Skip to content
Models / Alibaba Cloud (Qwen)

Qwen 3.8 Max

Alibaba Cloud (Qwen) · Model release

Released Not recorded

Catalog checked 2026-09-29

Input $/1M
$2.00
Output $/1M
$6.00
Context
1M
Max output
131K
Reasoning
Yes
Included in
7 plans
API priceUSD / 1M tokens
Published API rates in US dollars per million tokens
RateInputOutputCache read
StandardInput$2.00Output$6.00Cache read$0.25

Published rate checked 2026-09-29. Sources below.

Rates are the Singapore (International) list prices. Other Model Studio regions list different rates, and limited-time promotions are excluded. Explicit cache creation and explicit cache reads are billed at separate published rates.

Current published base rates. Context tiers, cache-write duration and other conditions may change the rate for a request. These are not a reconstructed historical invoice.

API token estimate

Explore a token scenario

Uncached text input and billed output at this exact model’s recorded Standard API list price. Totals across a scenario, without a claim about one-request capacity.

Standard API list price · USD / 1M tokens

Pricing checked Sep 29, 2026 · Rate record from Sep 29, 2026

Record dates describe catalog coverage; they do not establish provider price activation.

Pricing record: qwen-3-8-max-pricing

Capabilities & limitsProvider specifications
Context window
1,000,000
Maximum output
131,072
Input
text · image · video
Output
text
Reasoning
Supported
Tool calling
Supported
Structured output
Supported
Before you chooseChecked 2026-09-29
Thinking
Hybrid thinking. Thinking is on by default and can be turned off per request with enable_thinking.
Released on Model Studio
Listed for Singapore (International) on August 2, 2026.
Prompt caching
Implicit cache hits cost $0.25 per 1M tokens. Explicit cache creation costs $2.50 and explicit cache reads cost $0.17 per 1M tokens.
Regions
Rates shown are for Singapore (International). China (Beijing) and the Global regions (Frankfurt, Virginia, Tokyo, Hong Kong) list different rates.
Snapshots
qwen3.8-max-0902 is a separate upgraded snapshot with its own model id.
Thinking length
Maximum chain-of-thought length is 262,144 tokens.

QwenCloud Team · Published Aug 3, 2026

Developer reported · Qwen3.8-Max release: Terminal-Bench 2.1

Methodology & sources

QwenCloud reports Qwen3.8-Max evaluated with Claude Code, avg@10, a 5-hour timeout and max_tokens=131,072.

These scores are reported by QwenCloud Team. Model developers identify authorship; results may originate with another evaluator. Exact benchmark versions remain distinct. StackReplay calculates no composite score.

Terminal-Bench 2.1 · 86.6%

Multi-step tasks in a command-line environment.

Version: 2.1 · Reported benchmark score · percent · Higher is better · Task subset: Not separately specified

QwenCloud Team · Published Aug 3, 2026 · Developer reported

Reporting source
QwenCloud Team · Qwen3.8-Max release: Terminal-Bench 2.1
Evaluation origin
QwenCloud Team administered and reported the evaluation (source-computed)
Effort
Not reported
Harness
Claude Code (version unreported; avg@10)
Tools
Not reported
Fallback
Not reported
Provider
Not reported
Checked
Oct 4, 2026

The raw table score is 86.6 in the Qwen3.8-Max column. The provider source omits the unit marker. StackReplay interprets the raw notation 86.6 on Terminal-Bench 2.1's published percent accuracy scale (https://www.tbench.ai/news/terminal-bench-2-1); numeric value is unchanged, with no arithmetic rescaling. The display % is this documented metric interpretation, not provider-explicit notation. This is the unsuffixed release, not Qwen3.8-Max-0902. Timeout: 5 hours; max_tokens=131,072. Claude Code avg@10 is the reported aggregation label. Publication uses the visible article and official news-list date 2026-08-03. The HTML meta date is 2026-07-20 15:56:48; this discrepancy is unresolved.

Evaluation start, completion and original run publication dates, actual scored task count, task subset, suite revision beyond 2.1, exact model endpoint/version, prompts, seeds and error handling are unreported. Publication dates identify the source articles, not the evaluation runs. Claude Code version, reasoning effort, tools, temperature/top-p, API surface and sandbox details are unreported. The avg@10 label is retained without inferring a scored task count.

Original methodology ↗ · Original evidence ↗

Where you can use it1 API route · 7 subscriptions
Alibaba Cloud (Qwen) APIDirect API
ClinePass
$9.99 / month ↗

$9.99 monthly; weekly and monthly usage windows follow the calendar.

Command Code Go
$1 / month ↗

Monthly cycle; purchased credits carry over without expiry.

New subscriptions use per-model allowances from September 28, 2026. Existing flat-$10 subscriptions change at their next renewal.

Command Code Pro
$20 / month ↗

Monthly cycle; purchased credits carry over without expiry.

Command Code Max 10×
$100 / month ↗

Monthly cycle; purchased credits carry over without expiry.

Command Code Max 20×
$200 / month ↗

Monthly cycle; purchased credits carry over without expiry.

OpenCode Go
$10 / month ↗

Monthly subscription; one subscriber per workspace. Paid balance fallback is optional. Recurring charges continue until canceled through account settings. Reset anchors, rollover and a Go-specific refund policy are not established by the reviewed documentation.

OpenCode Go Plus
$40 / month ↗

Monthly subscription; one subscriber per workspace. Paid balance fallback is optional. Recurring charges continue until canceled through account settings. Reset anchors, rollover and a Go-specific refund policy are not established by the reviewed documentation.

Pricing, assumptions & evidence

Published base rate

Input $2.00 · Output $6.00 · Cache read $0.25 · Cache write Not listed

Missing token-category prices are not zero. Workload pricing applies exact recorded categories and admitted routes. No benchmark score or quality ranking is inferred from prices.

Aliases, routes and identity

Catalog ID qwen-3-8-max

Model release (kind: release)

Developer: Alibaba Cloud (Qwen)

qwen3.8-max

provider_id