ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
15 models
Meta 128K+ Open weights
Meta: Muse Spark Open T
Reasoning Tools Open weights

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

meta/muse-spark-open 2026-10-15 1.04858M context $1.25/M input $4.25/M output
14 providers
Meta: Muse Glimmer 30B T
Reasoning Tools JSON Open weights

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

meta/muse-glimmer-30b 2026-08-10 131.072K context $0.2/M input $0.8/M output
12 providers
Meta: Llama Guard 4 12B T
Open weights

Multimodal Llama 4-based safety classifier for moderating prompts and responses

meta/llama-guard-4-12b 2025-04-29 163.84K context $0.18/M input $0.18/M output
4 providers
Meta: Llama 4 Scout 17B Instruct T
Tools JSON Open weights

Open Llama with long-context vision for efficient multimodal agents

meta/llama-4-scout-17b-instruct 2025-04-05 10M context $0.17/M input $0.66/M output
5 providers
Meta: Llama 4 Maverick 17B Instruct T
Tools Open weights

Open multimodal Llama for strong reasoning with efficient everyday serving

meta/llama-4-maverick-17b-instruct 2025-04-05 1M context $0.14/M input $0.59/M output
8 providers
Meta: Llama-3.3-70B-Instruct T
Tools Open weights

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

meta/llama-3.3-70b-instruct 2024-12-06 128K context $0.1/M input $0.32/M output
29 providers
Meta: Llama-3.2-1B T
Open weights

Compact open Llama base model for lightweight and on-device use

meta/llama-3.2-1b 2024-09-25 131.072K context Input not listed Output not listed
1 provider
Meta: Llama-3.2-3B T
Open weights

Small open Llama base model for lightweight text generation and self-hosting

meta/llama-3.2-3b 2024-09-25 131.072K context Input not listed Output not listed
1 provider
Meta: Llama-3.2-11B-Vision-Instruct T
Tools JSON Open weights

Open multimodal Llama model for image understanding, captioning, and visual QA

meta/llama-3.2-11b-vision-instruct 2024-09-25 128K context $0.055/M input $0.055/M output
3 providers
Meta: Llama 3.2 1B Instruct T
Open weights

Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants

meta/llama-3.2-1b-instruct 2024-09-25 131.072K context $0.01/M input $0.01/M output
7 providers
Meta: Llama-3.2-90B-Vision-Instruct T
Tools Open weights

Large open multimodal Llama model for image reasoning, document QA, and captioning

meta/llama-3.2-90b-vision-instruct 2024-09-25 128K context Input not listed Output not listed
1 provider
Meta: Llama 3.2 3B Instruct T
JSON Open weights

Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval

meta/llama-3.2-3b-instruct 2024-09-25 131.072K context $0.02/M input $0.02/M output
6 providers
Meta: Llama-Guard-3-8B T
Open weights

Llama 3.1-based safety classifier for moderating prompts and model responses

meta/llama-guard-3-8b 2024-07-23 128K context Input not listed Output not listed
1 provider
Meta: Llama-3.1-8B-Instruct T
Tools JSON Open weights

Compact open Llama model for lightweight chat, drafting, and self-hosting

meta/llama-3.1-8b-instruct 2024-07-23 128K context $0.02/M input $0.04/M output
8 providers
Meta: Llama-3.1-70B-Instruct T
Tools JSON Open weights

Open Llama instruction model for multilingual chat, reasoning, and coding

meta/llama-3.1-70b-instruct 2024-07-23 128K context $0.4/M input $0.4/M output
4 providers