Ling-3.1-flash
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Open weights
Prices
1 offering · prices as listedLing-3.1-flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥2.00 | ¥0.40 | ¥6.00 |
Prices from Ant Ling: model pricing (opens in a new tab) (checked Nov 4, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Licence
- mit
- Family
- ling-flash
- Model ID
Not stated on Ant Group’s pages: max input, reasoning efforts, max thinking budget, structured output, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: inclusionAI/Ling-3.1-flash- Parameters 572.1B
- Active 25B · 512 experts, 8 per token
- Native precision FP8
- Layers 72
- KV cache per token 81 KB
- Config positions 256K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 297.9 GB (weights 283.1 + KV cache 0.6 + overhead 14.2)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| FP8 (native)maker’s file | 534.4 GB | ≈ 561.7 | ✕Doesn’t fit | — |
| Q6_K | 437.6 GB | ≈ 460.1 | ✕Doesn’t fit | — |
| Q5_K_M | 379.0 GB | ≈ 398.6 | ✕Doesn’t fit | — |
| Q5_0 | 366.3 GB | ≈ 385.3 | ✕Doesn’t fit | — |
| Q4_K_M | 323.7 GB | ≈ 340.5 | ✕Doesn’t fit | — |
| Q4_0 | 299.7 GB | ≈ 315.3 | ✕Doesn’t fit | — |
| IQ4_XS | 283.1 GB | ≈ 297.9 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 260.4 GB | ≈ 274.1 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 203.8 GB | ≈ 214.6 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 199.8 GB | ≈ 210.4 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 137.2 GB | ≈ 144.7 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed GPU; unified memory Apple M5 Ultra (80-core GPU) · 512 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
News
All news →- Oct 16, 2026Pricing Ant Group cuts Ling-3.1-flash cache read prices by 20% Ling-3.1-flash on Ant Ling API (CNY): cache read ¥0.125 → ¥0.10 per 1M tokens.
- Oct 15, 2026Pricing Ant Group raises Ling-3.1-flash and Ling-3.0-flash prices Ling-3.1-flash on Ant Ling API (CNY): input ¥0.00 → ¥0.50, output ¥0.00 → ¥1.50, cache read ¥0.00 → ¥0.125 per 1M tokens. Ling-3.0-flash on Ant Ling API (CNY): input ¥0.125 → ¥0.14, output ¥0.375 → ¥0.42, cache read ¥0.025 → ¥0.028 per 1M tokens.
Price history
Ant Ling API, China · standard rate · as listedInput per 1M tokens
| From | Price |
|---|---|
| Oct 9, 2026 | Free |
| Oct 15, 2026 | ¥0.50 |
| Oct 28, 2026 | ¥2.00 |
Output per 1M tokens
| From | Price |
|---|---|
| Oct 9, 2026 | Free |
| Oct 15, 2026 | ¥1.50 |
| Oct 28, 2026 | ¥6.00 |
Changes
All changes →- Context window 256K → 1M
- Cache read price cut 20% ¥0.125 → ¥0.10 / 1M tokens · Ant Ling API, China
- Cache read price raised Free → ¥0.125 / 1M tokens · Ant Ling API, China
- Output price raised Free → ¥1.50 / 1M tokens · Ant Ling API, China
- Input price raised Free → ¥0.50 / 1M tokens · Ant Ling API, China
- New language model
Sources
- Ant Ling: model pricing (opens in a new tab) developer.ant-ling.com · checked Nov 4, 2026
- Ling (opens in a new tab) developer.ant-ling.com · checked Nov 4, 2026
- models.dev: inclusionai/ling-3.1-flash (community data, MIT) (opens in a new tab) github.com · checked Oct 9, 2026
- inclusionAI/Ling-3.1-flash model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- inclusionAI/Ling-3.1-flash model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- inclusionAI/Ling-3.1-flash config.json (opens in a new tab) huggingface.co · checked Nov 5, 2026
- inclusionAI/Ling-3.1-flash files (opens in a new tab) huggingface.co · checked Oct 30, 2026
- inclusionAI/Ling-3.1-flash README.md (opens in a new tab) huggingface.co · checked Nov 5, 2026
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Ant Group · China · developer.ant-ling.com
Related models
Snapshots, the same family and other models from this provider