RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Qwen: Qwen4 Max API pricing

$1.425 per 1M input tokens and $4.275 per 1M output tokens on OpenRouter. Context window: 1,000,000 tokens.

$1.425input / 1M tokens
$4.275output / 1M tokens
$0.0712cached input / 1M
977Kcontext
text+image+video->textmodality

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$38.48
RAG: 1,000 queries (8,000 in / 600 out each)$13.96
Summarize 100 long documents (50,000 in / 1,000 out each)$7.55

Cross-check against the provider's list price

LiteLLM's price map lists dashscope/qwen4-max (dashscope) at $1.50 in / $4.50 out per 1M tokens. Differs from OpenRouter OpenRouter routes to several hosts and may list a different provider's price than the model maker's own API.

Price history

No price change recorded since we started tracking on Nov 17, 2026. We check every 6 hours and log every change.

Cheaper alternatives with similar context

Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.

ModelInput / 1MOutput / 1MContext
DeepSeek: DeepSeek Pro Latest$0.0999$8.001M
Google: Gemini 4 Carbon (batch)$1.00$5.001M
OpenAI: GPT-6.1 Terra Pro$1.00$5.001.0013580322265625M
OpenAI: GPT-6.1 Terra$1.00$5.001.0013580322265625M
Meta: Muse Spark Open$1.25$4.251M
Google: Gemini 4 Argon (batch)$1.00$5.001M
OpenAI: GPT-6.1 Sol Pro (batch)$1.00$5.001.0013580322265625M
OpenAI: GPT-6.1 Sol (batch)$1.00$5.001.0013580322265625M

Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 17, 2026. Model ID qwen/qwen4-max, listed Nov 16, 2026. Report an error.