LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen/Qwen3-VL-30B-A3B-Instruct

alibaba·alibaba/qwen3-vl-30b-a3b-instruct·GA·Open weights·qwen series
Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen/Qwen3-VL-30B-A3B-Instruct by alibaba is offered by 7 providers on this page. Its reference price is $0.29 per 1M input tokens and $1.00 per 1M output tokens. The lowest paid channel is Kilo Gateway at $0.13 / $0.52 per 1M, about 2.2× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Artificial Analysis rates it 7.9 on the Intelligence Index. Against its lowest blended price of $0.228 per 1M, that is roughly 35 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 113 tokens per second, with 2.21s to the first token.

The context window is 262,000 tokens at the reference host, but hosts report different limits, from 16,384 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and Video. 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 2025-03-31.

Specs & pricing

Input / output per 1M tokens
Reference price·SiliconFlow (China)
$0.29 / $1.00
Blended $0.47 · Cache read —
Lowest paid·Kilo GatewayGateway
$0.13 / $0.52
Blended $0.23 · 2.2× spread
Context
262,000
Output limit
262,000
Knowledge cutoff
2025-03-31
Released / updated
2025-10-05 / 2025-11-25
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence7.9
Value35
Coding—
Agentic—
Output speed113 tok/s
TTFT2.21 s
Value formulaIQ 7.9 ÷ min blended $0.228 = 35

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

Available at 7 providers7 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kilo GatewayGateway$0.13$0.52——262,144 ⚠16,384
NEAR AI Cloud
Qwen/Qwen3-VL-30B-A3B-Instruct
Gateway$0.15$0.55——16,384 ⚠8,192
OpenRouterGateway$0.15$0.60——262,144 ⚠16,384
DevPass (LLM Gateway)Gateway$0.15$0.60——262,144 ⚠8,192
NovitaAIGateway$0.20$0.70——131,072 ⚠32,768
SiliconFlow
Qwen/Qwen3-VL-30B-A3B-Instruct
Cloud$0.29$1.00——262,000262,000
SiliconFlow (China)
Qwen/Qwen3-VL-30B-A3B-Instruct
Cloud$0.29$1.00——262,000262,000

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

1Kilo Gateway$52.00
2NEAR AI Cloud$57.50
3OpenRouter$60.00
4DevPass (LLM Gateway)$60.00
5NovitaAI$75.00
6SiliconFlow$108.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.00$02026-08-052026-09-032026-08-05 · Input list $0.152026-08-06 · Input list $0.152026-08-07 · Input list $0.152026-08-08 · Input list $0.152026-08-09 · Input list $0.152026-08-10 · Input list $0.152026-08-11 · Input list $0.152026-08-12 · Input list $0.152026-08-13 · Input list $0.152026-08-14 · Input list $0.152026-08-29 · Input list $0.152026-09-03 · Input list $0.292026-08-05 · Output list $0.602026-08-06 · Output list $0.602026-08-07 · Output list $0.602026-08-08 · Output list $0.602026-08-09 · Output list $0.602026-08-10 · Output list $0.602026-08-11 · Output list $0.602026-08-12 · Output list $0.602026-08-13 · Output list $0.602026-08-14 · Output list $0.602026-08-29 · Output list $0.602026-09-03 · Output list $1.002026-08-05 · Min blended $0.252026-08-06 · Min blended $0.252026-08-07 · Min blended $0.252026-08-08 · Min blended $0.252026-08-09 · Min blended $0.252026-08-10 · Min blended $0.252026-08-11 · Min blended $0.252026-08-12 · Min blended $0.252026-08-13 · Min blended $0.252026-08-14 · Min blended $0.232026-08-29 · Min blended $0.252026-09-03 · Min blended $0.23

Artificial Analysis evaluations8 items

GPQA Diamond69.5%
Humanity's Last Exam6.3%
MMLU-Pro76.4%
LiveCodeBench47.6%
Terminal-Bench Hard6.1%
AIME 202572.3%
τ²-Bench Telecom19.0%
IFBench33.1%

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 / $0.60Gemma 3 12B ITcheaper alternative$0.27 / $0.27Grok 4.1 Fast (Non-Reasoning)cheaper alternative$0.20 / $0.50grok-4-fast-non-reasoningcheaper alternative$0.20 / $0.50Ministral 8Bcheaper alternative$0.15 / $0.15
Data partly from models.dev (MIT) · SiliconFlow (China) official docs ↗