Alibaba

Qwen3.5 4B (Non-reasoning)

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

Pricing (per 1M tokens)

Input$0.03
Output$0.15
Blended (3:1)$0.06

Source: Artificial Analysis

Performance

Output Speed28 tok/s
Time to First Token710ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Qwen3.5 4B (Non-reasoning) is a budget-tier option from Alibaba at $0.15/M output tokens. Despite the low price, it scores competitively on Coding Index (20.3) and Intelligence Index (16.1) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Qwen3.5 4B (Non-reasoning) reports 28 tok/s output speed and 710ms 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, Qwen3.5 4B (Non-reasoning) costs $0.04 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
Qwen3.5 4B (Non-reasoning)Current
$0.03$0.1528 tok/s
Ministral 3 8B
$0.15$0.15120 tok/s
Solar Mini
$0.15$0.15
Nova Micro
$0.04$0.14282 tok/s
Llama 3 Instruct 8B
$0.04$0.14
NVIDIA Nemotron Nano 9B V2 (Reasoning)
$0.04$0.16186 tok/s

Example Costs

Single Request
$0.0001
1.0K in / 500 out
1K Requests/day
$0.1050
1.0M in / 500.0K out
10K Requests/day
$1.05
10.0M in / 5.0M out