INInclusionai/ Ling
Ling-2.6-flash
inclusionai/ling-2.6-flash
Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....
Model information
Released
2026-04-21
Context window
262K
Max output
33K
Model parameters
107B
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- ling-2.6-flash
- License
- MIT
Resources
Capabilities
StructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | inclusionai/ling-2.6-flash | openai_chat | 262K | 33K | Tool callStructuredTemperature | - | input $0.01/M · output $0.03/M cache read $0.002/M | Yes | ||
| NanoGPT | inclusionai/ling-2.6-flash | openai_chat | 262K | 33K | Tool callStructured | - | input $0.1/M · output $0.3/M cache read $0.02/M | Yes | ||
| Kilo Gateway | inclusionai/ling-2.6-flash | openai_chat | 262K | 33K | Tool callStructuredTemperature | - | input $0.1/M · output $0.3/M cache read $0.02/M | Yes | ||
| NovitaAI | inclusionai/ling-2.6-flash | openai_chat | 262K | 33K | Tool callStructuredTemperature | - | input $0.1/M · output $0.3/M cache read $0.02/M | Yes | ||
| Inclusion AI | ling-2.6-flash | custom | 262K | 33K | - | - | - | Yes |