Inkling 2 Mini
Toolsthinkingmachines/inkling-2-miniVision · 262K context · Nov 2026 · 2 upstreamsupstream上游
Inkling 2 Mini is Thinking Machines Lab's open-weights multimodal model. It is a 26.4B-parameter mixture-of-experts looped transformer with 3.4B active parameters, a 1M-token context and image input. Trained in NVFP4, it runs in about 20GB.
Needs your own keyTo use Inkling 2 Mini, add your Thinking Machines key, or a key from another provider that serves it. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 262K
- inputđầu vào输入 / 1M (list)
- $0.10
- outputđầu ra输出 / 1M (list)
- $0.40
- routestuyến路由
- 2
- speed, 24htốc độ, 24h速度,24h
- No data yetChưa có dữ liệu暂无数据
Upstreams
2- 1Thinking MachinesBYOKnot addedBilled to your key
- 2OpenRouterBYOKnot addedBilled to your key
| 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 (Highest reported score in this row) | 30.0/30.0 (Second-highest reported score in this row) | 27.0/27.0 | 12.0/124.5 |
| Third party index | |||||
| AA Index (v5.0) | 20.1 (Highest reported score in this row) | 4.4 | 6.3 | 20.1 (Highest reported score in this row) | 13.6 (Second-highest reported score in this row) |
| Vals Index (v2.2) | 46.5% (Highest reported score in this row) | – | – | – | 29.8% (Second-highest reported score in this row) |
| Coding and autoresearch | |||||
| FrontierCode v2.0stirrup v0.2.1 | 15.1% (Highest reported score in this row) | 0.0% | 1.5% | 14.9% (Second-highest reported score in this row) | 6.1% |
| DeepSWE v1.1mini-swe-agent v2.4.6 | 48.2% (Highest reported score in this row) | 0.3% | 4.4% | 42.2% (Second-highest reported score in this row) | 24.7% |
| Terminal Bench v4.0mini-swe-agent v2.4.6 | 5.6% (Highest reported score in this row) | 0.0% | 0.5% (Second-highest reported score in this row) | 5.6% (Highest reported score in this row) | 0.0% |
| Terminal Bench v2.1Inkling 2 Mini in pi v0.83.0 | 71.6% (Second-highest reported score in this row) | 43.4% | 51.7% | 73.0% (Highest reported score in this row) | 60.7% |
| SWEBench Pro v2 (Hard)mini-swe-agent v2.4.6 | 77.9% (Highest reported score in this row) | 14.2% | 44.3% | 73.8% (Second-highest reported score in this row) | 44.1% |
| SWEBench MultilingualInkling 2 Mini with bash only | 73.7% (Highest reported score in this row) | 43.0% | 66.9% | 70.0% (Second-highest reported score in this row) | 67.7% |
| SWEBench Verifiedbash only | 79.2% (Highest reported score in this row) | 46.1% | 76.0% | 77.8% (Second-highest reported score in this row) | 71.1% |
| Vibe Code Bench v1.1openhands (vals) | 77.9% (Highest reported score in this row) | – | – | 64.9% (Second-highest reported score in this row) | 3.5% |
| PMPP-Hard (AUC, 0-10h)pi v0.83.0 | 455.8 (Highest reported score in this row) | – | – | 262.5 (Second-highest reported score in this row) | – |
| Agentic search, tool use and knowledge work | |||||
| BrowseCompInkling 2 Mini with compaction | 79.0% (Highest reported score in this row) | 37.0% | 63.9% | 61.6% | 78.9% (Second-highest reported score in this row) |
| DeepSearchQAInkling 2 Mini with compaction | 85.3% (Highest reported score in this row) | 61.7% | 74.6% | 79.7% (Second-highest reported score in this row) | 77.7% |
| MCP AtlasPublic | 82.7% (Highest reported score in this row) | 54.2% | 75.5% | 77.3% (Second-highest reported score in this row) | 67.7% |
| AA-Briefcase v1.1 | 1263.0 (Second-highest reported score in this row) | 369.0 | 478.0 | 1391.0 (Highest reported score in this row) | 999.0 |
| GDPVal-AA v2.1 | 1319.0 (Second-highest reported score in this row) | 627.0 | 792.0 | 1427.0 (Highest reported score in this row) | 1162.0 |
| JobBench | 49.6% (Highest reported score in this row) | 8.2% | 16.1% | 33.4% | 36.5% (Second-highest reported score in this row) |
| AutomationBench-AA v1.0.6 | 41.8% (Second-highest reported score in this row) | 4.9% | 6.8% | 48.2% (Highest reported score in this row) | 14.8% |
| EnterpriseOps-Gym | 42.0% (Second-highest reported score in this row) | 28.4% | 34.7% | 44.2% (Highest reported score in this row) | 28.1% |
| Vals Finance Index | 50.1% (Highest reported score in this row) | – | – | – | 41.0% (Second-highest reported score in this row) |
| AA-AnalystAgent | 46.3% (Highest reported score in this row) | – | 20.0% (Second-highest reported score in this row) | – | – |
