Ling-2.6-1T
inclusionAI · released Apr 29, 2026 · inclusionAI/Ling-2.6-1T
- Type
- Open weightsMIT License
- Params
- 1T
- Context
- 262K
active per word not recorded by us · about 197K words of context
Our take
Written Sep 2, 2026Ling-2.6-1T is a one-trillion-parameter text model from inclusionAI with a permissive MIT licence and a 262,144-token request limit. It is the cheapest way to access 1T-class parameters, though no quality scores exist to show what that scale delivers.
Pick this when you need open-weights access to a 1T-class model with a very long request limit, or when MIT licensing matters for commercial redistribution and modification. Use it if cost is paramount and you can tolerate slow output. Skip it if you need verified quality data, fast throughput, or certainty about how many parameters are active per word.
The case for it
- Extremely permissive MIT licence allows commercial use, modification, redistribution and sublicensing with minimal attribution.
- 262,144-token request limit, among the largest we list.
- Lowest-cost access to 1T-class parameters.
The case against it
- Zero benchmark scores in our data — chat, reasoning, coding and knowledge are all unverified.
- Very slow throughput on the cheapest tier: seven tokens per second.
- Premium tier costs four times more for identical weights with no disclosed quality or speed advantage; active parameter count is also undisclosed.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
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.
Radeon RX 7900 XT · 20 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked between 21 days and 39 days ago — each listing carries its own date.
- per 1M tokens
- $0.075 in / $0.63 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.075 / $0.63checked 39 days ago | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIDirect | $0.30 / $2.50checked 21 days ago | 262K | not measured | Unknown | Unknown | Unknown |
Novita AIAcross the 2 listings we hold: 0 say they do not train on prompts, 0 say they do and 2 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Novita AIDirect |
Tool calling: 1 of 2 listings says yes, 1 publishes no parameter list. JSON output: 1 of 2 listings says yes, 1 publishes no parameter list. Strict schema: 1 of 2 listings says yes, 1 publishes no parameter list.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 independent board has scored it, so we hold no quality figures at all.
- 1 of 2 listings publishes no parameter list, so what its API accepts is unknown to us.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 2 listings do not say whether they train on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsMIT License, 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
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- inclusionAI/Ling-2.6-1T
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- inclusionai-ling-2-6-1t