ling-3.0-tiny

Name: ling-3.0-tiny
Brand: misc
SKU: misc/ling-3.0-tiny

misc·misc/ling-3.0-tiny·GA·Closed·ling series·NEW

Ling-3.0-tiny is an efficient 7.9B parameter MoE model from inclusionAI with only 1.3B active parameters per token. Built for responsive agents, reliable instruction following and multi turn conversation, with a 256K context window, native function calling, prompt caching and switchable Thinking and Instant modes.

At a glance

Reference price$0 / $0 per 1M

Cache read — · Requesty

Lowest paidNo paid channels

1 more $0 channels

Context262,144

Output limit32,768

Capabilities

✓ Reasoning✓ Tool useStructured output? TemperatureAttachments

Modalities

Text

Knowledge cutoff—

Released / updated2026-08-05 / 2026-08-05

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence24.5

Value—

Coding26.5

Agentic16

Output speed158 tok/s

TTFT2.59 s

Cost per task$0

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 1 providers0 with public prices · 1 free

Priced only

Provider	Tier	Input	Output	Cache read	Cache write	Context	Output limit	Status
Requesty	Gateway	Free		—	—	262,144	32,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Input tokens / month

Output tokens / month

Cache hit rate

Common scenarios

This model is $0 across all listed channels (Requesty).

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokens

Price historyone sample accumulated per data sync

Input list $0Output list $0Min blended —

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-19). Each future sync adds a point, and once accumulated a line is drawn here.