LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3 Max

alibaba·alibaba/qwen3-max·Deprecated·Closed·qwen series
Flagship Qwen3 model for coding agents, complex reasoning, and tool use

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$1.20 / $6.00
Blended $2.40 · Cache read —
Lowest paid·OfoxGateway
$0.36 / $1.43
Blended $0.63 · 3.3× spread
Context
262,144
Output limit
65,536
Knowledge cutoff
2025-04
Released / updated
2025-09-23 / 2025-09-23
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Qwen3 Max by alibaba is offered by 17 providers on this page. Public prices are shown for 15 of them. Its official list price is $1.20 per 1M input tokens and $6.00 per 1M output tokens. The lowest paid channel is Ofox at $0.36 / $1.43 per 1M, about 3.8× 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 262,144 tokens at the reference host, but hosts report different limits, from 131,072 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. 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 17 providers15 with public prices · 2 subscription-covered

  • ProviderInput / Output
  • Alibaba Coding PlanGateway
    qwen3-max-2026-01-23
    Subscription
    Cache read $0Context 262,144Output limit 32,768deprecated
  • Alibaba Coding Plan (China)Gateway
    qwen3-max-2026-01-23
    Subscription
    Cache read $0Context 262,144Output limit 32,768deprecated
  • OfoxGateway
    $0.36 / $1.43
    Cache read $0.072Context 256,000 ⚠Output limit 64,000
  • OfoxGateway
    $0.36 / $1.43
    Cache read $0.072Context 262,144Output limit 65,536
  • Alibaba (China)OfficialFirst-party
    $0.36 / $1.43
    tiered >32K: $0.57 · >128K: $1.00
    Context 262,144Output limit 65,536deprecated
  • Merge GatewayGateway
    $0.36 / $1.43
    Cache read $0.072Context 262,144Output limit 65,536
  • OrcaRouterGateway
    $0.36 / $1.43
    tiered >32K: $0.57 · >128K: $1.00
    Context 262,144Output limit 65,536
  • AIHubMixGateway
    $0.45 / $2.70
    tiered >32K: $0.90 · >128K: $1.35
    Cache read $0.09Context 262,144Output limit 65,536deprecated
  • 302.AIGateway
    qwen3-max-2025-09-23
    $0.86 / $3.43
    tiered >32K: $1.43 · >128K: $2.15
    Context 258,048 ⚠Output limit 65,536
  • QiniuGateway
    $0.87 / $3.48
    tiered >32K: $1.45 · >128K: $2.17
    Context 262,144Output limit 65,536deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Alibaba Coding Plan
qwen3-max-2026-01-23
GatewaySubscription$0$0262,14432,768deprecated
Alibaba Coding Plan (China)
qwen3-max-2026-01-23
GatewaySubscription$0$0262,14432,768deprecated
OfoxGateway$0.36$1.43$0.072—256,000 ⚠64,000
OfoxGateway$0.36$1.43$0.072—262,14465,536
Alibaba (China)OfficialFirst-party$0.36
tiered >32K: $0.57 · >128K: $1.00
$1.43——262,14465,536deprecated
Merge GatewayGateway$0.36$1.43$0.072$0.45262,14465,536
OrcaRouterGateway$0.36
tiered >32K: $0.57 · >128K: $1.00
$1.43——262,14465,536
AIHubMixGateway$0.45
tiered >32K: $0.90 · >128K: $1.35
$2.70$0.09$0.56262,14465,536deprecated
302.AI
qwen3-max-2025-09-23
Gateway$0.86
tiered >32K: $1.43 · >128K: $2.15
$3.43——258,048 ⚠65,536
QiniuGateway$0.87
tiered >32K: $1.45 · >128K: $2.17
$3.48——262,14465,536deprecated

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
1Ofox$108.94
2Ofox$108.94
3Merge Gateway$109.04
4Alibaba (China) · Official$143.50
5OrcaRouter$143.50
6AIHubMix$182.12

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 Ofox to save $34.56/mo (24%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$7.75$02026-08-052026-09-24
2026-09-24Input list $1.20Output list $6.00Min blended $0.63

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index—26.4indexSource ↗
SciCode—38.3percent correctSource ↗
Terminal-Bench Hard—20.5success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—GPT-4.1 minicheaper alternative$0.40 / $1.60Mistral Large 3cheaper alternative$0.50 / $1.50Codestral 25.08cheaper alternative$0.30 / $0.90Qwen3 Coder Flashcheaper alternative$0.30 / $1.50Qwen3 Embedding 8Bsame lab—Qwen3-Next 80B-A3B Instructsame lab$0.50 / $2.00
Data partly from models.dev (MIT) · Alibaba official docs ↗