Packages
llm_db
2026.3.0
2026.7.3
2026.7.2
2026.7.1
2026.7.0
2026.6.4
2026.6.3
2026.6.2
2026.6.1
2026.6.0
2026.5.2
2026.5.1
2026.5.0
2026.4.8
2026.4.7
2026.4.6
2026.4.5
2026.4.4
2026.4.3
2026.4.2
2026.4.1
2026.4.0
2026.3.3
2026.3.2
2026.3.1
2026.3.0
2026.2.9
2026.2.8
2026.2.7
2026.2.6
2026.2.5
2026.2.4
2026.2.3
2026.2.2
2026.2.1
2026.2.0
2026.1.5
2026.1.4
2026.1.3
2026.1.2
2026.1.1
2026.1.0
2025.12.4
2025.12.3
2025.12.2
2025.12.1
2025.11.18-preview
2025.11.14-preview
2025.11.7-preview
LLM model metadata catalog with fast, capability-aware lookups.
Current section
Files
Jump to
Current section
Files
priv/llm_db/providers/inference.json
{
"alias_of": null,
"base_url": null,
"config_schema": null,
"doc": "https://inference.net/models",
"env": [
"INFERENCE_API_KEY"
],
"exclude_models": null,
"extra": null,
"id": "inference",
"models": {
"google/gemma-3": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.15,
"output": 0.3
},
"deprecated": false,
"extra": {
"attachment": true,
"family": "gemma",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "google/gemma-3",
"knowledge": "2024-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 125000,
"output": 4096
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"model": null,
"name": "Google Gemma 3",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"meta/llama-3.1-8b-instruct": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.025,
"output": 0.025
},
"deprecated": false,
"extra": {
"attachment": false,
"family": "llama",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "meta/llama-3.1-8b-instruct",
"knowledge": "2023-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 16000,
"output": 4096
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"model": null,
"name": "Llama 3.1 8B Instruct",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"meta/llama-3.2-11b-vision-instruct": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.055,
"output": 0.055
},
"deprecated": false,
"extra": {
"attachment": true,
"family": "llama",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "meta/llama-3.2-11b-vision-instruct",
"knowledge": "2023-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 16000,
"output": 4096
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"model": null,
"name": "Llama 3.2 11B Vision Instruct",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"meta/llama-3.2-1b-instruct": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.01,
"output": 0.01
},
"deprecated": false,
"extra": {
"attachment": false,
"family": "llama",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "meta/llama-3.2-1b-instruct",
"knowledge": "2023-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 16000,
"output": 4096
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"model": null,
"name": "Llama 3.2 1B Instruct",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"meta/llama-3.2-3b-instruct": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.02,
"output": 0.02
},
"deprecated": false,
"extra": {
"attachment": false,
"family": "llama",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "meta/llama-3.2-3b-instruct",
"knowledge": "2023-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 16000,
"output": 4096
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"model": null,
"name": "Llama 3.2 3B Instruct",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"mistral/mistral-nemo-12b-instruct": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.038,
"output": 0.1
},
"deprecated": false,
"extra": {
"attachment": false,
"family": "mistral-nemo",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "mistral/mistral-nemo-12b-instruct",
"knowledge": "2024-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 16000,
"output": 4096
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"model": null,
"name": "Mistral Nemo 12B Instruct",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"osmosis/osmosis-structure-0.6b": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.1,
"output": 0.5
},
"deprecated": false,
"extra": {
"attachment": false,
"family": "osmosis",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "osmosis/osmosis-structure-0.6b",
"knowledge": "2024-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 4000,
"output": 2048
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"model": null,
"name": "Osmosis Structure 0.6B",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"qwen/qwen-2.5-7b-vision-instruct": {
"aliases": [],
"base_url": null,
"capabilities": {
"chat": true,
"embeddings": false,
"json": {
"native": false,
"schema": false,
"strict": false
},
"reasoning": {
"enabled": false
},
"streaming": {
"tool_calls": true
},
"tools": {
"enabled": true
}
},
"cost": {
"input": 0.2,
"output": 0.2
},
"deprecated": false,
"extra": {
"attachment": true,
"family": "qwen",
"open_weights": true,
"temperature": true
},
"family": null,
"id": "qwen/qwen-2.5-7b-vision-instruct",
"knowledge": "2024-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 125000,
"output": 4096
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"model": null,
"name": "Qwen 2.5 7B Vision Instruct",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
},
"qwen/qwen3-embedding-4b": {
"aliases": [],
"base_url": null,
"capabilities": null,
"cost": {
"input": 0.01,
"output": 0
},
"deprecated": false,
"extra": {
"attachment": false,
"family": "qwen",
"open_weights": true,
"temperature": false
},
"family": null,
"id": "qwen/qwen3-embedding-4b",
"knowledge": "2024-12",
"last_updated": "2025-01-01",
"lifecycle": null,
"limits": {
"context": 32000,
"output": 2048
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"model": null,
"name": "Qwen 3 Embedding 4B",
"pricing": null,
"provider": "inference",
"provider_model_id": null,
"release_date": "2025-01-01",
"retired": false,
"tags": null
}
},
"name": "Inference",
"pricing_defaults": null
}