computetrail

All models ·qwen

Qwen: Qwen3 Max

Provider: qwen · qwen/qwen3-max

Input
$0.78 /1M
Output
$3.9 /1M
Cache read
$0.156 /1M
Context
262,144 tokens

How Qwen: Qwen3 Max pricing compares

At $3.9 / 1M output tokens, Qwen: Qwen3 Max is the 46th-cheapest of 51 qwen models we track. It's cheaper than 36% of the 392 paid models on computetrail (250th-cheapest overall). Output costs 5.0× its input price ($0.78 / 1M in). For a typical 3:1 input-to-output workload that works out to about $1.56 / 1M blended. Reading cached input costs 80% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 262,144 tokens context window ranks 213th-largest of 392 models with a published limit.

Output price history

$3.90$3.9006-2907-2908-27

Across 60 daily snapshots since 2026-06-29, the output price has held steady at $3.9 / 1M — no change so far.

Similar-priced models

ModelProviderOutput $/1MContext
Z.ai: GLM 5.1z-ai$3.96204,800
MoonshotAI: Kimi K2.7 Code (batch)moonshotai$4262,144
MoonshotAI: Kimi K2.6moonshotai$4262,144
OpenAI: o3 (batch)openai$4200,000
Google: Gemini 3.6 Flashgoogle$3.751,048,576
Z.ai: GLM 5.2z-ai$3.741,048,576

Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.