| Diligence Benchbest harness | 48.6% (Highest reported score in this row) | – | 40.9% | 46.4% (Second-highest reported score in this row) | 45.0% |
| Vision interpretation and creation | |||||
| GDP.pdf | 16.8% (Highest reported score in this row) | 6.0% | 11.8% | 16.4% (Second-highest reported score in this row) | 8.0% |
| PerceptionBench | 57.5% (Highest reported score in this row) | 40.7% | 42.8% | 52.4% (Second-highest reported score in this row) | 36.8% |
| MMMU Prostandard 10 | 74.9% (Second-highest reported score in this row) | 73.4% | 74.3% | 76.3% (Highest reported score in this row) | 72.3% |
| OmniDocBench v1.6 | 92.8% (Highest reported score in this row) | 82.5% | 90.4% | 91.5% (Second-highest reported score in this row) | 77.9% |
| ScreenSpot Prooriginal / with Python | 76.5/87.7% (Highest reported score in this row) | 5.9%/– | 75.4%/– (Second-highest reported score in this row) | 57.6/78.9% | 43.5%/– |
| Chartographyoriginal / with Python | 22.1/72.5% (Highest reported score in this row) | 12.0/11.8% | 17.4/25.1% (Second-highest reported score in this row) | 12.2/52.1% | 9.7/29.3% |
| ZeroBench (main)original / with Python | 17.0/34.0% (Highest reported score in this row) | 9.0/12.0% | 9.0/17.0% | 12.0%/– (Second-highest reported score in this row) | 11.0/12.0% |
| MuirBench | 77.5% (Second-highest reported score in this row) | 72.3% | 77.6% (Highest reported score in this row) | 65.9% | 72.7% |
| BVB | 68.4% (Second-highest reported score in this row) | 47.0% | 50.5% | 70.7% (Highest reported score in this row) | 52.1% |
| Reasoning, knowledge and epistemics | |||||
| HLE-Diamond | 15.2% (Second-highest reported score in this row) | 7.2% | 9.1% | 15.3% (Highest reported score in this row) | 8.8% |
| CritPt v2full / hard | 31.4/17.0% (Second-highest reported score in this row) | –/4.0% | –/7.0% | 10.6/4.0% | 36.9/13.5% (Highest reported score in this row) |
| Apex 2025 | 34.4% (Highest reported score in this row) | 5.2% | 4.2% | 18.8% | 22.9% (Second-highest reported score in this row) |
| ARC-AGIv1 / v2 | 84.5/49.3% (Second-highest reported score in this row) | – | – | 87.5/42.4% (Highest reported score in this row) | 22.7/1.5% |
| LongBench v2 | 66.9% (Highest reported score in this row) | 52.9% | 33.1% | 52.3% | 62.1% (Second-highest reported score in this row) |
| GraphWalks BFS256K | 69.7% (Highest reported score in this row) | – | – | 50.4% | 63.3% (Second-highest reported score in this row) |
| MRCR v28-needle 256K-512K | 46.4% (Highest reported score in this row) | – | – | 38.0% (Second-highest reported score in this row) | 5.7% |
| AA-Omniscience v1.1score | -8.6 | -48.5 | -32.2 | -6.4 (Second-highest reported score in this row) | -2.9 (Highest reported score in this row) |
| AA-Omniscience v1.1non-hallucination rate | 63.4% | 14.5% | 16.4% | 71.4% (Highest reported score in this row) | 69.5% (Second-highest reported score in this row) |
| ComplexConstraints v1.1openhands v1.45.0 | 33.4% (Second-highest reported score in this row) | 31.6% | 35.6% (Highest reported score in this row) | 30.1% | 30.1% |
| Safety and alignment | |||||
| FORTRESSadversarial public | 89.5% (Second-highest reported score in this row) | 67.8% | 90.3% (Highest reported score in this row) | 78.8% | 79.6% |
| FORTRESSbenign public | 96.4% | 97.6% (Second-highest reported score in this row) | 89.1% | 97.8% (Highest reported score in this row) | 92.7% |
| StrongREJECTnone | 97.8% | 98.1% | 99.0% (Second-highest reported score in this row) | 99.0% (Second-highest reported score in this row) | 99.4% (Highest reported score in this row) |
| Misbehavior (internal)lower is better | 9.8% (Highest reported score in this row) | 27.6% (Second-highest reported score in this row) | 46.4% | 57.7% | 52.8% |
| Covert misbehavior (internal)lower is better | 8.3% (Highest reported score in this row) | 24.3% (Second-highest reported score in this row) | 45.6% | 33.2% | 43.4% |
| Destructive actions (internal)lower is better | 10.2% (Highest reported score in this row) | 75.8% | 68.8% | 35.2% (Second-highest reported score in this row) | 65.6% |
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "thinkingmachines/inkling-2-mini",
"messages": [
{
"role": "user",
"content": "Say hi in 3 words."
