Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
Context
262K
262,144 tokens
Max output
262K
262,144 tokens
Input
$0.30
per 1M tokens
Output
$1.20
per 1M tokens
Providers
11
14 listings
Intelligence
25.7
Intelligence Index
Pricing
USD per 1M tokens · listed by Thinking Machines
| Token type | Standard |
|---|---|
| Input | $0.30 |
| Output | $1.20 |
| Cache read | $0.06 |
Lowest input price across providers: $0.30.
Capabilities
ReasoningYes
On / off · Effort: low, medium, high, xhigh, max
Tool callYes
Structured outputNo
TemperatureYes
AttachmentsYes
Interleaved reasoningYes
Field: reasoning_details
Open weightsYes
ModeratedNo
Input
TextImage
Output
Text
Benchmarks
Published scores and Design Arena Elo
- Intelligence25.7#70 of 208
- Coding52.9#48 of 112
- Agentic23.5#36 of 86
- ArenaNot scored—
Rankings
Position on each OneAtlas leaderboard
Providers · 11
14 listings
Thinking Machines
NanoGPT
Vercel AI Gateway
Kilo Gateway
Eden AI
AI/ML API
Hugging Face
Deep Infra
CommandCode
LLMTR
Arcee| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AI/ML API | thinkingmachines/inkling-small | 524K | — | 262K | $0.61 | $1.52 | — | $0.12 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| Arcee | thinkingmachines/inkling-small | 262K | — | 262K | $0.50 | $1.20 | — | $0.10 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| CommandCode | thinkingmachines/inkling-small | 1M | — | 1M | $0.50 | $1.20 | — | $0.10 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| Deep Infra | thinkingmachines/Inkling-Small | 524K | — | 1.05M | $0.45 | $1.20 | — | $0.10 | — | — | — | Yes | Yes | Yes | Yes | Jul 30, 2026 |
| Eden AI | deepinfra/thinkingmachines/Inkling-Small | 524K | — | 1.05M | $0.45 | $1.20 | — | $0.10 | — | — | — | Yes | Yes | Yes | Yes | Jul 30, 2026 |
| Hugging Face | thinkingmachines/Inkling-Small | 524K | — | 1.05M | $0.50 | $1.20 | — | — | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| Kilo Gateway | thinkingmachines/inkling-small | 524K | — | 262K | $0.45 | $1.20 | — | $0.10 | — | — | — | Yes | Yes | No | Yes | Jul 30, 2026 |
| LLMTR | thinkingmachines/inkling-small | 262K | — | 262K | $0.58 | $1.44 | — | $0.12 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| NanoGPT | thinkingmachines/Inkling-Small | 524K | 524K | 33K | $0.45 | $1.20 | — | $0.10 | — | — | — | No | Yes | No | Yes | Jul 30, 2026 |
| NanoGPT | thinkingmachines/Inkling-Small:thinking | 524K | 524K | 33K | $0.45 | $1.20 | — | $0.10 | — | — | — | Yes | Yes | No | Yes | Jul 30, 2026 |
| Thinking Machines | thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4 | 262K | — | 262K | $0.30 | $1.20 | — | $0.06 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| Thinking Machines | thinkingmachines/Inkling-Small:peft:262144 | 262K | — | 262K | $0.58 | $1.44 | — | $0.12 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| Thinking Machines | thinkingmachines/Inkling-Small | 66K | — | 66K | $0.58 | $1.44 | — | $0.12 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |
| Vercel AI Gateway | thinkingmachines/inkling-small | 1M | — | 1M | $0.45 | $1.20 | — | $0.10 | — | — | — | Yes | Yes | Unknown | Yes | Jul 30, 2026 |