# Inkling 2 Mini

> Thinking Machines' small open-weights multimodal model joins the catalog. A 26.4B looped MoE with 1M context, BYOK through Tinker and OpenRouter.

- Date: 2026-11-21
- HTML: https://anyrouter.dev/blog/releases/2026-11-21-inkling-2-mini

## Models

- `thinkingmachines/inkling-2-mini` (Inkling 2 Mini) — MoE 26.4B/3.4B active, text and image in, reasoning and tool use, 1M context, $0.15 / $0.50 per 1M (Tinker list). BYOK via Tinker and OpenRouter.

## Notes

[`thinkingmachines/inkling-2-mini`](https://anyrouter.dev/model/thinkingmachines/inkling-2-mini) is Thinking Machines Lab's smallest second-generation model. It is a 26.4B-parameter mixture-of-experts transformer with 3.4B active parameters and a 1M-token context, trained and deployed natively in NVFP4. Its middle layers run three times per token, which the lab calls looping. That gives it more reasoning per token without more parameters. It leads open-weights models under 100B on agentic coding and runs in about 20GB, small enough for a laptop.

It is **BYOK-only**. Add a [Tinker](https://anyrouter.dev/dashboard/byok) or [OpenRouter](https://anyrouter.dev/dashboard/byok) key under Dashboard → BYOK; the provider bills your own account and AnyRouter charges nothing for the route. Tinker lists it at $0.15 per 1M input and $0.50 per 1M output (256K train / 1M sample wire).

```ts
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"

const anyrouter = createAnyRouter()
const { text } = await generateText({
  model: anyrouter("thinkingmachines/inkling-2-mini"),
  prompt: "Summarise what makes a looped transformer different from a normal one.",
})
console.log(text)
```

