Skip to content

Qwen3 VL 30B A3B Instruct

text + image → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.263

at DeepInfra

Input / output
$0.15 / $0.60
Providers
3
Spread
1.78×
7 days
0%
30 days
0%
Context
256K
Prices per 1M tokens, blended: DeepInfra $0.263, Novita $0.325, SiliconFlow $0.468.

Providers

  • DeepInfraCheapest
    $0.263
    $0.15 in · $0.60 out
    ref vs ref
    256K ctx100% uptimefp8
  • $0.325
    $0.20 in · $0.70 out
    +24% vs ref
    128K ctx95.9% uptimebf16
  • $0.468
    $0.29 in · $1.00 out
    +78% vs ref
    256K ctx93.9% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.263 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

No provider has changed its price since tracking began on Oct 3, 2026.

Changes

About

The cheapest provider for Qwen3 VL 30B A3B Instruct is DeepInfra at $0.263 per 1M tokens (blended), charging $0.15 per 1M input and $0.60 per 1M output tokens. 3 providers serve it; the most expensive charges 1.78× the typical price. Context window: 256K tokens. Prices tracked since Oct 3, 2026.

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
Released
Oct 6, 2025
First tracked
Oct 3, 2026
Canonical slug
qwen/qwen3-vl-30b-a3b-instruct
Weights
Qwen/Qwen3-VL-30B-A3B-Instruct