Alibaba Qwen
Qwen3.8-Max: price, context window, and caching
Qwen's most capable model, built for long autonomous coding and professional work.
Released August 2, 2026 · Prices as of September 28, 2026
In Alibaba Qwen’s words
“Today, we are officially releasing Qwen 3.8-Max, the most capable model in the Qwen family to date.”
Facts
Specs and prices
| Fact | Qwen3.8-Max |
|---|---|
| Maker | Alibaba Qwen |
| API model id | qwen3.8-max |
| Released | August 2, 2026 |
| Status | Current |
| Context window | 1M tokens |
| Max output | 131K tokens |
| Open weights | No |
| Input, per 1M tokens | $2 |
| Cache hit, per 1M | $0.25 |
| Cache write, per 1M | $2 (same as input) |
| Output, per 1M tokens | $6 |
| Runs in | OpenCode and OpenRouter |
Standard API rates in US dollars, as published by the maker on September 28, 2026. Batch and priority tiers, taxes, and subscription plans are not included. Qwen3.8-Max: Qwen Cloud prices. Alibaba Cloud Model Studio's international scope lists the same input and output rates.
Good to know
- The API model is closed, and Qwen publishes open weights for its base variant, Qwen3.8-2.4T-A95B.
Cost
What typical work costs
Example token counts at Qwen3.8-Max’s published rates. On the agentic session, caching saves $3.50 against billing every token as ordinary input.
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $1.80 |
|---|---|
| Large one-off review, 150K input with no cache hits, 10K output | $0.36 |
| Output-heavy generation, 30K input, 80K output | $0.54 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $198.00 |
Prompt caching
How Alibaba Qwen bills cached tokens
Alibaba Qwen
Implicit caching is automatic and can't be turned off. A hit on Qwen3.8-Max costs $0.25 per million tokens, and written tokens cost ordinary input.
Explicit caching, marked with cache_control, lasts 5 minutes. On Qwen3.8-Max it costs $2.50 per million tokens to create and $0.17 per million to read. This blog prices Qwen with implicit caching.
Qwen3.8-Max compared
Qwen3.8-Max vs Claude Sonnet 5
Qwen3.8-Max and Claude Sonnet 5 both charge $2 per million input tokens. Output and cache writes set them apart: $1.80 against $2.40 per coding session.
Qwen3.8-Max vs Claude Opus 5.5
Qwen3.8-Max costs $1.80 on an agentic coding session against $4.40 on Claude Opus 5.5. Both are closed API models, and cache writes drive most of the gap.
Qwen3.8-Max vs GLM-5.3
GLM-5.3 costs $1.44 per cached coding session against $1.80 on Qwen3.8-Max, even though cache hits cost about the same. Rates, caching, weights, and tools.
Qwen3.8-Max vs GPT-6 Sol
Qwen3.8-Max and GPT-6 Sol list the same $2 input rate, and an agentic coding session differs by $0.30. How output, cache writes, and Codex shape the choice.
Qwen3.8-Max vs Kimi K3
Qwen3.8-Max undercuts Kimi K3 on every rate, $1.80 against $2.85 for an agentic coding session. Kimi K3 has open weights; the Qwen3.8-Max API model does not.
Your own numbers
See what Qwen3.8-Max really costs you.
everyaitoken reads your OpenRouter history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.