}
]
}'Details
- Owner
- Thinkingmachines
- Kind
- Vision
- Released
- Nov 2026
- Context
- 262K
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
GalleryThư viện ảnh图库
Images from the vendorẢnh từ nhà phát hành图片来自厂商
- Long-horizon agentic coding and autoresearch on local hardware.
- Fast local or offline inference on a laptop, including multiple persistent agents on one machine.
- Search- and tool-heavy knowledge work, and research into monitorability of looped transformers.
Architecture and licenseKiến trúc và giấy phép架构与许可
- LicenseGiấy phép许可
- Apache-2.0 · Open weightsTrọng số mở开放权重[3],[1]
StrengthsĐiểm mạnh优势[1]
- Leads every open-weights model under 100B total parameters on agentic coding (DeepSWE v1.1 48.2%) and the Vals Index v2.2 (46.5%).
- Looped transformer: the middle layers run three times per token, adding serial reasoning without adding parameters.
- Runs natively in NVFP4 in about 20GB, small enough for a consumer laptop, and is fast for its quality.
Known limitsGiới hạn đã biết已知局限[1]
- Not the strongest small model for multi-turn chat or instructions with many constraints: 50.0% on MultiChallenge and 33.4% on ComplexConstraints v1.1.
- Trails larger models on reasoning-intensive benchmarks such as CritPt v2 and HLE-Diamond.
- Looping does not add stored knowledge, so factuality (AA-Omniscience) is in line with other same-size models; it relies on search and tools instead.
API notesGhi chú APIAPI 说明[6],[1],[4]
- First-party serving via Tinker's OpenAI-compatible /chat/completions endpoint (https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1).
- Reasoning effort is a float from 0.0 to 0.99 (chat template maps none/minimal/low/medium/high/xhigh/max).
- Image input is accepted on the inference API; audio input is not supported.
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- thinkingmachines.ai
- Model cardThẻ mô hình模型卡
- thinkingmachines.ai
- DocsTài liệu文档
- tinker-docs.thinkingmachines.ai
- Pricing pageTrang giá价格页
- tinker-docs.thinkingmachines.ai
- Previous versionPhiên bản trước上一版本
- thinkingmachines/inkling-2-small
SourcesNguồn来源
- [1]Introducing Inkling 2 Mini - Thinking Machines Labaccessedtruy cập访问于 2026-11-21
- [2]Inkling 2 Mini Model Card - Thinking Machines Labaccessedtruy cập访问于 2026-11-21
- [3]Inkling 2 Mini released weights and Apache-2.0 licenseaccessedtruy cập访问于 2026-11-21
- [4]Inkling 2 Mini model configuration (1,048,576 context, loop config)accessedtruy cập访问于 2026-11-21
- [5]Tinker Docs - Models & Pricingaccessedtruy cập访问于 2026-11-21
- [6]Tinker Docs - OpenAI API Compatible Inferenceaccessedtruy cập访问于 2026-11-21
Upstreams and pricingUpstream và giá上游与价格
Share cards3 images



Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.
Across all upstreams
Loading usage…