" : [
"llm" ,
"thinkingmachines" ,
"openrouter" ,
"open-weights" ,
"reasoning" ,
"free" ,
"tool-calling" ,
"image" ,
"audio" ,
"models"
],
"languages" : [
"en"
],
"modalities" : [
"text" ,
"image" ,
"audio"
],
"supports_tools" : true ,
"supports_streaming" : true ,
"context_window" : 1048576
},
"quality_prior" : 0.25 ,
"examples" : [
"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,..."
],
"primary" : false ,
"metadata" : {
"source" : {
"provider" : "models" ,
"ref" : "1784325956" ,
"url" : "https://openrouter.ai/thinkingmachines/inkling:free" ,
"key" : "thinkingmachines/inkling:free" ,
"catalogue" : "https://openrouter.ai/api/v1"
},
"model" : "thinkingmachines/inkling:free" ,
"pricing" : {
"input_usd_per_1m" : 0 ,
"output_usd_per_1m" : 0
},
"max_output_tokens" : 262144 ,
"output_modalities" : [
"text"
],
"hugging_face_id" : "thinkingmachines/Inkling" ,
"reasoning" : true ,
"created" : 1784325956 ,
"benchmarks" : {
"intelligence_index" : 25 ,
"coding_index" : 52.1 ,
"agentic_index" : 22.5 ,
"osr_index" : 35.1 ,
"osr_coverage" : 0.4
}
},
"cost" : {
"usd_per_1k_tokens" : 0
},
"endpoints" : [
{
"protocol" : "openai" ,
"url" : "https://openrouter.ai/api/v1"
}
]
},
{
"ocm" : "1" ,
"id" : "model-nvidia-nemotron-3-ultra-550b-a55b-free" ,
"kind" : "llm" ,
"name" : "Nemotron 3 Ultra (free)" ,
"description" : "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it..." ,
"publisher" : "NVIDIA" ,
"version" : "1.0.0" ,
"capabilities" : {
"domains" : [
"coding" ,
"math"
],
"tags" : [
"llm" ,
"nvidia" ,
"openrouter" ,
"open-weights" ,
"reasoning" ,
"free" ,
"tool-calling" ,
"models"
],
"languages" : [
"en"
],
"modalities" : [
"text"
],
"supports_tools" : true ,
"supports_streaming" : true ,
"context_window" : 1000000
},
"quality_prior" : 0.229 ,
"examples" : [
"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it..."
],
"primary" : false ,
"metadata" : {
"source" : {
"provider" : "models" ,
"ref" : "1780551208" ,
"url" : "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free" ,
"key" : "nvidia/nemotron-3-ultra-550b-a55b:free" ,
"catalogue" : "https://openrouter.ai/api/v1"
},
"model" : "nvidia/nemotron-3-ultra-550b-a55b:free" ,
"pricing" : {
"input_usd_per_1m" : 0 ,
"output_usd_per_1m" : 0
},
"max_output_tokens" : 65536 ,
"output_modalities" : [
"text"
],
"hugging_face_id" : "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16" ,
"reasoning" : true ,
"created" : 1780551208 ,
"benchmarks" : {
"intelligence_index" : 22.9 ,
"coding_index" : 49.3 ,
"agentic_index" : 20.1 ,
"osr_index" : 33.9 ,
"osr_coverage" : 0.4
}
},
"cost" : {
"usd_per_1k_tokens" : 0
},
"endpoints" : [
{
"protocol" : "openai" ,
"url" : "https://openrouter.ai/api/v1"
}
]
}
],
"rules" : [
{
"name" : "hard-to-strongest" ,
"when" : {
"min_complexity" : 0.7
},
"prefer" : [
"model-nvidia-nemotron-3-5-super-vl-free"
]
}
],
"objective" : {
"quality" : 0.7 ,
"cost" : 0.8 ,
"latency" : 0.2
},
"metadata" : {
"source" : {
"provider" : "catalogue-stacks" ,
"path" : "free-models" ,
"ref" : "2026-10-24" ,
"url" : "https://openrouter.ai/models" ,
"key" : "catalogue-stacks/free-models" ,
"catalogue" : "https://openrouter.ai/api/v1" ,
"generated" : true
}
}
}
