LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen Max

alibaba·alibaba/qwen-max·GA·Closed·qwen series
Flagship Qwen model for complex reasoning, coding, and agentic workflows

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$1.60 / $6.40
Blended $2.80 · Cache read —
Lowest paid·Alibaba (China)First-party
$0.35 / $1.38
Blended $0.60 · 4.6× spread
Context
32,768
Output limit
8,192
Knowledge cutoff
2024-04
Released / updated
2024-04-03 / 2025-01-25
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Qwen Max by alibaba is offered by 10 providers on this page. Its official list price is $1.60 per 1M input tokens and $6.40 per 1M output tokens. The lowest paid channel is Alibaba (China) at $0.345 / $1.38 per 1M, about 4.6× below the list price.

The context window is 32,768 tokens at the reference host, but hosts report different limits, from 32,000 to 131,072, 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 2024-04.

Available at 10 providers10 with public prices

  • ProviderInput / Output
  • Alibaba (China)OfficialFirst-party
    $0.35 / $1.38
    Context 131,072 ⚠Output limit 8,192
  • OfoxGateway
    $0.35 / $1.38
    Cache read $0.069Context 32,000 ⚠Output limit 8,000
  • OfoxGateway
    $0.35 / $1.38
    Cache read $0.069Context 32,768Output limit 8,192
  • QiniuGateway
    qwen-max-2025-01-25
    $0.35 / $1.39
    Context 128,000 ⚠Output limit 4,096deprecated
  • AI/ML APIGateway
    $1.12 / $4.48
    Cache read $0.22Context 32,000 ⚠Output limit 8,192
  • NanoGPTGateway
    $1.60 / $6.39
    Cache read $0.80Context 32,000 ⚠Output limit 8,192
  • AlibabaOfficialFirst-party
    $1.60 / $6.40
    Context 32,768Output limit 8,192
  • LLM GatewayGateway
    $1.60 / $6.40
    Context 32,768Output limit 8,192
  • DevPass (LLM Gateway)Gateway
    $1.60 / $6.40
    Context 32,768Output limit 8,192
  • Eden AIGateway
    $1.60 / $6.40
    Cache read $0.32Context 32,768Output limit 8,192
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Alibaba (China)OfficialFirst-party$0.35$1.38——131,072 ⚠8,192
OfoxGateway$0.35$1.38$0.069—32,000 ⚠8,000
OfoxGateway$0.35$1.38$0.069—32,7688,192
Qiniu
qwen-max-2025-01-25
Gateway$0.35$1.39——128,000 ⚠4,096deprecated
AI/ML APIGateway$1.12$4.48$0.22—32,000 ⚠8,192
NanoGPTGateway$1.60$6.39$0.80—32,000 ⚠8,192
AlibabaOfficialFirst-party$1.60$6.40——32,7688,192
LLM GatewayGateway$1.60$6.40——32,7688,192
DevPass (LLM Gateway)Gateway$1.60$6.40——32,7688,192
Eden AIGateway$1.60$6.40$0.32—32,7688,192

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$105.28
2Ofox$105.28
3Alibaba (China) · Official$137.85
4Qiniu$139.13
5AI/ML API$340.48
6Eden AI$486.40
Switch to Ofox to save $32.57/mo (24%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$6.40$02026-08-052026-09-24
2026-09-24Input list $1.60Output list $6.40Min blended $0.60

Benchmark1 items

NameConditionsScoreMetricSource
Aider Polyglot—21.8percent correctSource ↗

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 / $1.60GPT-4o minicheaper alternative$0.15 / $0.60Grok 4.20 (Non-Reasoning)cheaper alternative$1.25 / $2.50Mistral Large 3cheaper alternative$0.50 / $1.50Qwen Flashsame lab$0.05 / $0.40Qwen MT Plussame lab$2.46 / $7.37
Data partly from models.dev (MIT) · Alibaba official docs ↗