Primary use stated or inferred cautiously from official documentation.
Inkling 2 Mini
Thinking Machines Lab multimodal model released on November 20. Its 26.4 billion parameters reuse the middle layers three times per token. The 3.4 billion physically active parameters correspond to about 5.4 billion in effective computation. It accepts text and images and generates text.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | thinkingmachines/Inkling-2-Mini |
|---|---|
| Model type | Multimodal · Code · Text and reasoning |
| Access model | Open weights |
| License | Apache 2.0 |
| Deployment | Self-hosted |
| Release | 20 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 1M tokens |
| maximum output | Text; separate output maximum unpublished |
| Reasoning | Not published |
| Published tools | Features |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | LoRA on Tinker |
| Verified platforms | Hugging Face · Tinker · Transformers · vLLM · SGLang |
Coding with tools, visual documents and local assistants. The native mixed NVFP4/MXFP8 checkpoint occupies about 20 GB; at least 32 GB of memory is recommended.
It can enter repetitive reasoning: limit tokens and agent turns. Minimum effort does not disable all reasoning. The million-token sampling window is not the training limit: Tinker offers 64K or 256K for fine-tuning. Memory and speed depend on the runtime.
What it can do
Orientation
Coding with tools, visual documents and local assistants. The native mixed NVFP4/MXFP8 checkpoint occupies about 20 GB; at least 32 GB of memory is recommended.
Context
1M tokens · Text; separate output maximum unpublished
Tools and integration
Features
Access
Open weights and Tinker sampling
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | USD 0.15 / 1M tokens | Standard API rate |
| Cached input | 0.015 USD / 1M tokens | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 0.50 USD / 1M tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Tinker charges USD 0.15 input, USD 0.015 cached input and USD 0.50 output per million tokens. Training costs USD 0.75 at 64K or USD 1.50 at 256K; both options sample up to 1M. Quantized formats are not separate models.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
The card reports 48.2% on DeepSWE v1.1 with mini-swe-agent v2.4.6 and 74.9% on ten-option MMMU Pro Standard. These use defined protocols; they do not transfer to other checkpoints and are not Inferama tests.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| DeepSWE v1.1 | 48.2 % | mini-swe-agent v2.4.6 | View source ↗ |
| MMMU Pro Standard 10 | 74.9 % | Published score | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
thinkingmachines/Inkling-2-Mini
Version added to Inferama's verified catalog.