LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3 235B-A22B

alibaba·alibaba/qwen3-235b-a22b·Deprecated·Open weights·qwen series
Large open Qwen MoE for multilingual reasoning, coding, and tool use

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$0.70 / $2.80
Blended $1.23 · Cache read —
Lowest paid·Jiekou.AIGateway
$0.20 / $0.80
Blended $0.35 · 3.5× spread
Context
131,072
Output limit
16,384
Knowledge cutoff
2025-04
Released / updated
2025-04-28 / 2025-04-28
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

Qwen3 235B-A22B by alibaba is offered by 8 providers on this page. Its official list price is $0.70 per 1M input tokens and $2.80 per 1M output tokens. The lowest paid channel is Jiekou.AI at $0.20 / $0.80 per 1M, about 3.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 40,960 to 131,072, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. 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 8 providers8 with public prices

  • ProviderInput / Output
  • Jiekou.AIGateway
    qwen/qwen3-235b-a22b-fp8
    $0.20 / $0.80
    Context 40,960 ⚠Output limit 20,000
  • Hugging FaceCloud
    Qwen/Qwen3-235B-A22B
    $0.20 / $0.80
    Context 40,960 ⚠Output limit 16,384
  • Alibaba (China)OfficialFirst-party
    $0.29 / $1.15
    Context 131,072Output limit 16,384deprecated
  • Merge GatewayGateway
    $0.29 / $1.15
    Cache read $0.057Context 131,072Output limit 32,768
  • QiniuGateway
    $0.29 / $1.16
    Context 128,000 ⚠Output limit 32,000deprecated
  • 302.AIGateway
    $0.29 / $2.86
    Context 128,000 ⚠Output limit 16,384
  • MoneoGateway
    qwen3-235b:web
    $0.40 / $3.00
    Context 128,000 ⚠Output limit 16,384
  • AlibabaOfficialFirst-party
    $0.70 / $2.80
    Context 131,072Output limit 16,384deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Jiekou.AI
qwen/qwen3-235b-a22b-fp8
Gateway$0.20$0.80——40,960 ⚠20,000
Hugging Face
Qwen/Qwen3-235B-A22B
Cloud$0.20$0.80——40,960 ⚠16,384
Alibaba (China)OfficialFirst-party$0.29$1.15——131,07216,384deprecated
Merge GatewayGateway$0.29$1.15$0.057—131,07232,768
QiniuGateway$0.29$1.16——128,000 ⚠32,000deprecated
302.AIGateway$0.29$2.86——128,000 ⚠16,384
Moneo
qwen3-235b:web
Gateway$0.40$3.00——128,000 ⚠16,384
AlibabaOfficialFirst-party$0.70$2.80——131,07216,384deprecated

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_tokens

2 / 8 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Jiekou.AI$80.00
2Hugging Face$80.00
3Merge Gateway$87.20
4Alibaba (China) · Official$114.75
5Qiniu$115.94
6302.AI$201.00
Switch to Jiekou.AI to save $34.75/mo (30%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.80$02026-08-052026-11-13
2026-11-13Input list $0.70Output list $2.80Min blended $0.35

Benchmark2 items

NameConditionsScoreMetricSource
Aider Polyglot—59.6percent correctSource ↗
SWE-Bench Prodataset: public21.41resolve 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—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 14Bsame lab$0.35 / $1.40Qwen3 235B-A22B Instruct 2507same lab—
Data partly from models.dev (MIT) · Alibaba official docs ↗