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.
Guides
When prompt caching costs more than it saves
Cache writes cost more than ordinary input on Claude and newer GPT models. Worked examples show when a write never pays back and caching adds cost.
5-minute vs 1-hour cache writes: which pays off?
Anthropic's 1-hour cache write costs 2x input, the 5-minute write 1.25x. When the longer lifetime saves money depends on the gaps between your requests.
What is API-equivalent cost?
API-equivalent cost is what your AI coding tokens would cost at the provider's published API rates. What it measures, how it is computed, and what it is 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. $9.99 once.