GPT-6 Luna
MiMo-V2.6-Flash
7.9B- input
- $0.042
- cached
- $0.0084
- output
- $0.1232
- Context
- 262Ktokens
- Released
- 2mo ago
Cost/1M tokens
Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval
- Language model
- Reasoning
- Tools
How it compares
Level
LightweightThe lab's smallest, cheapest and lowest-latency hosted line, built for high volume and simple tasks.
Lightweight models from other labs
Vs. your stack
Add the models you use to see how this one compares.
Sign inAdditional source evidence
- Source model
- inclusionai/ling-3.0-flash-sante
- Source family
- ling
- Last updated
- 2026-09-04
- Model context
- 262K
- Model output limit
- 33K
- Open weights
- No
- File attachments
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Temperature control
- Yes
Complete source record (JSON)
{
"id": "inclusionai/ling-3.0-flash-sante",
"name": "Ling 3.0 Flash Sante",
"description": "Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval",
"family": "ling",
"last_updated": "2026-09-04",
"attachment": false,
"reasoning": true,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"release_date": "2026-09-04",
"open_weights": false
}Frequently asked questions
API and pricing
Ling 3.0 Flash Sante costs $0.042 per 1M input tokens and $0.1232 per 1M output tokens. Paid providers tracked: 1.
Yes. Cached input costs $0.0084 per 1M tokens, an 80% discount off the uncached input price of $0.042 per 1M tokens.
A typical request of 10,000 input tokens and 1,000 output tokens costs $0.0005432 at the cheapest provider, Novita.
In the last day, 1 endpoint had uptime data and 1 of those ran at 99% uptime or better. Best uptime was 100.0%, by Novita.
Privacy and data
Novita is the provider offering zero data retention (ZDR eligible or 0-day retention).
Capabilities and specs
The context window is 262K tokens (262,144) and the maximum output is 33K tokens (32,768).
No. The input modalities are text only, so images, audio, video and PDFs are not supported.
Yes, tool calling (function calling) is supported.
Yes, a reasoning mode is supported, but reasoning is not always on. 1 of 1 tracked providers expose reasoning, and no provider offers an effort setting (reasoning_effort).
Quality and benchmarks
Matched on model kind, blended price and release date: Solar Mini 4 by Upstage at $0.0875 per 1M tokens, Qwen3.7 Flash by Qwen at $0.055 per 1M tokens, and Schematron V2 Turbo by Inference.net at $0.06 per 1M tokens.
Solar Mini 4Ling 3.0 Flash Sante vs Solar Mini 4Qwen3.7 FlashLing 3.0 Flash Sante vs Qwen3.7 FlashSchematron V2 TurboLing 3.0 Flash Sante vs Schematron V2 Turbo
Ling 3.0 Flash Sante is closed, so the best open-weight alternative is Kimi K3, the highest-ranked open-weight model on Arena Text at rank 19.
Versions and lineage
Both have a 262K token (262,144) context. Sante costs $0.042 input and $0.1232 output per 1M tokens, while Flash costs $0.021 input and $0.063 output per 1M tokens. Sante was released September 4, 2026 and Flash on July 23, 2026.
Licensing and access
No, Ling 3.0 Flash Sante is closed.
Basics
Made by InclusionAI and released September 4, 2026.
No. The model is closed and the listed API price is $0.042 input and $0.1232 output per 1M tokens.
Generated from Vertical Tabs data, updated November 12, 2026.
Discussion
No comments yet
Be the first to share your thoughts.