Inkling 2 Mini: Intelligence, Performance & Price Analysis
Available providers
Model summary
Inkling 2 Mini is amongst the leading models in intelligence and reasonably priced when comparing to other open weight models of similar size. It's also quicker than average per task, however very verbose. The model supports text and image input, outputs text, and has a 1M tokens context window.
Inkling 2 Mini scores 20 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 10). When evaluating the Intelligence Index, it generated 161M tokens, which is very verbose in comparison to the median of 85.7M.
Pricing for Inkling 2 Mini is $0.15 per 1M input tokens (somewhat expensive, median: $0.14) and $0.50 per 1M output tokens (somewhat expensive, median: $0.32). On average, it costs $0.59 per task to evaluate Inkling 2 Mini on the Intelligence Index.
At 9.0 minutes per Intelligence Index task, Inkling 2 Mini is quicker than average compared with the median of 9.0 minutes for comparable models (lower is better).
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text and image |
| Output modality | Supports: text |
| Context window | 1M ~1536 A4 pages of size 12 Arial font |
| Total parameters | 26B |
| Active parameters | 5.4B Number of parameters active per token during inference |
| License | Apache 2.0 |
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 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
Agentic business operations
Agentic real-world work tasks, Elo
Product and brand videos designed in code, Elo
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 2 Mini | 20 | 26B 5.4B active at inference time | 1M | $0.0905 | 9.0 | 280 | Not available |
More from Thinking Machines
Frequently Asked Questions
Common questions about Inkling 2 Mini
Inkling 2 Mini was released on November 20, 2026.
Inkling 2 Mini was created by Thinking Machines.
Inkling 2 Mini scores 20 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 10).
Inkling 2 Mini takes 9.0 minutes per Intelligence Index task (based on the median across providers serving the model), which is quicker than average compared to other open weight models of similar size (median: 9.0 minutes; lower is better).
Inkling 2 Mini has a time to first answer token of 9.72s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight models of similar size (median: 6.91s).
Inkling 2 Mini costs $0.15 per 1M input tokens (somewhat higher than average, median: $0.14) and $0.50 per 1M output tokens (somewhat higher than average, median: $0.32), based on the median across providers serving the model.
Inkling 2 Mini costs $0.15 per 1M input tokens and $0.50 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.0905 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, Inkling 2 Mini generated 161M output tokens, which is at the higher end compared to other open weight models of similar size (median: 85.7M).
Yes, Inkling 2 Mini is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Inkling 2 Mini supports text and image input.
Inkling 2 Mini supports text output.
Yes, Inkling 2 Mini supports image input and can analyze, describe, and answer questions about images.
Yes, Inkling 2 Mini is multimodal. It can process text and image input and generate text output.
Inkling 2 Mini 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 2 Mini is open weights. The model weights are publicly available.
Inkling 2 Mini has 26B parameters (5.4B active).
Inkling 2 Mini is a Mixture of Experts (MoE) model with 26B total parameters, but only 5.4B active parameters are used during inference.
Inkling 2 Mini is released under the Apache 2.0 license. This license allows commercial use. View license
Inkling 2 Mini achieves a score of 20 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across knowledge work, coding, science, and general knowledge.
Yes, Inkling 2 Mini is available via API through 1 provider. Compare API providers
Inkling 2 Mini is available through 1 API provider. Compare providers