Ling 3.1 Flash
Summary
Ling 3.1 Flash is an open-weight language model from Inclusionai, released on 29 Sept 2026. It accepts text and generates text, with a 262K-token context window and up to 33K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.04 per million input tokens and $0.14 per million output tokens (OpenRouter), across 3 providers we track.
Efficient model for low-latency assistance, extraction, and routine automation
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Inclusionai |
|---|---|
| Release date | 29 Sept 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 572B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 33K tokens [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | No [models.dev] |
| Hugging Face | inclusionAI/Ling-3.1-flash [Hugging Face] |
Ling 3.1 Flash API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter inclusionai/ling-3.1-flash | $0.04 | $0.14 | $0.009 | 1M | OpenRouter, 18 Nov 2026 |
| Novita AI inclusionai/ling-3.1-flash | $0.30 | $0.90 | $0.06 | 1M | models.dev, 18 Nov 2026 |
| Vercel AI Gateway inclusionai/ling-3.1-flash | $0.30 | $0.90 | $0.06 | 262K | models.dev, 18 Nov 2026 |
Running Ling 3.1 Flash locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 347 GB | 348 GB | 350 GB |
| Q8_0 (8-bit) | 608 GB | 609 GB | 611 GB |
| FP16 / BF16 (16-bit) | 1144 GB | 1146 GB | 1148 GB |
At 4-bit with an 8K conversation, Ling 3.1 Flash needs about 348 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Ling 3.1 Flash?
Ling 3.1 Flash has a context window of 262,144 tokens (262K) and can generate up to 32,768 tokens in a single response, according to models.dev.
How much does the Ling 3.1 Flash API cost?
Ling 3.1 Flash is listed from $0.04 per million input tokens and $0.14 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.
Is Ling 3.1 Flash open source?
Ling 3.1 Flash is an open-weight model: its weights are published on Hugging Face as inclusionAI/Ling-3.1-flash under the mit license. Check the license terms before commercial use.
When was Ling 3.1 Flash released?
Inclusionai released Ling 3.1 Flash on 29 Sept 2026, according to models.dev.
Which providers offer Ling 3.1 Flash?
We track Ling 3.1 Flash on 3 providers: OpenRouter, Novita AI, Vercel AI Gateway.
How much VRAM does Ling 3.1 Flash need?
About 348 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 609 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Ternary Bonsai 2 9B | Prism ML | 16 Oct 2026 | 262K | $0.08 | $0.13 | Open |
| Nex-N2.5-Mini | NEX AGI | 8 Sept 2026 | 262K | $0.03 | $0.10 | Open |
| Nemotron 3.5 Lightning 30B | NVIDIA | 11 Aug 2026 | 262K | $0.06 | $0.16 | Open |
| LFM3-1.7B | Liquid | 6 Nov 2026 | 262K | $0.08 | $0.20 | Open |
| Nex-N2.5-Pro | NEX AGI | 8 Sept 2026 | 262K | $0.07 | $0.25 | Open |
| Granite 4.2 8B | IBM | 25 Aug 2026 | 131K | $0.06 | $0.15 | Open |
Change history
- Max output changed from 262K to 33K
- Context window changed from 1M to 262K
- Max output changed from 33K to 262K
- Context window changed from 262K to 1M
- Context window changed from 1M to 262K
- Max output changed from 262K to 33K
- Max output changed from 33K to 262K
- Structured output changed from yes to no
- Context window changed from 262K to 1M
- Parameter count changed from none to 572B
- License changed from none to mit
- Max output changed from 262K to 33K
- Context window changed from 1M to 262K
- Context window changed from 262K to 1M
- Max output changed from 33K to 262K
- OpenRouter price changed: input $0.07 → $0.04, output $0.23 → $0.14 per 1M tokens
- Max output changed from 262K to 33K
- Context window changed from 1M to 262K
- Max output changed from 33K to 262K
- Context window changed from 262K to 1M
- Context window changed from 1M to 262K
- Max output changed from 262K to 33K
- Context window changed from 262K to 1M
- Max output changed from 33K to 262K
- Max output changed from 262K to 33K
Sources
- https://openrouter.ai/inclusionai/ling-3.1-flash
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/inclusionai/ling-3.1-flash.toml
- https://huggingface.co/inclusionAI/Ling-3.1-flash
- https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/inclusionai/ling-3.1-flash.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/inclusionai/ling-3.1-flash.toml