Inkling Small
Thinking Machines · released Jul 27, 2026 · thinkingmachines/Inkling-Small
- Type
- Open weightsApache License 2.0
- Params
- 266B
- Context
- 524K
about 393K words of context
Our take
Written Aug 3, 2026Inkling Small is a large downloadable model from Thinking Machines that accepts text, images and audio, and can handle up to 524,288 tokens in a single request. Released in 2026 under a permissive Apache licence, it is built for long-document and multimodal workflows, though no quality benchmarks are yet available.
Pick this for extremely long documents or multimodal pipelines combining text, image and audio, or when your project requires a licence that permits commercial use and redistribution. Skip it if you need measured quality scores or the lowest per-token cost among open models.
The case for it
- 524,288-token request limit — twice the length of the other open model with a disclosed context in this input.
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution without restriction.
- Accepts text, images and audio in a single model.
- Measured at up to 189 tokens per second on one endpoint, the faster of two measured hosts.
The case against it
- No benchmark scores of any kind in our data — no measured quality to judge against peers.
- 266 billion parameters with no active-parameter count disclosed, so efficiency claims are unverified.
- Costs several times more per token than smaller open alternatives; throughput also varies sharply across endpoints.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Inkling Small — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 209.7 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 4 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.50 in / $1.20 out
- Context served
- 524K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.50 / $1.20 | 524K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8 | $0.45 / $1.20 | 524K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8 | $0.45 / $1.20 | 524K | 190 tok/s | No | No | Confirmed |
| Together AI | $0.50 / $1.20 | 524K | 139 tok/s | No | No | Confirmed |
DeepInfra
Together AIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 2 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| DeepInfrafp8 | |||
| DeepInfrafp8 | ✗ | ✗ | ✗ |
| Together AI | ✓ | ✗ | ✗ |
Tool calling: 2 of 4 listings say yes, 1 says no, 1 publishes no parameter list. JSON output: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list. Strict schema: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 3d ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No board we watch has turned up a score, so we hold no quality figures at all.
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- thinkingmachines/Inkling-Small
- Architecture
- Dense
- Modality record
- text+image+audio->text
- Catalogue slug
- thinkingmachines-inkling-small