Novita AI (Ling 3.0 Flash Sante)

Overview

Ling 3.0 Flash Sante is a health and medicine-enhanced MoE model from InclusionAI with 124B total parameters and 5.1B activated per token. Optimized for medical knowledge reasoning, clinical safety, and evidence-based retrieval. Supports function calling with a 256K token context window — served via Novita AI serverless inference. This circuit provides an OpenAI-compatible chat completion endpoint backed by the inclusionai/ling-3.0-flash-sante model.

Inputs

1. Messages (messages)

• Description: A list of messages comprising the conversation so far.
• Type: array
• Required: Yes

2. Max Tokens (max_tokens)

• Description: The maximum number of tokens to generate in the completion. Ling 3.0 Flash Sante supports up to 32768.
• Type: number
• Default Value: 32768
• Required: No

3. Temperature (temperature)

• Description: Sampling temperature, controls randomness. Range [0.0, 2.0]. Lower values are more deterministic.
• Type: number
• Default Value: 1
• Required: No

4. Top-p (top_p)

• Description: Nucleus sampling. Range [0.01, 1.0]. Recommended to use either this or temperature, not both.
• Type: number
• Default Value: 0.95
• Required: No

5. Tools (tools)

• Description: A list of tools the model may call. Supports function-type tools.
• Type: array
• Default Value: []
• Required: No

6. Tool Choice (tool_choice)

• Description: Controls how the model selects a tool. auto or none.
• Type: string
• Default Value: auto
• Required: No

Outputs

1. Chat Completion Output (chat_completion_output)

• Description: The generated chat completion text — the model's final answer.
• Value: Accumulated from choices[0].delta.content stream chunks.

2. Reasoning Output (reasoning_output)

• Description: The chain-of-thought reasoning content — the model's thinking process, separate from the final answer.
• Value: Accumulated from choices[0].delta.reasoning_content stream chunks.

3. Chat Completion Tool Calls (chat_completion_tool_calls)

• Description: Tool calls made by the model (if any).
• Value: Accumulated from choices[0].delta.tool_calls stream chunks.

Try It

You can try this circuit directly in the Playground — no setup required.

Notes

1. Text-Only Input: Ling 3.0 Flash Sante does not support image, video, or audio input — text only.
2. Health/Medicine-Enhanced: Optimized for medical knowledge reasoning and clinical safety. Outputs are informational and not a substitute for professional medical advice.
3. MoE Architecture: 124B total parameters with 5.1B active per token — efficient inference despite large capacity.
4. Reasoning Always On: Reasoning is always on for Ling 3.0 Flash Sante and cannot be disabled.
5. Function Calling: Supports function calling via the tools and tool_choice inputs.
6. Context & Output: 256K context window, 32K max output tokens.

Enjoy .....!