Alibaba

Qwen3 VL 235B A22B Instruct

AI model by Alibaba. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.40
Output$1.60
Blended (3:1)$0.70

Source: Artificial Analysis

Performance

Output Speed47 tok/s
Time to First Token2700ms

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. Qwen3 VL 235B A22B Instruct is a budget-tier option from Alibaba at $1.60/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Qwen3 VL 235B A22B Instruct reports 47 tok/s output speed and 2700ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.

Cost model. For a workload of 1M input tokens + 100K output tokens, Qwen3 VL 235B A22B Instruct costs $0.56 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
Qwen3 VL 235B A22B InstructCurrent
$0.40$1.6047 tok/s
GPT-4.1 mini
$0.40$1.6086 tok/s
DeepSeek V3.1 (Non-reasoning)
$0.56$1.68
DeepSeek V3.1 (Non-reasoning)
$0.56$1.68
DeepSeek V3.1 (Reasoning)
$0.59$1.69
GPT-3.5 Turbo
$0.50$1.50

Example Costs

Single Request
$0.0012
1.0K in / 500 out
1K Requests/day
$1.20
1.0M in / 500.0K out
10K Requests/day
$12.00
10.0M in / 5.0M out