As recorded at collection: Ling-3.0-flash input/output at $0

This conversational AI model was developed by inclusionAI (IAI), an AI research organization under Ant Group (蚂蚁集团), to automate tasks in production environments. According to OpenRouter's notice about its free availability, input and output are each priced at $0 per 1 million tokens. A token is a unit that AI uses to process text.

Select the Ling-3.0-flash (free) entry on OpenRouter to use it right away. It accepts a context of 262,144 tokens at a time and has a maximum output of 32,768 tokens. The default context length is 256K and can be extended to 1M.

The model has 124 billion parameters in total, and uses 5.1 billion parameters to process each token. Compared with the same company's flagship model with 1 trillion parameters, it has one-eighth as many total parameters and one-twelfth as many parameters actively used, yet performs as well as or better in most benchmarks. Free availability ends on August 3, 2026.