LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3 VL 235B A22B Instruct

alibaba·alibaba/qwen3-vl-235b-a22b-instruct·GA·Open weights·qwen series
Qwen vision-language instruct model for visual reasoning, documents, and agent tasks

Qwen3 VL 235B A22B Instruct by alibaba is offered by 16 providers on this page. Its reference price is $0.53 per 1M input tokens and $2.66 per 1M output tokens. The lowest paid channel is Deep Infra at $0.20 / $0.88 per 1M, about 2.7× below the reference price.

Artificial Analysis rates it 9.9 on the Intelligence Index. Against its lowest blended price of $0.37 per 1M, that is roughly 27 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 53 tokens per second, with 2.75s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 129,024 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and Video. 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 2025-03-31.

Specs & pricing

Input / output per 1M tokens
Reference price·Amazon Bedrock
$0.53 / $2.66
Blended $1.06 · Cache read —
Lowest paid·Deep InfraCloud
$0.20 / $0.88
Blended $0.37 · 2.7× spread
Context
262,144
Output limit
262,000
Knowledge cutoff
2025-03-31
Released / updated
2025-09-23 / 2025-09-23
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Weights
Hugging Face

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence9.9
Value27
Coding—
Agentic—
Output speed53 tok/s
TTFT2.75 s
Value formulaIQ 9.9 ÷ min blended $0.370 = 27

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

Available at 16 providers16 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Deep Infra
Qwen/Qwen3-VL-235B-A22B-Instruct
Cloud$0.20$0.88$0.11—262,14432,768
DevPass (LLM Gateway)Gateway$0.20$0.88$0.11—262,1448,192
LLM GatewayGateway$0.20$0.88$0.11—262,14432,768
Kilo GatewayGateway$0.26$1.04——131,072 ⚠32,768
Merge GatewayGateway$0.29$1.15$0.16—131,072 ⚠32,768
NovitaAIGateway$0.30$1.50——131,072 ⚠32,768
Hugging Face
Qwen/Qwen3-VL-235B-A22B-Instruct
Cloud$0.30$1.50——131,072 ⚠32,768
Jalapeno Cloud
Qwen3-VL-235B-A22B-Instruct
Gateway$0.30$1.50——129,024 ⚠32,768
HeliconeGateway$0.30$1.50——256,000 ⚠16,384
LLM GatewayGateway$0.30$1.50——131,072 ⚠32,768

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

1Deep Infra$73.20
2DevPass (LLM Gateway)$73.20
3LLM Gateway$73.20
4Merge Gateway$99.25
5Kilo Gateway$104.00
6OpenRouter$123.80
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.66$02026-08-052026-09-122026-08-05 · Input list $0.402026-08-06 · Input list $0.402026-08-07 · Input list $0.402026-08-08 · Input list $0.402026-08-09 · Input list $0.402026-08-10 · Input list $0.402026-08-11 · Input list $0.402026-08-12 · Input list $0.402026-08-13 · Input list $0.402026-09-12 · Input list $0.532026-08-05 · Output list $1.602026-08-06 · Output list $1.602026-08-07 · Output list $1.602026-08-08 · Output list $1.602026-08-09 · Output list $1.602026-08-10 · Output list $1.602026-08-11 · Output list $1.602026-08-12 · Output list $1.602026-08-13 · Output list $1.602026-09-12 · Output list $2.662026-08-05 · Min blended $0.372026-08-06 · Min blended $0.372026-08-07 · Min blended $0.372026-08-08 · Min blended $0.372026-08-09 · Min blended $0.372026-08-10 · Min blended $0.372026-08-11 · Min blended $0.372026-08-12 · Min blended $0.372026-08-13 · Min blended $0.372026-09-12 · Min blended $0.37

Artificial Analysis evaluations9 items

GPQA Diamond71.2%
Humanity's Last Exam6.6%
MMLU-Pro82.3%
LiveCodeBench59.4%
Terminal-Bench Hard6.8%
AIME 202570.7%
τ²-Bench Telecom35.1%
AA-LCR32.7%
IFBench42.6%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Qwen-Image-2.1same series$0 / $0Qwen 3.8 27B Hemingwaysame series$0.25 / $1.50Qwen 3.8 27B Cybersecuritysame series$0.10 / $0.60Qwen3 Coder Flashcheaper alternative$0.30 / $1.50Gemma 3 12B ITcheaper alternative$0.27 / $0.27Qwen3 30B A3B Instruct 2507cheaper alternative$0.30 / $0.50DeepSeek V3.2 Expcheaper alternative$0.29 / $0.43
Data partly from models.dev (MIT) · Amazon Bedrock official docs ↗