_AI SDK._

```bash
anyr claude --model "thinkingmachines/inkling-2-mini"
```

_Run it in the terminal with your coding agent._

**Inkling 2 Mini vs open-weight peers**

| Vendor benchmarks | Inkling 2 Mini | Gemma 4 31B | Muse Glimmer 30B | Qwen3.8-27B | Nemotron 3.5 Super VL 120B A12B |
| --- | --- | --- | --- | --- | --- |
| Model info |  |
| Inkling 2 Mini has 3.4B unique active parameters. The vendor's 'activated' column below counts weight activations per token (5.4B), which includes the three loop passes. |  |
| Params (B) (activated per token (incl. loops) / total) | 5.4/26.4 | **30.7/30.7** | 30.0/30.0 | 27.0/27.0 | 12.0/124.5 |
| Third party index |  |
| AA Index (v5.0) | **20.1** | 4.4 | 6.3 | **20.1** | 13.6 |
| Vals Index (v2.2) | **46.5%** | – | – | – | 29.8% |
| Coding and autoresearch |  |
| FrontierCode v2.0 (stirrup v0.2.1) | **15.1%** | 0.0% | 1.5% | 14.9% | 6.1% |
| DeepSWE v1.1 (mini-swe-agent v2.4.6) | **48.2%** | 0.3% | 4.4% | 42.2% | 24.7% |
| Terminal Bench v4.0 (mini-swe-agent v2.4.6) | **5.6%** | 0.0% | 0.5% | **5.6%** | 0.0% |
| Terminal Bench v2.1 (Inkling 2 Mini in pi v0.83.0) | 71.6% | 43.4% | 51.7% | **73.0%** | 60.7% |
| SWEBench Pro v2 (Hard) (mini-swe-agent v2.4.6) | **77.9%** | 14.2% | 44.3% | 73.8% | 44.1% |
| SWEBench Multilingual (Inkling 2 Mini with bash only) | **73.7%** | 43.0% | 66.9% | 70.0% | 67.7% |
| SWEBench Verified (bash only) | **79.2%** | 46.1% | 76.0% | 77.8% | 71.1% |
| Vibe Code Bench v1.1 (openhands (vals)) | **77.9%** | – | – | 64.9% | 3.5% |
| PMPP-Hard (AUC, 0-10h) (pi v0.83.0) | **455.8** | – | – | 262.5 | – |
| Agentic search, tool use and knowledge work |  |
| BrowseComp (Inkling 2 Mini with compaction) | **79.0%** | 37.0% | 63.9% | 61.6% | 78.9% |
| DeepSearchQA (Inkling 2 Mini with compaction) | **85.3%** | 61.7% | 74.6% | 79.7% | 77.7% |
| MCP Atlas (Public) | **82.7%** | 54.2% | 75.5% | 77.3% | 67.7% |
| AA-Briefcase v1.1 | 1263.0 | 369.0 | 478.0 | **1391.0** | 999.0 |
| GDPVal-AA v2.1 | 1319.0 | 627.0 | 792.0 | **1427.0** | 1162.0 |
| JobBench | **49.6%** | 8.2% | 16.1% | 33.4% | 36.5% |
| AutomationBench-AA v1.0.6 | 41.8% | 4.9% | 6.8% | **48.2%** | 14.8% |
| EnterpriseOps-Gym | 42.0% | 28.4% | 34.7% | **44.2%** | 28.1% |
| Vals Finance Index | **50.1%** | – | – | – | 41.0% |
| AA-AnalystAgent | **46.3%** | – | 20.0% | – | – |
| Diligence Bench (best harness) | **48.6%** | – | 40.9% | 46.4% | 45.0% |
| Vision interpretation and creation |  |
| GDP.pdf | **16.8%** | 6.0% | 11.8% | 16.4% | 8.0% |
| PerceptionBench | **57.5%** | 40.7% | 42.8% | 52.4% | 36.8% |
| MMMU Pro (standard 10) | 74.9% | 73.4% | 74.3% | **76.3%** | 72.3% |
| OmniDocBench v1.6 | **92.8%** | 82.5% | 90.4% | 91.5% | 77.9% |
| ScreenSpot Pro (original / with Python) | **76.5/87.7%** | 5.9%/– | 75.4%/– | 57.6/78.9% | 43.5%/– |
| Chartography (original / with Python) | **22.1/72.5%** | 12.0/11.8% | 17.4/25.1% | 12.2/52.1% | 9.7/29.3% |
| ZeroBench (main) (original / with Python) | **17.0/34.0%** | 9.0/12.0% | 9.0/17.0% | 12.0%/– | 11.0/12.0% |
| MuirBench | 77.5% | 72.3% | **77.6%** | 65.9% | 72.7% |
| BVB | 68.4% | 47.0% | 50.5% | **70.7%** | 52.1% |
| Reasoning, knowledge and epistemics |  |
| HLE-Diamond | 15.2% | 7.2% | 9.1% | **15.3%** | 8.8% |
| CritPt v2 (full / hard) | 31.4/17.0% | –/4.0% | –/7.0% | 10.6/4.0% | **36.9/13.5%** |
| Apex 2025 | **34.4%** | 5.2% | 4.2% | 18.8% | 22.9% |
| ARC-AGI (v1 / v2) | 84.5/49.3% | – | – | **87.5/42.4%** | 22.7/1.5% |
| LongBench v2 | **66.9%** | 52.9% | 33.1% | 52.3% | 62.1% |
| GraphWalks BFS (256K) | **69.7%** | – | – | 50.4% | 63.3% |
| MRCR v2 (8-needle 256K-512K) | **46.4%** | – | – | 38.0% | 5.7% |
| AA-Omniscience v1.1 (score) | -8.6 | -48.5 | -32.2 | -6.4 | **-2.9** |
| AA-Omniscience v1.1 (non-hallucination rate) | 63.4% | 14.5% | 16.4% | **71.4%** | 69.5% |
| ComplexConstraints v1.1 (openhands v1.45.0) | 33.4% | 31.6% | **35.6%** | 30.1% | 30.1% |
| Safety and alignment |  |
| FORTRESS (adversarial public) | 89.5% | 67.8% | **90.3%** | 78.8% | 79.6% |
| FORTRESS (benign public) | 96.4% | 97.6% | 89.1% | **97.8%** | 92.7% |
| StrongREJECT (none) | 97.8% | 98.1% | 99.0% | 99.0% | **99.4%** |
| Misbehavior (internal) (lower is better) | **9.8%** | 27.6% | 46.4% | 57.7% | 52.8% |
| Covert misbehavior (internal) (lower is better) | **8.3%** | 24.3% | 45.6% | 33.2% | 43.4% |
| Destructive actions (internal) (lower is better) | **10.2%** | 75.8% | 68.8% | 35.2% | 65.6% |

| Independent evals | Inkling 2 Mini | Gemma 4 31B | Muse Glimmer 30B | Qwen3.8-27B | Nemotron 3.5 Super VL 120B A12B |
| --- | --- | --- | --- | --- | --- |
| GPQA Diamond (Artificial Analysis) | – | 76.3% | – | – | – |
| ARC-AGI-2 (Epoch AI) | – | – | – | 42.4% | – |
| CursorBench | – | – | – | – | – |
| SciCode (Artificial Analysis, Epoch AI) | – | 41.1% | – | **46.6%** | – |
| SimpleQA (verified) | – | – | – | – | – |

_Sources: [Introducing Inkling 2 Mini (Thinking Machines Lab)](https://thinkingmachines.ai/news/inkling-2-mini/) (as of 2026-11-21); [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0). Interactive version: https://anyrouter.dev/compare/inkling-2-mini_

Playbooks: [AI SDK](https://anyrouter.dev/use-cases/ai-sdk), [OpenAI SDK](https://anyrouter.dev/use-cases/openai-sdk), [coding agents](https://anyrouter.dev/use-cases/coding-agents), [playground](https://anyrouter.dev/playground?model=thinkingmachines%2Finkling-2-mini).
