Alibaba

Qwen3 235B A22B 2507 (Reasoning)

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

Pricing (per 1M tokens)

Input$0.23
Output$2.30
Blended (3:1)$0.75

Source: Artificial Analysis

Performance

Output Speed64 tok/s
Time to First Token2690ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Qwen3 235B A22B 2507 (Reasoning) is a budget-tier option from Alibaba at $2.30/M output tokens. Despite the low price, it scores competitively on Coding Index (22.1) and Intelligence Index (19.9) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Qwen3 235B A22B 2507 (Reasoning) reports 64 tok/s output speed and 2690ms 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 2507 (Reasoning) costs $0.46 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 2507 (Reasoning)Current
$0.23$2.3064 tok/s
Kimi K2
$0.57$2.3041 tok/s
GLM-4.6 (Reasoning)
$0.55$2.2054 tok/s
GLM-4.7 (Reasoning)
$0.60$2.20101 tok/s
GLM-4.7 (Non-reasoning)
$0.60$2.20104 tok/s
GLM-4.6 (Non-reasoning)
$0.57$2.2062 tok/s

Example Costs

Single Request
$0.0014
1.0K in / 500 out
1K Requests/day
$1.38
1.0M in / 500.0K out
10K Requests/day
$13.80
10.0M in / 5.0M out