AL
Jamba 1.5 Large
AI21 Labs
Thinkingmachines model product
Inkling
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Updated Aug 12, 2026. Default version: Inkling
LLMBoard scoreN/ANot scored
CoverageN/ANot scored
Context window1MTokens
Official input price$1.87Thinking Machines API
Inkling Specifications
Technical details for the model's default version.
- Version
- Inkling
- Released
- Jul 15, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 1M
- Inputs
- text, image, audio
- Outputs
- text
- Open weights
- Yes
- License
- Unspecified
Inkling Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
No capability profile
No version of this model currently has enough benchmark coverage for a score.
Inkling Benchmark Results
Benchmark scores for the scored version.
No benchmark results
No benchmark result is linked to the scored version.
Inkling Arena Results
Preference and agent-evaluation results for the default version.
| agent bash recovery steps | overall | 20 | 0.1 | N/A | 33.2K | |
| agent tool hallucination | overall | 31 | 0.0 | N/A | 1.1M | |
| agent | overall | 37 | -0.1 | N/A | 1.2M | |
| agent task outcome explicit | overall | 42 | -0.1 | N/A | 18.2K | |
| agent steerability | overall | 44 | -0.1 | N/A | 26.9K | |
| agent praise complaint | overall | 45 | -0.2 | N/A | 7K | |
| text factuality | overall | 46 | 1452.3 | 14,043 | N/A | |
| text | overall | 55 | 1441.7 | 14,064 | N/A | |
| webdev | overall | 57 | 1406.7 | 6,079 | N/A | |
| text style control | overall | 73 | 1442.6 | 14,064 | N/A |
Inkling Runtime Performance
Provider-specific output speed and catalog latency for Inkling. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Inkling Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.87 input, $4.68 output per 1M
- Official provider
- Thinking Machines
- Lowest third-party
- From $0.95 input, $4.05 output per 1M via Kilo Gateway
- Tracked offerings
- 15
| Nvidia | thinkingmachines/inkling | global | N/A | N/A | 1M | |
| Kilo Gateway | thinkingmachines/inkling | global | $0.95 | $4.05 | 524.3K | |
| OpenRouter | thinkingmachines/inkling | global | $0.95 | $4.05 | 1M | |
| Deep Infra | thinkingmachines/Inkling | global | $0.95 | $4.05 | 524.3K | |
| Baseten | thinkingmachines/inkling | global | $1 | $4.05 | 1M | |
| NanoGPT | thinkingmachines/inkling | global | $1 | $4.05 | 1M | |
| Together AI | thinkingmachines/Inkling | global | $1 | $4.05 | 524.3K | |
| Merge Gateway | thinkingmachines/inkling | global | $1 | $4.05 | 1M | |
| Vercel AI Gateway | thinkingmachines/inkling | global | $1 | $4.05 | 256K | |
| Hugging Face | thinkingmachines/Inkling | global | $1 | $4.05 | 1M | |
| Modal | thinkingmachines/Inkling-NVFP4 | global | $1.2 | $5 | 1M | |
| Venice AI | inkling | global | $1.25 | $5.06 | 524.3K | |
| Impossibl | thinkingmachines/inkling | global | $1.87 | $4.68 | 65.5K | |
| Thinking Machines | thinkingmachines/Inkling | global | $1.87 | $4.68 | 65.5K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Inkling Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Inkling | N/A | N/A | 1M | 1M | Yes | Unspecified |
What is Inkling?
Key information about Inkling and its available data.
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Data as of 2026-08-11.
Models similar to Inkling
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AL
Jamba 1.5 Mini
AI21 Labs
AL
Qwen3.5 Flash
Alibaba
AL
Qwen3.6 Max
Alibaba
AC
QvQ 72B
Alibaba Cloud / Qwen Team
AC
QwQ 32B
Alibaba Cloud / Qwen Team
FAQ
Common questions about Inkling.
When was Inkling released?
Inkling's default version was released on Jul 15, 2026.
How much does Inkling cost?
Inkling's official API price is $1.87 per million input tokens and $4.68 per million output tokens via Thinking Machines. The lowest tracked third-party offer starts at $0.95 input and $4.05 output via Kilo Gateway.
Who created Inkling?
Inkling was created by Thinkingmachines.
What is the context window for Inkling?
The default version has a 1M token context window.
Is Inkling open weight?
Yes. The default version is marked as open weight under an unspecified license.
How many API providers offer Inkling?
15 provider offerings are linked to the default version.
What models should I compare Inkling with?
No nearby ranked alternatives are currently available.