Unified model directory
Find the right model
Search reviewed catalog entries and imported provider listings together. Select up to three to compare.
Imported capabilities, licenses and context sizes are provider-reported. A repository listing does not establish downloadable weights or commercial rights. Models without context data are excluded by a minimum-context filter.
Qwen: Qwen3.8 Max (0902)
qwen · OpenRouter
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
Qwen: Qwen3.8 Max Prime
qwen · OpenRouter
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
Qwen: Qwen3.8 Omni Flash
qwen · OpenRouter
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
Qwen/Qwen2.5-7B-Instruct
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- LLM
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3-0.6B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- LLM
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3-14B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- LLM
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3-4B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- LLM
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3-8B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- LLM
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3-Embedding-0.6B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- Embedding
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3.5-4B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- Multimodal
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3.5-9B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- Multimodal
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Qwen/Qwen3.8-27B
Qwen · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- Multimodal
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
Recursive: Flint (free)
recursive · OpenRouter
Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 262,144 · Reported
Reflection: Beam 1.0 501B A23B
reflection · OpenRouter
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,048,576 · Reported
Reka Edge
rekaai · OpenRouter
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in ima…
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 16,384 · Reported
Sakana: Fugu Max
sakana · OpenRouter
Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
Sakana: Fugu Ultra
sakana · OpenRouter
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
Sakana: Fugu Ultra v2
sakana · OpenRouter
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
Sakana: Sakana Namazu
sakana · OpenRouter
Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 262,144 · Reported
ScaleDown: Extract
scaledown · OpenRouter
Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and th…
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
ScaleDown: Summarize
scaledown · OpenRouter
Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...
- Reported capability
- LLM
- Access
- Hosted API listing
- License
- Unknown · Unverified
- Context (tokens)
- 1,000,000 · Reported
sentence-transformers/all-MiniLM-L6-v2
sentence-transformers · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- Embedding
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
sentence-transformers/all-mpnet-base-v2
sentence-transformers · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- Embedding
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
sentence-transformers · Hugging Face
Imported provider listing. Add a reviewed English description before publication.
- Reported capability
- Embedding
- Access
- Repository listing
- License
- apache-2.0 · Unverified
- Context (tokens)
- Not supplied