LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3 14B

alibaba·alibaba/qwen3-14b·GA·Open weights·qwen series
Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen3 14B by alibaba is offered by 8 providers on this page. Its official list price is $0.35 per 1M input tokens and $1.40 per 1M output tokens. The lowest paid channel is NanoGPT at $0.08 / $0.24 per 1M, about 5.0× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Artificial Analysis rates it 8.2 on the Intelligence Index, with 13.8 for coding and 0.9 for agentic tasks. Against its lowest blended price of $0.12 per 1M, that is roughly 68 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 62 tokens per second, with 2.78s to the first token.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 40,960 to 131,072, 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. Its training knowledge cuts off at 2025-04.

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$0.35 / $1.40
Blended $0.61 · Cache read —
Lowest paid·NanoGPTGateway
$0.08 / $0.24
Blended $0.12 · 5× spread
Context
131,072
Output limit
8,192
Knowledge cutoff
2025-04
Released / updated
2025-04-28 / 2025-11-25
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Quality & performanceArtificial Analysis · Intelligence Index v4.3 · rep. tier Reasoning

Intelligence8.2
Value68
Coding13.8
Agentic0.9
Output speed62 tok/s
TTFT2.78 s
Value formulaIQ 8.2 ÷ min blended $0.120 = 68
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 6.7 · 63 tok/s
ReasoningIQ 8.2 · 62 tok/s

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

Available at 8 providers8 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$0.08$0.24$0.04—41,000 ⚠32,768
SiliconFlow
Qwen/Qwen3-14B
Cloud$0.07$0.28——131,000 ⚠131,000
SiliconFlow (China)
Qwen/Qwen3-14B
Cloud$0.07$0.28——131,000 ⚠131,000
OpenRouterGateway$0.12$0.24——131,07216,384
Vercel AI Gateway
alibaba/qwen-3-14b
Cloud$0.12$0.24——40,960 ⚠16,384
Alibaba (China)OfficialFirst-party$0.14$0.57——131,0728,192
Kilo GatewayGateway$0.23$0.91——40,960 ⚠16,384
AlibabaOfficialFirst-party$0.35$1.40——131,0728,192

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

Toggle (on / off)budget_tokenseffort = noneeffort = high

Your usage cost

1NanoGPT$23.20
2SiliconFlow$28.00
3SiliconFlow (China)$28.00
4OpenRouter$36.00
5Vercel AI Gateway$36.00
6Alibaba (China) · Official$57.50
Switch to NanoGPT to save $34.30/mo (60%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.40$02026-08-052026-09-242026-08-05 · Input list $0.352026-08-06 · Input list $0.352026-08-07 · Input list $0.352026-08-08 · Input list $0.352026-08-09 · Input list $0.352026-08-10 · Input list $0.352026-08-11 · Input list $0.352026-08-12 · Input list $0.352026-08-13 · Input list $0.142026-09-24 · Input list $0.352026-08-05 · Output list $1.402026-08-06 · Output list $1.402026-08-07 · Output list $1.402026-08-08 · Output list $1.402026-08-09 · Output list $1.402026-08-10 · Output list $1.402026-08-11 · Output list $1.402026-08-12 · Output list $1.402026-08-13 · Output list $0.572026-09-24 · Output list $1.402026-08-05 · Min blended $0.122026-08-06 · Min blended $0.122026-08-07 · Min blended $0.122026-08-08 · Min blended $0.122026-08-09 · Min blended $0.122026-08-10 · Min blended $0.122026-08-11 · Min blended $0.122026-08-12 · Min blended $0.122026-08-13 · Min blended $0.122026-09-24 · Min blended $0.12

Artificial Analysis evaluations14 items

GPQA Diamond60.4%
Humanity's Last Exam4.5%
MMLU-Pro77.4%
SciCode30.7%
LiveCodeBench52.3%
Terminal-Bench Hard3.8%
Terminal-Bench 2.14.9%
AIME 202555.7%
AIME76.3%
MATH-50096.1%
τ²-Bench Telecom34.5%
τ³-Bench Banking5.6%
AA-LCR0.0%
IFBench40.5%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Qwen-Image-2.1same series$0 / $0Qwen 3.8 27B Hemingwaysame series$0.25 / $1.50Qwen 3.8 27B Cybersecuritysame series$0.10 / $0.60GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flashcheaper alternative$0.15 / $0.60GPT-5 Nanocheaper alternative$0.05 / $0.40Qwen3.8 Flashcheaper alternative$0.15 / $0.47
Data partly from models.dev (MIT) · Alibaba official docs ↗