All models
Inclusionai
Ling 3.0 Tiny fastruns locally
inclusionai/ling-3-0-tiny
Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...
Input / 1M
$0.015
USD per million tokens
Output / 1M
$0.045
USD per million tokens
Est. cost / token
$0.000000022
$0.022 per 1M, 3:1 mix
Context window
262K
max output 250K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 5.1 GB |
| Q3_K_M | fair | 5.7 GB |
| Q4_K_Mrecommended | good | 6.7 GB |
| Q5_K_M | very good | 7.6 GB |
| Q6_K | excellent | 8.5 GB |
| Q8_0 | near-lossless | 10.5 GB |
| F16 | lossless | 18.3 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 07:48 | $0.015 | $0.045 | $0.003 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.015
- Output
- $0.045
- Cached input
- $0.003
- Blended (3:1)
- $0.022
Details
- Company
- Inclusionai
- Version
- 3
- Family
- Ling
- Released
- 2026-08-06
- Parameters
- 7.9B
- Max output
- 250K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 5 min ago