Ling 3.0 Tiny
Ling 3.0 Tiny is a mixture-of-experts model developed by InclusionAI. It is built for responsive agent interactions, complex instruction following, and multi-turn conversations. The model features a large context window and supports both reasoning and tool calling capabilities.
Ling 3.0 Tiny specs and pricing
- Provider: inclusionAI
- Released: November 5, 2026
- Context window: 262K tokens
- Max output: 250K tokens
- Input: text
- Output: text
- Price: $0.015 input / $0.045 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Ling 3.0 Tiny is good at
- Building responsive AI agents
- Managing complex multi-turn conversations
- Executing tasks that require logical reasoning
To-dos to try with Ling 3.0 Tiny
- Analyze a long transcript of a meeting and summarize the key action items for each participant.
- Use tool calling to query a database and generate a structured report based on the results.
- Follow a multi-step set of instructions to draft and refine a technical document.
FAQ
- What is Ling 3.0 Tiny designed for? It is designed for responsive agent behavior, instruction following, and maintaining context during multi-turn conversations.
- Does this model support tool calling? Yes, Ling 3.0 Tiny is equipped with tool calling capabilities to assist in agent-based tasks.
- How much does Ling 3.0 Tiny cost? Ling 3.0 Tiny costs $0.015 per million input tokens and $0.045 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.05 credits ($1 = 100 credits).
- What is the context window of Ling 3.0 Tiny? Ling 3.0 Tiny can read up to 262K tokens at once and write up to 250K tokens in one reply.
- Can I use Ling 3.0 Tiny without coding? Yes. In todo.is you pick Ling 3.0 Tiny 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.