Ling-3.1-flash
- Family
- Ling 3.0
- Released
- 2026-09-30
- Context
- 256K
- Max output
- 32K
- Parameters
- 560B (25B activated)
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
InclusionAI is Ant Group's artificial general intelligence research lab, responsible for developing the Ling series of l
Cheapest of 2 routes · OpenRouter
About
Ling-3.1-flash is InclusionAI's (Ant Group 蚂蚁百灵 / Ant Ling) hybrid reasoning mixture-of-experts Flash model announced 2026-09-30. Authoritative Chinese IT Home coverage: ~560B total parameters with ~25B activated per token; designed context window up to 1M tokens; two-week free trial capped at 256K context, with paid 1M context and planned open-source weights after the trial. TechNode English summary of the same launch positions it for agent tasks, search, office software, and specialist applications.
Providers(2)
Compare all 2Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | Free | Free | Serverless |
| Vercel AI Gateway | Free | Free | Serverless |
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
inclusionai/ling-3.1-flashInclusionAI is Ant Group's artificial general intelligence research lab, responsible for developing the Ling series of l
Cheapest of 2 routes · OpenRouter