Ling-2.6-1T
inclusionAI · released Apr 29, 2026 · inclusionAI/Ling-2.6-1T
- Type
- Open weightsMIT License
- Params
- 1T
- Context
- 262K
about 197K words of context
Our take
Written Aug 3, 2026Ling-2.6-1T is a trillion-parameter text model from inclusionAI released in April 2026 with a permissive MIT licence. It handles up to 262,144 tokens in a single request and is available as a download, though no quality benchmarks have been measured yet.
Pick this for research or commercial projects that need a very large downloadable model with minimal licensing restrictions, or for long-document tasks up to 262,144 tokens. Use it if you want a low-cost entry point among trillion-parameter models. Skip it if you need measured quality scores to compare against alternatives, if you need to know the active parameter count for cost planning, or if you need guaranteed throughput on every tier.
The case for it
- Permissive MIT licence allows commercial use, modification and redistribution.
- Over one trillion parameters in downloadable form.
- Handles up to 262,144 tokens in a single request, suitable for document-scale tasks.
- Entry tier is among the cheaper options in its parameter class.
The case against it
- No measured quality benchmarks in our data — no Elo, MMLU or other scores to judge performance.
- Active parameter count is undisclosed, so true per-token inference cost is unclear.
- Throughput is unverified for two of the three tracked offers.
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 Ling-2.6-1T — 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.
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.
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 3 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
- $0.075 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.075 / $0.63 | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.075 / $0.63 | 262K | 33 tok/s | No | No | Confirmed |
| Novita AI | $0.30 / $2.50 | 262K | not measured | Unknown | Unknown | Unknown |
Novita AIAcross the 3 listings we hold: 1 say they do not train on prompts, 0 say they do and 2 do not say. 1 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 | ✓ | ✓ | ✓ |
| Novita AI | ✓ | ✓ | ✓ |
| Novita AI |
Tool calling: 2 of 3 listings say yes, 1 publishes no parameter list. JSON output: 2 of 3 listings say yes, 1 publishes no parameter list. Strict schema: 2 of 3 listings say yes, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 35h 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 3 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 3 listings do not say whether they train on prompts.
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
- Modality record
- text->text
- Catalogue slug
- inclusionai-ling-2-6-1t