Identity
- Status
- active
- Developer ID
thinkingmachines/Inkling- Released
- Jul 15, 2026
- Version
- Inkling
- License
- apache-2.0
Thinking Machines LabInkling
Inkling is Thinking Machines Lab's open-weight multimodal mixture-of-experts model with 975B total parameters, 41B active parameters, native text, image, audio, and video input, and a 1M-token context window.
- Context
- 1,048,576 tokens
- Inputs
- Text, Image, Video, Audio
- Outputs
- Text
- Released
- Jul 15, 2026
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.95 | $4.05 | $0.16 | — | Sep 3, 2026 | Provider-reported |
 OpenrouterAvailable | $1.00 | $4.05 | $0.17 | — | Sep 3, 2026 | Provider-reported |
Benchmarks
All benchmark results →| ARC-AGI-1verified-v1-b2e2a31b3d53 | 79.50 | — | — | Inklingunknown | Original sourcewinner eligible | Third-party benchmark |
| ARC-AGI-2verified-v2-326661568d5f | 36.53 | — | — | Inklingunknown | Original sourcewinner eligible | Third-party benchmark |
| LMArena Agent Arenaagent-2026-08-31-011508720696 | -7.02 | — | 39,537 | Inkling; 95% CI [-8.08412500, -5.94789916]; sessions 39537; observations 1486696; rank 47unknown | Original sourcewinner eligible | Third-party benchmark |
| LMArena Text Arenatext-2026-09-01-011508720696 | 1,438.25 | — | 21,973 | inkling; 95% CI [1433.11517161, 1443.38005000]; votes 21973; rank 67unknown | Original sourcewinner eligible | Third-party benchmark |
| ToneBench2026-08-28-10-task-cd9819ab6e4d | 79.41 | 5,785 | 50 | Inklingaverage per case | Original sourcewinner eligible | Third-party benchmark |
| ToneBench2026-08-28-10-task-cd9819ab6e4d | 78.74 | 5,282 | 50 | Inkling (high)average per case | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Context
- 1,048,576 tokens
- Maximum output
- Unknown
- Total parameters
- 975,000,000,000
- Active parameters
- 41,000,000,000
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image, Video, Audio
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- Yes
- Tool calling
- Yes
- Capabilities
- agents, chat, coding, generation, reasoning, tools, vision
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesinkling, thinkingmachines/Inkling, Thinking Machines Inkling
Explicit Unknowns
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
thinkingmachines/Inkling developer model repositoryThinking Machines Lab · observed Sep 3, 2026thinkingmachines/Inkling README.md at 828496eeae4cThinking Machines Lab · observed Sep 3, 2026Inkling: Our Open-Weights ModelThinking Machines Lab · observed Sep 3, 2026thinkingmachines/Inkling config.json at 828496eeae4cThinking Machines Lab · observed Sep 3, 2026thinkingmachines/Inkling immutable Hub API metadataThinking Machines Lab · observed Sep 3, 2026Inkling Model CardThinking Machines Lab · observed Sep 3, 2026thinkingmachines/Inkling tokenizer_config.json at 828496eeae4cThinking Machines Lab · observed Sep 3, 2026Deepinfra catalogDeepinfra · observed Sep 3, 2026Fireworks Ai catalogFireworks Ai · observed Sep 3, 2026Openrouter catalogOpenrouter · observed Sep 3, 2026Together Ai catalogTogether Ai · observed Sep 3, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
InklingThinking Machines Lab | vs | cross-developer peerstext | |
InklingThinking Machines Lab | vs |  Kimi-K3Moonshot AI | cross-developer peersimage, text |
InklingThinking Machines Lab | vs | cross-developer peerstext | |
InklingThinking Machines Lab | vs | Seed 2.0 LiteByteDance Seed | cross-developer peersaudio, image, text, video |
InklingThinking Machines Lab | vs |  Muse Spark 1.1Meta | cross-developer peersaudio, image, text, video |
InklingThinking Machines Lab | vs |  Nova 2 LiteAmazon | cross-developer peersimage, text, video |
InklingThinking Machines Lab | vs |  MiniMax-M3MiniMax | cross-developer peersimage, text |
InklingThinking Machines Lab | vs |  VibeVoice-ASR-Streaming-1.5BMicrosoft | cross-developer peersaudio, text |
InklingThinking Machines Lab | vs |  DeepSeek-V4-Pro-BaseDeepSeek | cross-developer peerstext |
InklingThinking Machines Lab | vs | MiniMax-Music3MiniMax | cross-developer peersaudio |
InklingThinking Machines Lab | vs |  stable-audio-3-mediumStability AI | cross-developer peersaudio |
InklingThinking Machines Lab | vs |  Hunyuan3D-2.1Tencent | cross-developer peersvideo |
Questions
Inkling FAQs
What is Inkling?+
Inkling is Thinking Machines Lab's open-weight multimodal mixture-of-experts model with 975B total parameters, 41B active parameters, native text, image, audio, and video input, and a 1M-token context window. It is developed by Thinking Machines Lab and its current sourced lifecycle status is active.
What inputs and outputs does Inkling support?+
Inkling's current record lists Text, Image, Video, and Audio as input and Text as output.
How much context does Inkling support?+
The current record lists a 1,048,576-token context window and does not report a maximum output length.
Is Inkling available through an API?+
Inkling is marked as API-available. The directly sourced provider records currently include Deepinfra, Fireworks Ai, Openrouter, and Together Ai.
How large is Inkling?+
The current record lists 975,000,000,000 total parameters and 41,000,000,000 active parameters. Its architecture is InklingForConditionalGeneration.
What capabilities and tasks does Inkling support?+
Inkling's recorded capabilities are agents, chat, coding, generation, reasoning, tools, and vision. Its supported tasks are audio, coding, image, reasoning, text, and video.
How much does Inkling cost through an API?+
The lowest directly sourced prices currently attached to Inkling are $0.95 per million input tokens through Deepinfra and $4.05 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
Can Inkling be self-hosted?+
Inkling is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Inkling have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are inkling, thinkingmachines/Inkling, and Thinking Machines Inkling.
Which models can Inkling be compared with?+
The current compatible peer set includes NVIDIA Nemotron 3.5 Lightning 30B-A3B, Kimi-K3, NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16, Seed 2.0 Lite, and Muse Spark 1.1. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →