siliconFlow/nex-agi/DeepSeek-V3.1-Nex-N1
DeepSeek-V3.1-Nex-N1 is a large language model developed based on leading open-source models and optimized through post-training. This optimization significantly enhances its agency, leading to outstanding performance in Agent tasks and code generation and understanding, tool usa
- Maximum output
- 163,840
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
siliconFlow/nex-agi/Nex-N2-Pro
Nex-N2 is a family of thinking models with Agentic Thinking. They adaptively decide when and how deeply to reason, unifying agent cognition across coding, search, and tool use into a single coherent paradigm. Key Claims - SOTA among open models on SWE-Verified, SWE-Pro, Terminal
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
qwen/qwen3-reranker-0.6b
Qwen3 Reranker 0.6B is the smallest text reranking model from Alibaba Cloud in the Qwen3 Reranker series. Built on the Qwen3 architecture, it evaluates query-document pairs to produce relevance scores for retrieval and RAG pipelines. Supports 100+ languages with instruction-aware
- Context window
- 32,768
- Input modalities
- text
- Output modalities
- rerank
- Capabilities
- rerank
Inference prices
- Input tokens (per 1M) : $0.01 / input_tokens_per_million · siliconFlow ↗
qwen/qwen3-reranker-8b
Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG pipelines. Supports 100+ languages and programming languages, with instruction-aware rerankin
- Context window
- 40,960
- Input modalities
- text
- Output modalities
- rerank
- Capabilities
- rerank
Inference prices
- Input tokens (per 1M) : $0.04 / input_tokens_per_million · siliconFlow ↗
huggingface/Qwen/Qwen2.5-14B-Instruct
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Open Ko-LLM Leaderboard: 60.65%
- Open LLM Leaderboard v2: 41.309%
huggingface/Qwen/Qwen2.5-32B-Instruct
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Open LLM Leaderboard v2: 46.597%
- Open Persian LLM Leaderboard: 38.19%
siliconFlow/Qwen/Qwen2.5-72B-Instruct-128K
Qwen2.5-72B-Instruct is one of the latest large language models series released by Alibaba Cloud. This 72B model demonstrates significant improvements in areas such as coding and mathematics. It supports a context length of up to 128K tokens. The model also offers multilingual su
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
qwen/qwen-2.5-7b-instruct
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
- Context window
- 32,768
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Open Ko-LLM Leaderboard: 70.178%
- Open LLM Leaderboard v2: 35.2%
- Open Persian LLM Leaderboard: 69.13%
Inference prices
- Input tokens (per 1M) : $0.05 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $0.05 / output_tokens_per_million · siliconFlow ↗
huggingface/Qwen/Qwen2.5-VL-32B-Instruct
- Capabilities
- multimodal, visionInput
Benchmarks
- LLM Stats · GitHub archive: 0.696
- LMArena: 1,152.03
- MMBench: 98.9%
qwen/qwen2.5-vl-72b-instruct
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
- Context window
- 128,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, structuredOutputs, visionInput
Benchmarks
- LLM Stats · GitHub archive: 0.937
- LMArena: 1,107.269
- MMBench: 100%
- OpenRouter Benchmarks: 44.276%
huggingface/Qwen/Qwen2.5-VL-7B-Instruct
- Capabilities
- multimodal, visionInput
Benchmarks
- LLM Stats · GitHub archive: 0.914
- MMBench: 87.1%
qwen/qwen3-30b-a3b-04-28
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex
- Context window
- 40,960
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 7.6
- LLM Stats · GitHub archive: 0.804
- OpenRouter Benchmarks: 47%
qwen/qwen3.5-27b-20260224
The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.
- Context window
- 262,144
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 22.9
Inference prices
- Input tokens (per 1M) : $0.25 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $2.00 / output_tokens_per_million · siliconFlow ↗
qwen/qwen3-coder-30b-a3b-instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native contex
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
Inference prices
- Input tokens (per 1M) : $0.07 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $0.28 / output_tokens_per_million · siliconFlow ↗
qwen/qwen3-coder-480b-a35b-07-25
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameter
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 11.9
- OpenRouter Benchmarks: 40.889%
Inference prices
- Input tokens (per 1M) : $0.25 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $1.00 / output_tokens_per_million · siliconFlow ↗
huggingface/Qwen/Qwen3-Embedding-0.6B
- Capabilities
- embeddings
Benchmarks
Inference prices
- Input tokens (per 1M) : $0.01 / input_tokens_per_million · siliconFlow ↗
qwen/qwen3-embedding-4b
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model
- Context window
- 32,768
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
Benchmarks
Inference prices
- Input tokens (per 1M) : $0.02 / input_tokens_per_million · siliconFlow ↗
qwen/qwen3-embedding-8b
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model
- Context window
- 40,960
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
Benchmarks
Inference prices
- Input tokens (per 1M) : $0.04 / input_tokens_per_million · siliconFlow ↗