Alibaba

Qwen3 Max

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

Pricing (per 1M tokens)

Input$1.20
Output$6.00
Blended (3:1)$2.40

Source: Artificial Analysis

Performance

Output Speed58 tok/s
Time to First Token2270ms

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. Qwen3 Max is positioned in the mid-tier at $6.00/M output tokens. The benchmark profile is balanced — scoring across standard tests — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.

Latency. On latency, Qwen3 Max reports 58 tok/s output speed and 2270ms 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 Max costs $1.80 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 MaxCurrent
$1.20$6.0058 tok/s
Grok 4.20 0309 (Reasoning)
$2.00$6.00
Mistral Large 2 (Jul '24)
$2.00$6.00
Grok 4.20 0309 (Non-reasoning)
$2.00$6.00
Grok 4.5 (high)
$2.00$6.0064 tok/s
Grok 4.6 (high)
$2.00$6.0056 tok/s

Example Costs

Single Request
$0.0042
1.0K in / 500 out
1K Requests/day
$4.20
1.0M in / 500.0K out
10K Requests/day
$42.00
10.0M in / 5.0M out