Qwen3.8 Max (0902)

Provider: Alibaba (Qwen) CN Official API price

Input price
$2.00
/ 1M tokens
Output price
$6.00
/ 1M tokens
Cache price
$0.25
/ 1M tokens (read)
Batch API
$1.15 / $3.45
input / output per 1M tokens
Context
1M tokens
Max output 131K tokens

Overview

Alibaba's Qwen3.8 Max (0902) is a 2.4-trillion-parameter MoE flagship model built for multimodal reasoning tasks.

Strengths

  • 2.4-trillion-parameter mixture-of-experts architecture
  • 1,000,000 token context window
  • 131,072 token maximum output length
  • Supports vision, function-calling, json-mode, and thinking

Best use cases

  • Large-scale multimodal document analysis
  • Complex agentic tool-use workflows
  • Long-context video and text reasoning

Pricing position

Priced at $2/1M input and $6/1M output, matching Mistral Large 2407 while undercutting GPT-4.1 output costs.

Caveats

Batch API offers discounted rates at $1.15/1M input and $3.45/1M output.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
131K tokens
Listed on OpenRouter
2026-09-03
Tracked since
2026-09-05
Last updated
2026-11-10

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-09-05 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.50
1M (small app) 1 0.5 $5.00
10M (mid scale) 10 5 $50.00
100M (large) 100 50 $500.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3.8-max-0902)