LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3.5 Plus

alibaba·alibaba/qwen3.5-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
$0.40 / $2.40
Blended $0.90 · Cache read —
Lowest paid·AIHubMixGateway
$0.11 / $0.66
Blended $0.25 · 3.6× spread
Context
1,000,000
Output limit
65,536
Knowledge cutoff
2025-04
Released / updated
2026-02-16 / 2026-02-16
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF

Qwen3.5 Plus by alibaba is offered by 19 providers on this page. Public prices are shown for 17 of them. Its official list price is $0.40 per 1M input tokens and $2.40 per 1M output tokens. The lowest paid channel is AIHubMix at $0.11 / $0.658 per 1M, about 3.6× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 2 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 262,144 to 1,000,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, and PDF. 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 19 providers17 with public prices · 2 subscription-covered

  • ProviderInput / Output
  • Alibaba Coding PlanGateway
    Subscription
    Cache read $0Context 1,000,000Output limit 65,536
  • Alibaba Coding Plan (China)Gateway
    Subscription
    Cache read $0Context 1,000,000Output limit 65,536
  • AIHubMixGateway
    $0.11 / $0.66
    tiered >128K: $0.27 · >256K: $0.55
    Cache read $0.011Context 1,000,000Output limit 65,536
  • Alibaba (China)OfficialFirst-party
    $0.12 / $0.69
    tiered >128K: $0.29 · >256K: $0.57
    Context 1,000,000Output limit 65,536
  • Merge GatewayGateway
    $0.12 / $0.69
    Cache read $0.023Context 1,000,000Output limit 250,000
  • 302.AIGateway
    $0.12 / $0.69
    tiered >128K: $0.29 · >256K: $0.58
    Context 1,000,000Output limit 65,536
  • OpenCodeGateway
    $0.20 / $1.20
    Cache read $0.02Context 262,144 ⚠Output limit 65,536
  • EmpirioLabs AIGateway
    qwen3-5-plus
    $0.36 / $2.21
    tiered >256K: $0.45
    Cache read $0.36Context 983,616 ⚠Output limit 65,536deprecated
  • AlibabaOfficialFirst-party
    $0.40 / $2.40
    tiered >256K: $0.50
    Context 1,000,000Output limit 65,536
  • NanoGPTGateway
    qwen/qwen3.5-plus:thinking
    $0.40 / $2.40
    Cache read $0.04Context 983,616 ⚠Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Alibaba Coding PlanGatewaySubscription$0$01,000,00065,536
Alibaba Coding Plan (China)GatewaySubscription$0$01,000,00065,536
AIHubMixGateway$0.11
tiered >128K: $0.27 · >256K: $0.55
$0.66$0.011$0.141,000,00065,536
Alibaba (China)OfficialFirst-party$0.12
tiered >128K: $0.29 · >256K: $0.57
$0.69——1,000,00065,536
Merge GatewayGateway$0.12$0.69$0.023$0.141,000,000250,000
302.AIGateway$0.12
tiered >128K: $0.29 · >256K: $0.58
$0.69——1,000,00065,536
OpenCodeGateway$0.20$1.20$0.02$0.25262,144 ⚠65,536
EmpirioLabs AI
qwen3-5-plus
Gateway$0.36
tiered >256K: $0.45
$2.21$0.36—983,616 ⚠65,536deprecated
AlibabaOfficialFirst-party$0.40
tiered >256K: $0.50
$2.40——1,000,00065,536
NanoGPT
qwen/qwen3.5-plus:thinking
Gateway$0.40$2.40$0.04$0.50983,616 ⚠65,536

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_tokenseffort = loweffort = mediumeffort = higheffort = noneeffort = minimaleffort = xhigheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 2 of 19 providers.

2 / 19 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1AIHubMix$42.96
2Merge Gateway$46.36
3Alibaba (China) · Official$57.40
4302.AI$58.50
5OpenCode$78.40
6NanoGPT$156.80

2 more channels offer $0 (Alibaba Coding Plan, Alibaba Coding Plan (China)); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to AIHubMix to save $14.44/mo (25%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$3.44$02026-08-052026-09-28
2026-09-28Input list $0.40Output list $2.40Min blended $0.25

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 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20Qwen3.5 Flashsame lab$0.10 / $0.40Qwen3.6 27Bsame lab$0.60 / $3.60
Data partly from models.dev (MIT) · Alibaba official docs ↗