Skip to content

Qwen3 VL 235B A22B Instruct

text + image → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.37

at DeepInfra

Input / output
$0.20 / $0.88
Providers
3
Spread
1.71×
7 days
0%
30 days
0%
Context
256K
Prices per 1M tokens, blended: DeepInfra $0.37, Parasail $0.633, Venice $0.633.

Providers

  • DeepInfraCheapest
    $0.37
    $0.20 in · $0.88 out
    ref vs ref
    256K ctx99.9% uptimefp8
  • $0.633
    $0.21 in · $1.90 out
    +71% vs ref
    128K ctx100% uptimefp8
  • $0.633
    $0.21 in · $1.90 out
    +71% vs ref
    125K ctx100% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.37 = 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.

Other pricing

Offered byCache read
DeepInfra$0.11
Parasail, Venice$0.10

Changes

  • No longer served,
    Delisted
  • No longer served,
    Delisted
  • No longer served,
    Delisted
  • Now served,
    Listed

About

The cheapest provider for Qwen3 VL 235B A22B Instruct is DeepInfra at $0.37 per 1M tokens (blended), charging $0.20 per 1M input and $0.88 per 1M output tokens. 3 providers serve it; the most expensive charges 1.71× the typical price. Context window: 256K tokens. Prices tracked since Oct 3, 2026.

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Released
Sep 23, 2025
First tracked
Oct 3, 2026
Canonical slug
qwen/qwen3-vl-235b-a22b-instruct
Weights
Qwen/Qwen3-VL-235B-A22B-Instruct