This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Thinking Machines has launched a newer release, Inkling 2 Small. We suggest considering it instead.
Inkling Small: Intelligence, Performance & Price Analysis
Available providers
Model summary
Inkling Small is among the least intelligent models, but reasonably priced when comparing to other open weight models of similar size. It's also notably quick per task and fairly concise. The model supports text, image, and speech input, outputs text, and has a 1M tokens context window.
Inkling Small scores 13 on the Artificial Analysis Intelligence Index, placing it at the lower end among comparable models (median: 23). When evaluating the Intelligence Index, it generated 71.6M tokens, which is fairly concise in comparison to the median of 104M.
Pricing for Inkling Small is $0.30 per 1M input tokens (moderately priced, median: $0.43) and $1.20 per 1M output tokens (moderately priced, median: $1.84). On average, it costs $0.20 per task to evaluate Inkling Small on the Intelligence Index.
At 6.2 minutes per Intelligence Index task, Inkling Small is notably quick compared with the median of 13.7 minutes for comparable models (lower is better).
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text, image, and speech |
| Output modality | Supports: text |
| Context window | 1M ~1500 A4 pages of size 12 Arial font |
| Total parameters | 266B |
| Active parameters | 12B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Capability Indexes
Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better
Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better
Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Briefcase v1.1 · Higher is better
Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Medical long context reasoning
Visual reasoning
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Token Use
Output Tokens per Intelligence Index Task
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Inkling Small | 13 | 266B 12B active at inference time | 1M | $0.22 | 6.2 | 98 |
More from Thinking Machines
Frequently Asked Questions
Common questions about Inkling Small
Inkling Small was released on July 30, 2026.
Inkling Small was created by Thinking Machines.
Inkling Small scores 13 on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight models of similar size (median: 23).
Inkling Small takes 6.2 minutes per Intelligence Index task (based on Thinking Machines's API), which is among the quickest compared to other open weight models of similar size (median: 13.7 minutes; lower is better).
Inkling Small has a time to first answer token of 23.67s (based on Thinking Machines's API), which is somewhat higher than average compared to other open weight models of similar size (median: 19.92s).
Inkling Small costs $0.30 per 1M input tokens (better than average, median: $0.43) and $1.20 per 1M output tokens (better than average, median: $1.84), based on Thinking Machines's API.
Inkling Small costs $0.30 per 1M input tokens and $1.20 per 1M output tokens (based on Thinking Machines's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.22 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, Inkling Small generated 71.6M output tokens, which is better than average compared to other open weight models of similar size (median: 104M).
Yes, Inkling Small is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Inkling Small supports text, image, and speech input.
Inkling Small supports text output.
Yes, Inkling Small supports image input and can analyze, describe, and answer questions about images.
Yes, Inkling Small is multimodal. It can process text, image, and speech input and generate text output.
Inkling Small has a context window of 1M tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Inkling Small is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Inkling Small has 266B parameters (12B active).
Inkling Small is a Mixture of Experts (MoE) model with 266B total parameters, but only 12B active parameters are used during inference.
Inkling Small is released under the Apache 2.0 license. This license allows commercial use. View license
Inkling Small achieves a score of 13 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across knowledge work, coding, science, and general knowledge.
Yes, Inkling Small is available via API through 2 providers. Compare API providers
Inkling Small is available through 2 API providers. Compare providers