LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen4 Max

alibaba·alibaba/qwen4-max·GA·Closed·qwen series·NEW
Flagship multimodal model for coding, office productivity, frontend design, and complex agentic tasks

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Deep InfraCloud
$1.41 / $4.24
Blended $2.12 · 1.1× spread
Context
1,000,000
Output limit
393,216
Knowledge cutoff
—
Released / updated
2026-11-16 / 2026-11-16
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImageVideoPDF

Qwen4 Max by alibaba is offered by 16 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Deep Infra at $1.41 / $4.24 per 1M.

Artificial Analysis rates it 42.9 on the Intelligence Index, with 56.9 for Strategy & Ops, its strongest domain. Against its lowest blended price of $2.12 per 1M, that is roughly 20 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 52 tokens per second, with 3.88s to the first token. Running one task of the Artificial Analysis suite costs about $3.2681, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 983,616 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.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence42.9
Value20
Engineering50.1
Finance & Accounting54.1
Legal49.6
Healthcare & Medical48.2
Strategy & Ops56.9
Economics51.3
Output speed52 tok/s
TTFT3.88 s
Cost per task$3.27
Value formulaIQ 42.9 ÷ min blended $2.120 = 20

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 16 providers16 with public prices

  • ProviderInput / Output
  • Deep InfraCloud
    Qwen/Qwen4-Max
    $1.41 / $4.24
    Cache read $0.071Context 1,000,000Output limit 262,144
  • NanoGPTGateway
    $1.41 / $4.24
    Cache read $0.071Context 1,000,000Output limit 131,072
  • NanoGPTGateway
    qwen/qwen4-max:thinking
    $1.41 / $4.24
    Cache read $0.071Context 1,000,000Output limit 262,144
  • Novita AIGateway
    $1.41 / $4.24
    Cache read $0.071Context 1,000,000Output limit 131,000
  • OpenRouterGateway
    $1.43 / $4.28
    Cache read $0.071Context 1,000,000Output limit 131,072
  • Kilo GatewayGateway
    $1.50 / $4.50
    Cache read $0.075Context 1,000,000Output limit 131,072
  • Charm HyperGateway
    $1.50 / $4.50
    Cache read $0.075Context 1,000,000Output limit 128,000
  • DevPass (LLM Gateway)Gateway
    $1.50 / $4.50
    Cache read $0.075Context 983,616 ⚠Output limit 262,144
  • OfoxGateway
    $1.50 / $4.50
    Cache read $0.075Context 1,000,000Output limit 262,144
  • LLM GatewayGateway
    $1.50 / $4.50
    Cache read $0.075Context 983,616 ⚠Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Deep Infra
Qwen/Qwen4-Max
Cloud$1.41$4.24$0.071—1,000,000262,144
NanoGPTGateway$1.41$4.24$0.071$1.771,000,000131,072
NanoGPT
qwen/qwen4-max:thinking
Gateway$1.41$4.24$0.071$1.771,000,000262,144
Novita AIGateway$1.41$4.24$0.071$1.771,000,000131,000
OpenRouterGateway$1.43$4.28$0.071$1.781,000,000131,072
Kilo GatewayGateway$1.50$4.50$0.075$1.881,000,000131,072
Charm HyperGateway$1.50$4.50$0.075—1,000,000128,000
DevPass (LLM Gateway)Gateway$1.50$4.50$0.075$1.88983,616 ⚠262,144
OfoxGateway$1.50$4.50$0.075$1.881,000,000262,144
LLM GatewayGateway$1.50$4.50$0.075$1.88983,616 ⚠131,072

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

effort = noneeffort = loweffort = higheffort = xhigheffort = minimaleffort = mediumToggle (on / off)budget_tokens ≥ 1 ≤ 262,144

Interleaved thinking (reasoning between tool calls) is declared by 1 of 16 providers.

1 / 16 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Deep Infra$333.56
2NanoGPT$333.56
3NanoGPT$333.56
4Novita AI$333.56
5OpenRouter$336.30
6Kilo Gateway$354.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.25$02026-11-162026-11-17
2026-11-17Input list —Output list —Min blended $2.12

Related models

Qwen 3.6 Plus Uncensoredsame series—Qwen3.8 27B Uncensoredsame series—Qwen3.8 27B Abliteratedsame series—Qwen3.8 Omni Flashsame lab$0.15 / $0.47Wan v2.5 Text-to-Video Previewsame lab—
Data partly from models.dev (MIT)