Ling-3.0-flash
inclusionAI · released Aug 2, 2026 · inclusionAI/Ling-3.0-flash
- Type
- Open weightsMIT License
- Params
- 128B
- Context
- 131K
active per word not recorded by us · about 98K words of context
Our take
Written Sep 5, 2026Ling 3.0 Flash is a large downloadable text model from inclusionAI with a permissive MIT licence and a 131,072-token request limit. It is a licensing-first pick for teams that need commercial freedom, though no quality benchmarks have been measured yet.
Pick this when you need a permissive open licence with minimal obligations, or for long-context text tasks up to 131,072 tokens. Use it for budget-conscious hosted inference, or speed-sensitive workloads where a faster tier is available at twice the base rate. Skip it if you need verified quality scores, multimodal input, or predictable throughput across providers.
The case for it
- MIT licence allows commercial use, modification and redistribution with attribution only.
- 131,072-token request limit is among the longer contexts in this parameter class.
- Wide price spread across eight offers, with a budget entry point well below the premium tiers.
The case against it
- No benchmark scores yet — chat, reasoning, coding and other capabilities are all unverified.
- Throughput varies nearly tenfold across providers, with no speed disclosed for half the offers.
- 127.5 billion total parameters with no efficiency architecture disclosed.
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.
Comfortable fit
Apple M1 Ultra (64-core GPU) · 128 GB
Room to spare. 10.6 GB spare means a 10% error in the size would not change the answer.
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 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.021 in / $0.062 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 | $0.021 / $0.062checked 4 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16Through OpenRouter | $0.021 / $0.062checked 4 hours ago | 262K33K max reply | 60 tok/s | No | No | Confirmed |
| Novita AIThrough OpenRouter | $0.021 / $0.063checked 4 hours ago | 262K33K max reply | 134 tok/s | No | No | Confirmed |
| DeepInfrafp16Direct and through OpenRouter | $0.060 / $0.18checked 4 hours ago | 131K33K max reply through OpenRouter | 60 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| DeepInfrafp4Direct and through OpenRouter | $0.060 / $0.18checked 4 hours ago | 262K236K max reply through OpenRouter | 120 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| DeepInfrabf16Through OpenRouter | $0.060 / $0.18checked 4 hours ago | 131K33K max reply | 42 tok/s | No | No | Confirmed |
| DeepInfraDirect | $0.060 / $0.18checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AIDirect | $0.075 / $0.22checked 4 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
Novita AI
DeepInfraAcross the 8 listings we hold: 5 say they do not train on prompts (2 of them only through OpenRouter), 0 say they do and 3 do not say. 5 appear in the zero-retention registry we check (2 of them only through OpenRouter); 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 AIbf16Through OpenRouter | ✓ | ✗ | ✗ |
| Novita AIThrough OpenRouter | ✓ | ✗ | ✗ |
| DeepInfrafp16Direct and through OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp4Direct and through OpenRouter | ✓ | ✗ | ✓ |
| DeepInfrabf16Through OpenRouter | ✓ | ✓ | ✗ |
| DeepInfraDirect | |||
| Novita AIDirect |
Tool calling: 6 of 8 listings say yes, 2 publish no parameter list. JSON output: 3 of 8 listings say yes, 3 say no, 2 publish no parameter list. Strict schema: 3 of 8 listings say yes, 3 say no, 2 publish no parameter list.
Models people weigh against Ling-3.0-flash
When we formed this view
Recent changes
What moved
input +33% ($0.045 → $0.060 per 1M tokens), output +80% ($0.10 → $0.18 per 1M tokens)What moved
input +50% ($0.030 → $0.045 per 1M tokens), output +43% ($0.070 → $0.100 per 1M tokens)What moved
input −60% ($0.075 → $0.030 per 1M tokens), output −68% ($0.220 → $0.070 per 1M tokens)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.
- 2 of 8 listings publish no parameter list, so what their 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.
- 3 of 8 listings do not say whether they train on prompts, and 2 answer only through OpenRouter, not for their own listing.
- 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-3.0-flash
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- inclusionai-ling-3-0-flash