Qwen: Qwen3.8 Max (0902) — pricing & benchmarks

By qwen · Updated 2026-10-06 · Reads imageslong-context / RAGreads images / documentsstep-by-step reasoning

What Qwen: Qwen3.8 Max (0902) is used for

Qwen: Qwen3.8 Max (0902) is best suited for long-context / RAG, reads images / documents, step-by-step reasoning. Access it through one Appmo API key alongside 458 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.

What people are saying (last 30 days)

Not enough posts yet to judge community sentiment. 1 Hacker News stories (1 points) · 9 new GitHub repos mentioning it. How we measure this.

• Qwen3.8 Max – Cost per task higher than Astra on Artificial Analysis — Hacker News, 1 pts, 1 comments

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"qwen/qwen3.8-max-0902","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does Qwen: Qwen3.8 Max (0902) cost?
Qwen: Qwen3.8 Max (0902) costs $2 per 1M input tokens and $6 per 1M output tokens ($3 blended), as of 2026-10-06. Prices are expected to fall as competition increases.

What is Qwen: Qwen3.8 Max (0902) best for?
Qwen: Qwen3.8 Max (0902) is best suited for long-context / RAG, reads images / documents, step-by-step reasoning.

How do I use Qwen: Qwen3.8 Max (0902)?
Send requests to Appmo's OpenAI-compatible endpoint with model id "qwen/qwen3.8-max-0902" and one API key — no separate provider account needed.

Is Qwen: Qwen3.8 Max (0902) open source?
We have no record of public weights for Qwen: Qwen3.8 Max (0902); treat it as a closed model available only through its provider's API.

Can Qwen: Qwen3.8 Max (0902) create images?
No. Qwen: Qwen3.8 Max (0902) can read and understand images, but it only writes text.