Alibaba

Qwen3 235B A22B (Non-reasoning)

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

Pricing (per 1M tokens)

Input$0.70
Output$2.80
Blended (3:1)$1.23

Source: Artificial Analysis

Performance

Output Speed59 tok/s
Time to First Token2650ms

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. Qwen3 235B A22B (Non-reasoning) is a budget-tier option from Alibaba at $2.80/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 235B A22B (Non-reasoning) reports 59 tok/s output speed and 2650ms 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 235B A22B (Non-reasoning) costs $0.98 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 235B A22B (Non-reasoning)Current
$0.70$2.8059 tok/s
DeepSeek V3.1 Terminus (Reasoning)
$1.64$2.75
Nemotron 3 Ultra 550B A55B (Reasoning)
$0.60$2.75146 tok/s
Llama 3 Instruct 70B
$0.65$2.75
Apertus 70B Instruct
$0.82$2.92
LongCat 2.0
$0.75$2.9544 tok/s

Example Costs

Single Request
$0.0021
1.0K in / 500 out
1K Requests/day
$2.10
1.0M in / 500.0K out
10K Requests/day
$21.00
10.0M in / 5.0M out