LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
in

Ling 3.0 Tiny

inclusionai·inclusionai/ling-3.0-tiny·GA·Open weights·ling series
Lightweight hybrid-linear MoE reasoning model with 7.9B total and 1.3B active parameters for on-device deployment and offline agents

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Kilo GatewayGateway
$0.015 / $0.045
Blended $0.023 · 1× spread
Context
262,144
Output limit
32,768
Knowledge cutoff
—
Released / updated
2026-08-07 / 2026-08-07
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
License
MIT
Weights
Hugging Face

Ling 3.0 Tiny by inclusionai is offered by 5 providers on this page. Public prices are shown for 4 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Kilo Gateway at $0.015 / $0.045 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Median output speed is 189 tokens per second, with 1.94s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 131,072 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Strategy & Ops9.7
Output speed189 tok/s
TTFT1.94 s

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

Available at 5 providers4 with public prices

  • ProviderInput / Output
  • Kilo GatewayGateway
    $0.015 / $0.045
    Cache read $0.003Context 262,144Output limit 250,000
  • OpenRouterGateway
    $0.015 / $0.045
    Cache read $0.003Context 262,144Output limit 250,000
  • NanoGPTGateway
    inclusionai/ling-3.0-tiny:thinking
    $0.015 / $0.045
    Cache read $0.003Context 262,144Output limit 32,768
  • NanoGPTGateway
    $0.015 / $0.045
    Cache read $0.003Context 262,144Output limit 32,768
  • BailingGateway
    Ling-3.0-tiny
    — / —
    Context 131,072 ⚠Output limit 32,768hostTable.undisclosed
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kilo GatewayGateway$0.015$0.045$0.003—262,144250,000
OpenRouterGateway$0.015$0.045$0.003—262,144250,000
NanoGPT
inclusionai/ling-3.0-tiny:thinking
Gateway$0.015$0.045$0.003—262,14432,768
NanoGPTGateway$0.015$0.045$0.003—262,14432,768
Bailing
Ling-3.0-tiny
Gateway————131,072 ⚠32,768hostTable.undisclosed

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.

Reasoning control

effort = noneeffort = highToggle (on / off)effort = minimaleffort = loweffort = mediumeffort = xhigh

Your usage cost

Common scenarios
1Kilo Gateway$3.81
2OpenRouter$3.81
3NanoGPT$3.81
4NanoGPT$3.81
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.13$02026-08-102026-11-05
2026-11-05Input list —Output list —Min blended $0.023

Artificial Analysis evaluations16 items

GPQA Diamond73.4%
Humanity's Last Exam9.3%
CritPt0.0%
SciCode24.2%
Terminal-Bench 2.127.7%
Terminal-Bench 4.00.0%
τ³-Bench Banking20.8%
AutomationBench-AA0.3%
AA-Briefcase476
GDPval-AA568
GDP.pdf0.8%
AA-LCR60.3%
MLCR-AA10.0%
AA-Omniscience Index-15.9
AA-Omniscience Accuracy37.9%
AA-Omniscience Non-Hallucination13.3%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

inLing 3.2 Flash (free)same series—Inkling 2 Smallsame series—inLing 3.2 Flashsame series—inLing 3.0 Flash VLsame lab—inLing 3.1 Flashsame lab—
Data partly from models.dev (MIT)