Ling 3.0 Flash
Ling 3.0 Flash is a 124B-parameter Mixture-of-Experts model developed by inclusionAI. It is designed for token efficiency and production-scale agentic inference, supporting both reasoning and tool-calling capabilities.
Ling 3.0 Flash specs and pricing
- Provider: inclusionAI
- Released: July 23, 2026
- Context window: 262K tokens
- Max output: 33K tokens
- Input: text
- Output: text
- Price: $0.021 input / $0.063 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Ling 3.0 Flash is good at
- High-volume text processing tasks
- Complex reasoning workflows
- Building scalable AI agents
To-dos to try with Ling 3.0 Flash
- Analyze a long technical document and extract key action items
- Use tool-calling to query a database and summarize the results
- Execute a multi-step reasoning task based on provided text inputs
FAQ
- What is the primary design focus of Ling 3.0 Flash? The model is specifically designed for token efficiency and production-scale agentic inference.
- Does this model support reasoning and tool-calling? Yes, Ling 3.0 Flash includes both reasoning and tool-calling capabilities.
- How much does Ling 3.0 Flash cost? Ling 3.0 Flash costs $0.021 per million input tokens and $0.063 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.07 credits ($1 = 100 credits).
- What is the context window of Ling 3.0 Flash? Ling 3.0 Flash can read up to 262K tokens at once and write up to 33K tokens in one reply.
- Can I use Ling 3.0 Flash without coding? Yes. In todo.is you pick Ling 3.0 Flash as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.