LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3 VL 30B A3B Instruct

alibaba·alibaba/qwen3-vl-30b-a3b-instruct·GA·Open weights·qwen series
Open vision-language MoE model for image and video understanding, documents, and visual agents

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·SiliconFlow (China)Cloud
$0.10 / $0.42
Blended $0.18 · 2.8× spread
Context
262,000
Output limit
262,000
Knowledge cutoff
—
Released / updated
2025-10-04 / 2025-10-04
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImageVideo
License
Apache-2.0
Weights
Hugging Face

Qwen3 VL 30B A3B Instruct by alibaba is offered by 15 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is SiliconFlow (China) at $0.105 / $0.418 per 1M. Prices vary about 2.8× across the providers that host it.

Median output speed is 38 tokens per second, with 2.46s 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.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed38 tok/s
TTFT2.46 s

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

Available at 15 providers15 with public prices

  • ProviderInput / Output
  • SiliconFlow (China)Cloud
    Qwen/Qwen3-VL-30B-A3B-Instruct
    $0.10 / $0.42
    Context 262,000Output limit 262,000
  • NEAR AI CloudGateway
    Qwen/Qwen3-VL-30B-A3B-Instruct
    $0.15 / $0.55
    Cache read $0.03Context 16,384 ⚠Output limit 8,192
  • LLM GatewayGateway
    $0.15 / $0.60
    Context 262,144 ⚠Output limit 32,768
  • DevPass (LLM Gateway)Gateway
    $0.15 / $0.60
    Context 262,144 ⚠Output limit 8,192
  • Merge GatewayGateway
    $0.15 / $0.60
    Cache read $0.022Context 131,072 ⚠Output limit 32,768
  • OpenRouterGateway
    $0.15 / $0.60
    Context 262,144 ⚠Output limit 16,384
  • Eden AIGateway
    deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct
    $0.15 / $0.60
    Context 262,144 ⚠Output limit 32,768
  • Kilo GatewayGateway
    $0.15 / $0.60
    Context 262,144 ⚠Output limit 16,384
  • Deep InfraCloud
    Qwen/Qwen3-VL-30B-A3B-Instruct
    $0.15 / $0.60
    Context 262,144 ⚠Output limit 32,768
  • LLM GatewayGateway
    $0.20 / $0.70
    Context 131,072 ⚠Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
SiliconFlow (China)
Qwen/Qwen3-VL-30B-A3B-Instruct
Cloud$0.10$0.42——262,000262,000
NEAR AI Cloud
Qwen/Qwen3-VL-30B-A3B-Instruct
Gateway$0.15$0.55$0.03—16,384 ⚠8,192
LLM GatewayGateway$0.15$0.60——262,144 ⚠32,768
DevPass (LLM Gateway)Gateway$0.15$0.60——262,144 ⚠8,192
Merge GatewayGateway$0.15$0.60$0.022—131,072 ⚠32,768
OpenRouterGateway$0.15$0.60——262,144 ⚠16,384
Eden AI
deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct
Gateway$0.15$0.60——262,144 ⚠32,768
Kilo GatewayGateway$0.15$0.60——262,144 ⚠16,384
Deep Infra
Qwen/Qwen3-VL-30B-A3B-Instruct
Cloud$0.15$0.60——262,144 ⚠32,768
LLM GatewayGateway$0.20$0.70——131,072 ⚠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

Common scenarios
1SiliconFlow (China)$41.85
2NEAR AI Cloud$43.10
3Merge Gateway$44.59
4Phala$54.60
5LLM Gateway$60.00
6DevPass (LLM Gateway)$60.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.25$02026-08-052026-10-22
2026-10-22Input list —Output list —Min blended $0.18

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—Qwen3 VL 235B A22B Thinkingsame lab—Qwen/Qwen3-VL-8B-Instructsame lab—
Data partly from models.dev (MIT)