meta/muse-wonder-20261012
Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window. The model handles long-horizon work: it plans, delegates
- Context window
- 1,048,576
- Input modalities
- text, image, video, file, audio
- Output modalities
- text
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 43.6
Inference prices
- Published price : $0.20 / cache_read_tokens_per_million · openRouter ↗
- Published price : $4.00 / input_tokens_per_million · openRouter ↗
- Published price : $20.00 / output_tokens_per_million · openRouter ↗
meta/muse-spark-1.3-20260902
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed, with an
- Context window
- 1,048,576
- Input modalities
- text, image, video, file
- Output modalities
- text
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Benchmarks
- Artificial Analysis: 36.6
Inference prices
- Published price : $0.0020 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.10 / input_tokens_per_million · openRouter ↗
- Published price : $0.20 / output_tokens_per_million · openRouter ↗
meta/muse-spark-open-20261015
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers actually work in.
- Context window
- 1,048,576
- Input modalities
- text, image, video, file, audio
- Output modalities
- text
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 24.9
- OpenRouter Benchmarks: 90.152%
Inference prices
meta/muse-glimmer-30b-20260810
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use
- Context window
- 131,072
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 6.3
- OpenRouter Benchmarks: 77.069%
Inference prices
- Published price : $0.04 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.30 / input_tokens_per_million · openRouter ↗
- Published price : $1.20 / output_tokens_per_million · openRouter ↗
meta/muse-spark-1.2-20260805
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window. The model is built to support multi-agent workflows, whether as either a main agent that plan
- Context window
- 1,048,576
- Input modalities
- text, image, video, file
- Output modalities
- text
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Benchmarks
- Artificial Analysis: 39.6
Inference prices
- Published price : $0.0020 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.10 / input_tokens_per_million · openRouter ↗
- Published price : $0.20 / output_tokens_per_million · openRouter ↗
meta/muse-spark-1.1-20260709
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window. The model is designed to orchestrate multi-agent workflows, acting as either a main agent that p
- Context window
- 1,048,576
- Input modalities
- text, image, video, file
- Output modalities
- text
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Benchmarks
- Artificial Analysis: 33.7
Inference prices
- Standard · Cached input / 1M tokens : $0.15 / cache_read_tokens_per_million · meta ↗
- Standard · Input / 1M tokens : $1.25 / input_tokens_per_million · meta ↗
- Standard · Output / 1M tokens : $4.25 / output_tokens_per_million · meta ↗
meta-llama/llama-3.3-70b-instruct
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 is optimized for multilingual dialogue use cases and outperforms many of the available open
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 7.7
- Open LLM Leaderboard v2: 44.847%
- Open Persian LLM Leaderboard: 71.4%
- OpenRouter Benchmarks: 49.952%
Inference prices
- Published price : $0.23 / input_tokens_per_million · deepInfra ↗
- Published price : $0.40 / output_tokens_per_million · deepInfra ↗
meta-llama/llama-4-maverick-17b-128e-instruct
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produc
- Context window
- 524,288
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 9.3
- LiveBench: 52.398%
- LLM Stats · GitHub archive: 0.776
- LMArena: 1,287.261
- OpenCompass LLM: 79.6%
- OpenRouter Benchmarks: 41.441%
Inference prices
- Published price : $0.17 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.35 / input_tokens_per_million · openRouter ↗
- Published price : $1.00 / output_tokens_per_million · openRouter ↗
meta-llama/llama-3.1-8b-instruct
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...
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 6.9
- Open LLM Leaderboard v2: 23.764%
- OpenRouter Benchmarks: 29.121%
Inference prices
- Published price : $0.02 / input_tokens_per_million · openRouter ↗
- Published price : $0.04 / output_tokens_per_million · openRouter ↗
meta-llama/llama-4-scout-17b-16e-instruct
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. De
- Context window
- 1,310,720
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 6.5
- BFCL: 28.13%
- LLM Stats · GitHub archive: 0.678
- LMArena: 1,279.207
Inference prices
- Published price : $0.10 / input_tokens_per_million · deepInfra ↗
- Published price : $0.30 / output_tokens_per_million · deepInfra ↗
awsBedrock/meta.llama3-70b-instruct-v1:0
- Input modalities
- text
- Output modalities
- text
Benchmarks
awsBedrock/meta.llama3-8b-instruct-v1:0
- Input modalities
- text
- Output modalities
- text
Benchmarks
meta-llama/llama-3.2-3b-instruct
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including Engl
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Benchmarks
- Artificial Analysis: 5.7
- LMArena: 1,109.541
- Open LLM Leaderboard v2: 24.205%
- OpenRouter Benchmarks: 28.62%
Inference prices
- Published price : $0.02 / input_tokens_per_million · deepInfra ↗
- Published price : $0.02 / output_tokens_per_million · deepInfra ↗
meta-llama/llama-3.2-1b-instruct
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong
- Context window
- 60,000
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Artificial Analysis: 4.8
- LMArena: 1,054.641
- Open LLM Leaderboard v2: 14.443%
- Open Persian LLM Leaderboard: 28.28%
Inference prices
- Published price : $0.01 / input_tokens_per_million · deepInfra ↗
- Published price : $0.01 / output_tokens_per_million · deepInfra ↗
vertexAI/publishers/meta/models/codellama-7b-hf@codellama-13b-hf
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-meta/CodeLlama-13b-hf@1
# **Code Llama** Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 13B version in the Hugging Face Transformers format. This model is designed for general c
azureFoundry/azureml-meta/CodeLlama-13b-hf@10
# **Code Llama** Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 13B version in the Hugging Face Transformers format. This model is designed for general c
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-meta/CodeLlama-13b-hf@11
# **Code Llama** Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 13B version in the Hugging Face Transformers format. This model is designed for general c
- Input modalities
- text
- Output modalities
- text