Clarifai
OpenRouter lists Qwen3 Coder 30B A3B Instruct as a 30.5-billion-parameter Mixture-of-Experts coding model with 128 experts and eight active per forward pass. The supplied excerpt says it targets advanced code generation, repository-scale understanding, and agentic tool use, including function calls, browser use, and st The model supports a native 256K-token context, with Yarn extension up to one million tokens, and works with OpenAI-compatible tool-use formats without thinking mode. OpenRouter lists a 262K context and released the model on July 31, 2025; its listed price is $0.07 per million input tokens and $0.27 per million output