← LLM Directory
Alibaba Cloud (Qwen)

Alibaba Cloud (Qwen)

LLM Provider

Alibaba's Qwen model family. Open-weight and API-available. Strong multilingual support.

Flagship1 model

ModelInput / 1MOutput / 1MContext
Qwen3 235B-A22B
MoE model. 235B total, 22B active. Top open-source coding model.
$0.800$1.60128K

Mid-range2 models

ModelInput / 1MOutput / 1MContext
Qwen3 32B
Dense 32B model. Great for local deployment.
$0.300$0.600128K
Qwen3.6-27B
Dense 27B model for coding, reasoning, and agent workloads.
$0.200$0.400131K

Coding1 model

ModelInput / 1MOutput / 1MContext
Qwen3 Coder 480B-A35B
MoE coding specialist. 480B total, 35B active params.
$0.500$1.00256K

Multimodal1 model

ModelInput / 1MOutput / 1MContext
Qwen2.5-VL 72B
Vision-language model. Image and video understanding.
$0.500$1.00131K

Budget3 models

ModelInput / 1MOutput / 1MContext
Qwen3 14B
Compact model. Runs on consumer GPUs.
$0.150$0.300128K
Qwen3 4B
Small model for edge devices and mobile.
$0.050$0.10033K
Qwen3 1.7B
Ultra-small model. Good for classification and extraction.
$0.010$0.02033K

Legacy1 model

ModelInput / 1MOutput / 1MContext
Qwen2.5 72B
Previous-generation 72B. Still strong for many tasks.
$0.400$0.800131K

Agentic1 model

ModelInput / 1MOutput / 1MContext
Qwen-AgentWorld-35B-A3B
Qwen's language world model that simulates agent environments across MCP, search, terminal, SWE, Android, web, and OS in a single 35B MoE (3B active). Apache 2.0.
$0.300$1.20262K

Other Providers