Ling 3.0 Flash Sante
Ling-3.0-Flash-Sante is a Mixture-of-Experts (MoE) model with enhanced capabilities across health and medicine. Built on Ling-3.0-Flash, it has 124 billion total parameters and activates approximately 5.1 billion parameters per token. The model excels in medical knowledge reasoning, clinical safety, evidence-based retrieval, and long-horizon medical tasks, while retaining strong general capabilities in reasoning, coding, and agentic tasks.
- Input / output price
- $0.075 / $0.22 per 1M
- Context
- 262K tokens
- Released
- Sep 3, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Novita novita/ling-3.0-flash-sante | $0.075/M | $0.22/M |
Pricing
USD per 1M tokens on Novita, after gateway discounts.
- Input
- $0.075 per 1M
- Output
- $0.22 per 1M
- Cache read
- $0.015 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better49tokens/sacross providers
Response latency
Lower is better1.0sacross providers
Benchmarks
5 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Healthbench Professionalhuggingface.co | 54.3% | huggingface.co | Nov 15, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MedQA-USMLEhuggingface.co | 94.2% | huggingface.co | Nov 15, 2026 |
| ReDisQAhuggingface.co | 89.7% | huggingface.co | Nov 15, 2026 |
| MedMCQAhuggingface.co | 80.3% | huggingface.co | Nov 15, 2026 |
| MedXpertQA-Texthuggingface.co | 51% | huggingface.co | Nov 15, 2026 |
Apps
Use Ling 3.0 Flash Sante in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Ling 3.0 Flash Sante FAQ
Short answers, built from the data on this page.
Ling 3.0 Flash Sante is a model from InclusionAI, released on Sep 3, 2026. Ling-3.0-Flash-Sante is a Mixture-of-Experts (MoE) model with enhanced capabilities across health and medicine. Built on Ling-3.0-Flash, it has 124 billion total parameters and activates approximately 5.1 billion parameters per token. The model excels in medical knowledge reasoning, clinical safety, evidence-based retrieval, and long-horizon medical tasks, while retaining strong general capabilities in reasoning, coding, and agentic tasks.
On the Respan gateway, Ling 3.0 Flash Sante costs $0.075 per 1M input tokens and $0.22 per 1M output tokens on Novita, after gateway discounts.
Ling 3.0 Flash Sante is served by Novita.
Ling 3.0 Flash Sante accepts up to 262K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "ling-3.0-flash-sante". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Ling 3.0 Flash Sante has 5 published benchmark scores, including Healthbench Professional 54.3% and MedQA-USMLE 94.2%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.