LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3-Next 80B-A3B Instruct

alibaba·alibaba/qwen3-next-80b-a3b-instruct·Deprecated·Open weights·qwen series
Qwen instruction model for multilingual chat, reasoning, and tool use

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$0.50 / $2.00
Blended $0.88 · Cache read —
Lowest paid·Alibaba (China)First-party
$0.14 / $0.57
Blended $0.25 · 5.6× spread
Context
131,072
Output limit
32,768
Knowledge cutoff
2025-04
Released / updated
2025-09 / 2025-09
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Weights
Hugging Face

Qwen3-Next 80B-A3B Instruct by alibaba is offered by 22 providers on this page. Its official list price is $0.50 per 1M input tokens and $2.00 per 1M output tokens. The lowest paid channel is Alibaba (China) at $0.144 / $0.574 per 1M, about 3.5× below the list price.

Median output speed is 154 tokens per second, with 0.78s to the first token.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 65,536 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2025-04.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed154 tok/s
TTFT0.78 s

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

Available at 22 providers22 with public prices

  • ProviderInput / Output
  • Alibaba (China)OfficialFirst-party
    $0.14 / $0.57
    Context 131,072Output limit 32,768deprecated
  • QiniuGateway
    $0.14 / $0.58
    Context 131,072Output limit 32,768deprecated
  • GraphNGateway
    qwen3-80b
    $0.20 / $0.60
    Context 131,072Output limit 32,768
  • NanoGPTGateway
    $0.09 / $1.10
    Cache read $0.045Context 262,144 ⚠Output limit 32,768
  • Eden AIGateway
    deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct
    $0.09 / $1.10
    Context 262,144 ⚠Output limit 32,768
  • Vercel AI GatewayCloud
    $0.09 / $1.10
    Context 262,144 ⚠Output limit 32,768
  • Deep InfraCloud
    Qwen/Qwen3-Next-80B-A3B-Instruct
    $0.09 / $1.10
    Context 262,144 ⚠Output limit 32,768
  • Merge GatewayGateway
    $0.10 / $1.10
    Cache read $0.05Context 131,072Output limit 32,768
  • OpenRouterGateway
    $0.10 / $1.10
    Cache read $0.07Context 262,144 ⚠Output limit 235,929
  • Kilo GatewayGateway
    $0.10 / $1.10
    Cache read $0.07Context 262,144 ⚠Output limit 235,929
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Alibaba (China)OfficialFirst-party$0.14$0.57——131,07232,768deprecated
QiniuGateway$0.14$0.58——131,07232,768deprecated
GraphN
qwen3-80b
Gateway$0.20$0.60——131,07232,768
NanoGPTGateway$0.09$1.10$0.045—262,144 ⚠32,768
Eden AI
deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct
Gateway$0.09$1.10——262,144 ⚠32,768
Vercel AI GatewayCloud$0.09$1.10——262,144 ⚠32,768
Deep Infra
Qwen/Qwen3-Next-80B-A3B-Instruct
Cloud$0.09$1.10——262,144 ⚠32,768
Merge GatewayGateway$0.10$1.10$0.05—131,07232,768
OpenRouterGateway$0.10$1.10$0.07—262,144 ⚠235,929
Kilo GatewayGateway$0.10$1.10$0.07—262,144 ⚠235,929

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
1Alibaba (China) · Official$57.50
2Qiniu$57.97
3NanoGPT$67.60
4Merge Gateway$69.00
5GraphN$70.00
6OpenRouter$71.40
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.00$02026-08-052026-08-12
2026-08-12Input list $0.50Output list $2.00Min blended $0.25

Artificial Analysis evaluations9 items

GPQA Diamond73.8%
Humanity's Last Exam7.6%
CritPt0.0%
LiveCodeBench68.4%
Terminal-Bench Hard7.6%
AIME 202566.3%
τ²-Bench Telecom21.6%
AA-LCR52.7%
IFBench39.7%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—GPT-4o minicheaper alternative$0.15 / $0.60Codestral 25.08cheaper alternative$0.30 / $0.90Nova Litecheaper alternative$0.06 / $0.24Nova Microcheaper alternative$0.035 / $0.14Qwen3 Maxsame lab$1.20 / $6.00Qwen3-Next 80B-A3B (Thinking)same lab$0.50 / $6.00
Data partly from models.dev (MIT) · Alibaba official docs ↗