stack-meta-llama.stack.json json {
"osr": "1",
"kind": "stack",
"name": "Meta tiers",
"description": "Meta only: Llama 3.1 8B Instruct for everyday requests, Llama 3.3 70B Instruct for moderate work, Llama 3.1 70B Instruct for hard ones - with complexity rules and a cost-aware objective.",
"targets": [
{
"ocm": "1",
"id": "model-meta-llama-llama-3-1-8b-instruct",
"kind": "llm",
"name": "Llama 3.1 8B Instruct",
"description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...",
"publisher": "Meta",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"llm",
"meta-llama",
"openrouter",
"open-weights",
"tool-calling",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 131072
},
"quality_prior": 0.6,
"examples": [
"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1721692800",
"url": "https://openrouter.ai/meta-llama/llama-3.1-8b-instruct",
"key": "meta-llama/llama-3.1-8b-instruct",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "meta-llama/llama-3.1-8b-instruct",
"pricing": {
"input_usd_per_1m": 0.05,
"output_usd_per_1m": 0.08,
"cache_read_usd_per_1m": 0.025
},
"max_output_tokens": 117964,
"output_modalities": [
"text"
],
"hugging_face_id": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"created": 1721692800,
"benchmarks": {
"coding_index": 5.4,
"ifeval": 49.2,
"bbh": 50.9,
"math_lvl5": 15.6,
"gpqa": 31.5,
"musr": 39.7,
"mmlu_pro": 38,
"hf_leaderboard_avg": 37.5,
"hub_downloads": 5934139,
"hub_downloads_total": 184687159,
"hub_likes": 7715,
"hub_trending": 215,
"mmlu": 0.73,
"osr_index": 30.6,
"osr_coverage": 0.3
}
},
"cost": {
"usd_per_1k_tokens": 0.000065
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-meta-llama-llama-3-3-70b-instruct",
"kind": "llm",
"name": "Llama 3.3 70B Instruct",
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...",
"publisher": "Meta",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"meta-llama",
"openrouter",
"open-weights",
"tool-calling",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 131072
},
"quality_prior": 0.6,
"examples": [
"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1733506137",
"url": "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct",
"key": "meta-llama/llama-3.3-70b-instruct",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "meta-llama/llama-3.3-70b-instruct",
"pricing": {
"input_usd_per_1m": 0.1,
"output_usd_per_1m": 0.32
},
"max_output_tokens": 16384,
"output_modalities": [
"text"
],
"hugging_face_id": "meta-llama/Llama-3.3-70B-Instruct",
"created": 1733506137,
"benchmarks": {
"coding_index": 11.9,
"ifeval": 90,
"bbh": 69.2,
"math_lvl5": 48.3,
"gpqa": 32.9,
"musr": 44.6,
"mmlu_pro": 53.3,
"hf_leaderboard_avg": 56.4,
"hub_downloads_total": 14539092,
"hub_likes": 3042,
"hub_trending": 11,
"hub_downloads": 920801,
"osr_index": 38.7,
"osr_coverage": 0.3
}
},
"cost": {
"usd_per_1k_tokens": 0.00021
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
},
{
"ocm": "1",
"id": "model-meta-llama-llama-3-1-70b-instruct",
"kind": "llm",
"name": "Llama 3.1 70B Instruct",
"description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...",
"publisher": "Meta",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"llm",
"meta-llama",
"openrouter",
"open-weights",
"tool-calling",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 131072
},
"quality_prior": 0.6,
"examples": [
"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1721692800",
"url": "https://openrouter.ai/meta-llama/llama-3.1-70b-instruct",
"key": "meta-llama/llama-3.1-70b-instruct",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "meta-llama/llama-3.1-70b-instruct",
"pricing": {
"input_usd_per_1m": 0.4,
"output_usd_per_1m": 0.4
},
"max_output_tokens": 16384,
"output_modalities": [
"text"
],
"hugging_face_id": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"created": 1721692800,
"benchmarks": {
"ifeval": 86.7,
"bbh": 69.2,
"math_lvl5": 38.1,
"gpqa": 35.6,
"musr": 45.8,
"mmlu_pro": 53.1,
"hf_leaderboard_avg": 54.8,
"hub_likes": 983,
"hub_trending": 1,
"hub_downloads": 157151,
"hub_downloads_total": 24463496,
"mmlu": 0.86,
"osr_index": 38,
"osr_coverage": 0.3
}
},
"cost": {
"usd_per_1k_tokens": 0.0004
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
],
"rules": [
{
"name": "hard-to-strongest",
"when": {
"min_complexity": 0.7
},
"prefer": [
"model-meta-llama-llama-3-1-70b-instruct"
]
},
{
"name": "easy-stays-cheap",
"when": {
"max_complexity": 0.3
},
"avoid": [
"model-meta-llama-llama-3-1-70b-instruct"
]
}
],
"objective": {
"quality": 0.7,
"cost": 0.8,
"latency": 0.2
},
"metadata": {
"source": {
"provider": "catalogue-stacks",
"path": "meta-llama",
"ref": "2026-09-19",
"url": "https://openrouter.ai/meta-llama",
"key": "catalogue-stacks/meta-llama",
"catalogue": "https://openrouter.ai/api/v1",
"generated": true
}
}
}
