thinkingmachines
Thinking Machines: Inkling Small (batch)
thinkingmachines/inkling-small:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
thinkingmachines/inkling-small:batch is the OpenRouter batch listing for Inkling Small, an open-weight model from Thinking Machines. Its documentation describes a multimodal mixture-of-experts transformer with 276B total and 12B active parameters, accepting text, image, and audio inputs and returning text. The catalog reports a very large context window, tool use, and configurable reasoning effort; measured benchmark results are presented separately and should not be treated as guaranteed outcomes.[1][2]
Strengths
- Accepts text, images, and audio while producing text, with modalities processed in a shared decoder space.[2]
- Released with open weights and documented deployment routes across several local inference stacks.[2]
- The catalog reports tool-calling parameters and configurable reasoning effort, enabled by default at high effort.[1]
Limitations
- Text is the only output modality; image and audio are inputs only.[1][2]
- Documented optimal input ranges constrain images to 40-4096 px per dimension and 16 kHz WAV audio ideally under two minutes.[2]
- Evidence is limited to a provider catalog and model card; validate latency, cost, modality quality, and agent behavior on target workloads.[1][2]
Where to use it
- Evaluate for assistants that combine text, image, and audio inputs into text responses.[2]
- Potentially useful for coding assistants, retrieval-augmented generation, chatbots, and tool-using agents.[1][2]
- Worth considering where open weights, fine-tuning, or deployment through supported local stacks matter.[2]
Sources
- [1] OpenRouter catalog · Thinking Machines: Inkling Small (batch)Sources checked: Nov 13, 2026
- [2] Model documentation · Thinking Machines: Inkling Small (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- thinkingmachines/inkling-small:batch
- Canonical ID
- thinkingmachines/inkling-small-20260730
- Creator
- thinkingmachines
- Added to OpenRouter
- 30.07.2026
- Context length
- 524,288
- Modality
- text+image+audio->text
- Input modalities
- text, image, audio
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.360 / out $0.960
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: optional · default high · efforts: max, high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | BB — next 30% of the cohort | — |
| Agents | BB — next 30% of the cohort | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: max, high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 12.9 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 52.9 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 23.5 | BB — next 30% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrafp8 | 524,288 | $0.360 | $0.960 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.