TMThinking Machines/ Ling
Inkling
thinkingmachines/inkling
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Model information
Released
2026-07-15
Context window
1M
Max output
1M
Model parameters
952B
Weights
Open
Modalities
Input
AudioImageText
Output
Text
Identity
- Version
- inkling
- License
- Apache-2.0
- Aliases
- Inkling
Resources
Capabilities
AttachmentsOpen weightReasoningTemperatureTool call
Official price
input $1.87/M · output $4.68/M
cache read $0.374/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Baseten | thinkingmachines/inkling | openai_chat | 1M | 1M | AttachmentsReasoningTool callStructuredTemperature | - | input $1/M · output $4.05/M | Yes | ||
| Nvidia | thinkingmachines/inkling | custom | 1M | 1M | AttachmentsReasoningTool callTemperature | - | input $0/M · output $0/M | Yes | ||
| Thinking Machines | thinkingmachines/Inkling | custom | 1M | 1M | AttachmentsReasoningTool callTemperature | - | input $1.87/M · output $4.68/M cache read $0.374/M | Yes | ||
| Venice AI | inkling | openai_chat | 1M | 1M | AttachmentsReasoningTool callStructuredTemperature | - | input $1.25/M · output $5.063/M cache read $0.213/M | Yes | ||
| Together AI | thinkingmachines/Inkling | openai_chat | 1M | 1M | AttachmentsReasoningTool callStructuredTemperature | - | input $1/M · output $4.05/M cache read $0.17/M | Yes | ||
| Vercel AI Gateway | thinkingmachines/inkling | openai_chat | 1M | 1M | AttachmentsReasoningTool callTemperature | - | input $1/M · output $4.05/M cache read $0.17/M | Yes | ||
| OpenRouter | thinkingmachines/inkling | openai_chat | 1M | 1M | AttachmentsReasoningTool callStructuredTemperature | Reasoning levels: max, high, medium, low, minimal, none, Default reasoning: high, Hugging Face: thinkingmachines/Inkling | input $1/M · output $4.05/M cache read $0.17/M | Yes | ||
| Hugging Face | thinkingmachines/Inkling | openai_chat | 1M | 1M | AttachmentsReasoningTool callStructuredTemperature | - | input $1/M · output $4.05/M | Yes | ||
| NanoGPT | thinkingmachines/inkling | openai_chat | 1M | 1M | AttachmentsTool callStructuredTemperature | - | input $1/M · output $4.05/M cache read $0.17/M | Yes | ||
| Kilo Gateway | thinkingmachines/inkling | openai_chat | 1M | 1M | AttachmentsReasoningTool callTemperature | - | input $0.95/M · output $4.05/M cache read $0.16/M | Yes | ||
| Merge Gateway | thinkingmachines/inkling | openai_chat | 1M | 1M | ReasoningTool callStructuredTemperature | - | input $1/M · output $4.05/M cache read $0.17/M | Yes |