LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3-VL Plus

alibaba·alibaba/qwen3-vl-plus·GA·Closed·qwen series
Qwen vision-language model for visual reasoning, documents, and agent tasks

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$0.20 / $1.60
Blended $0.55 · Cache read $0.04
Lowest paid·AIHubMixGateway
$0.14 / $1.37
Blended $0.45 · 1.5× spread
Context
262,144
Output limit
32,768
Knowledge cutoff
2025-04
Released / updated
2025-09-23 / 2025-09-23
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo

Qwen3-VL Plus by alibaba is offered by 8 providers on this page. Its official list price is $0.20 per 1M input tokens and $1.60 per 1M output tokens. The lowest paid channel is AIHubMix at $0.137 / $1.37 per 1M, about 1.2× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 256,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and Video. 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.

Available at 8 providers8 with public prices

  • ProviderInput / Output
  • AIHubMixGateway
    $0.14 / $1.37
    tiered >32K: $0.21 · >128K: $0.41
    Cache read $0Context 262,144Output limit 32,768
  • Merge GatewayGateway
    $0.14 / $1.43
    Cache read $0.029Context 262,144Output limit 65,536
  • Alibaba (China)OfficialFirst-party
    $0.14 / $1.43
    tiered >32K: $0.22 · >128K: $0.43
    Cache read $0.029Context 262,144Output limit 32,768
  • Novita AIGateway
    $0.14 / $1.43
    tiered >32K: $0.22 · >128K: $0.43
    Cache read $0.014Context 262,000 ⚠Output limit 32,000
  • AlibabaOfficialFirst-party
    $0.20 / $1.60
    tiered >32K: $0.30 · >128K: $0.60
    Cache read $0.04Context 262,144Output limit 32,768
  • LLM GatewayGateway
    $0.20 / $1.60
    Cache read $0.04Context 262,144Output limit 32,768
  • DevPass (LLM Gateway)Gateway
    $0.20 / $1.60
    Cache read $0.04Context 262,144Output limit 32,768
  • LLMTRGateway
    $0.20 / $1.60
    Cache read $0.04Context 256,000 ⚠Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
AIHubMixGateway$0.14
tiered >32K: $0.21 · >128K: $0.41
$1.37$0—262,14432,768
Merge GatewayGateway$0.14$1.43$0.029$0.18262,14465,536
Alibaba (China)OfficialFirst-party$0.14
tiered >32K: $0.22 · >128K: $0.43
$1.43$0.029$0.18262,14432,768
Novita AIGateway$0.14
tiered >32K: $0.22 · >128K: $0.43
$1.43$0.014$0.18262,000 ⚠32,000
AlibabaOfficialFirst-party$0.20
tiered >32K: $0.30 · >128K: $0.60
$1.60$0.04$0.25262,14432,768
LLM GatewayGateway$0.20$1.60$0.04$0.25262,14432,768
DevPass (LLM Gateway)Gateway$0.20$1.60$0.04$0.25262,14432,768
LLMTRGateway$0.20$1.60$0.04—256,000 ⚠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.

Reasoning control

Toggle (on / off)budget_tokens

Interleaved thinking (reasoning between tool calls) is declared by 2 of 8 providers.

2 / 8 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1AIHubMix$79.46
2Novita AI$84.90
3Merge Gateway$86.57
4Alibaba (China) · Official$86.59
5Alibaba · Official$100.80
6LLM Gateway$100.80
Switch to AIHubMix to save $7.13/mo (8%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.60$02026-08-052026-09-28
2026-09-28Input list $0.20Output list $1.60Min blended $0.45

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60Claude Haiku 5.5cheaper alternative$0.10 / $0.50Gemma 4 31B ITcheaper alternative$0 / $0Qwen/Qwen3-VL-8B-Instructsame lab—Qwen3.5 122B-A10Bsame lab$0.40 / $3.20
Data partly from models.dev (MIT) · Alibaba official docs ↗