Ling 3.0 Flash Sante
Neural Network
Ling 3.0 Flash Sante is an InclusionAI MoE model for healthcare and medical tasks, available via BotHub API.
Specifications
- Input
- text, documents
- Output
- text
- Context size
- 262 144 tokens
- Max answer length
- 32 768 tokens
- Reasoning effort
- low, medium, high
- Capabilities
- reasoning, function calling
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: '<your bothub access token>',
baseURL: 'https://openai.bothub.chat/v1'
});
// Sync - Text generation
async function main() {
const chatCompletion = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'ling-3.0-flash-sante',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'ling-3.0-flash-sante',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works Ling 3.0 Flash Sante?
Ling 3.0 Flash Sante is a specialized InclusionAI model based on Ling 3.0 Flash. It uses a mixture-of-experts architecture: out of 124 billion parameters, about 5.1 billion are activated per request, combining the knowledge of a large network with efficient computation. Its industry focus is healthcare and medicine, where precise terminology and accurate professional phrasing are essential. Via BotHub, the model is accessible without a VPN or foreign card; payment is made with Russian cards in rubles, pay-as-you-go for tokens used, no subscription required. Over 250 other models are available in the same window, and a unified OpenAI-compatible API allows switching between them without rewriting integrations. Requests are encrypted, and companies have access to contracts, invoices, electronic document management, and an admin panel with limits. Ling 3.0 Flash Sante is used for parsing and structuring medical texts, supporting reference services and chatbots, and preparing educational materials and digital health product prototypes.Frequently asked questions about Ling 3.0 Flash Sante
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
This is a text model from inclusionAI with a 262,144 token context. It is suitable for analyzing documents and long materials, writing and refactoring code, debugging, explanations, and tasks requiring sequential reasoning. It supports function calling, making it easy to integrate into agents and workflows.
The output limit is 32,768 tokens per response. This is enough for comprehensive analysis, large code modules, detailed documentation, or extensive reports on uploaded documents. If the material is longer, break the task into parts: the 262,144 token context allows keeping the entire project in the dialogue.
Yes, reasoning mode is confirmed in our data. The model breaks down tasks step-by-step before the final answer, which significantly helps with math, logic, code analysis, and parsing long documents. This approach isn't needed for simple questions, but it provides more accurate results for complex ones.
Yes, the model supports function calling and structured JSON output. You describe the tools, it selects the right one and returns arguments in a predictable format. Via the unified OpenAI-compatible BotHub API, this connects to your backend, and you can switch to another model without rewriting the integration.
According to our data, the model accepts text and documents as input: reports, contracts, specifications, articles, logs. The large context allows uploading multiple files at once and working with them in a single dialogue. If you need images, audio, or video, multimodal models are available nearby in BotHub.
The model is designed to work with multilingual texts, so it processes Russian documents and queries correctly. The best way to check quality for your task is to run a few real examples and compare the results with other models: in BotHub, this is done in one window, without a VPN or foreign card.