Qwen3.8 27B model profile

Evidence snapshot: 2026-09-06

Qwen3.8 27B is a Alibaba Qwen model profile with a 1,000,000-token context window. The dated catalog snapshot records text, image, video modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.

Qwen3.8 27B is a reference profile: Alibaba Qwen publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.

Qwen3.8 27B is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.

Qwen3.8 27B accepts text, image, and video and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, tool calling, video input, and vision as capabilities or interfaces.

The dated reference snapshot lists $0.15 input and $2 output per million tokens. Cached input is $0.032 per million tokens.

Qwen3.8 27B ranked #50 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.

Profile facts

Profile type: Model research profile
Provider or publisher: Alibaba Qwen
Context window: 1,000,000 tokens
Snapshot date: 2026-09-06
Knowledge cutoff: Not disclosed
Reference catalog ID: qwen/qwen3.8-27b

When to pick Qwen3.8 27B

Qwen3.8 27B is a reference profile: Alibaba Qwen publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.

Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.

Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described.
Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
Reach for it when you want to trade depth against cost per call. Reasoning effort is selectable across xhigh, medium, low, so one route can serve both cheap and deep work.
Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
Look elsewhere when the task is hard reasoning. Its 41.4 Artificial Analysis intelligence index is below the median of the 32 models carrying that field. Scores from different suites are not interchangeable, so treat this as one signal rather than a ranking.

Context, modalities, and identity

Provider or publisher: Alibaba Qwen
Context window: 1,000,000 tokens
Maximum output: 131,072 tokens
Input modalities: text, image, and video
Output modalities: text
Knowledge cutoff: Not disclosed

Model overview

Reference model ID: qwen/qwen3.8-27b
Canonical version: qwen/qwen3.8-27b-20260814
Hugging Face ID: Qwen/Qwen3.8-27B

Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

prompt caching
reasoning controls
structured output
text generation
tool calling
video input
vision

Dated pricing snapshot

The dated reference snapshot lists $0.15 input and $2 output per million tokens. Cached input is $0.032 per million tokens.

These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.

Price date: 2026-09-06
Input: $0.15 per 1M tokens
Cached input: $0.032 per 1M tokens
Output: $2 per 1M tokens

Provider routes, performance, and uptime

The snapshot retains 13 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.

Active provider endpoints: 11
Best p50 latency: 0.58 s
Best p50 throughput: 102.5 tok/s
Availability with routing: 99.78% over the sampled window
Availability without routing: 96.05% over the sampled window
Performance date: 2026-09-06

Provider	Quantization	Input / 1M	Output / 1M	Cache read / 1M	Context	p50 latency	p50 throughput	Uptime (1d)
Darkbloom	fp4	$0.15 / 1M	$2 / 1M	No verified rate	262,144 tokens	4.63 s	38 tok/s	99.43%
Parasail	fp8	$0.24 / 1M	$2.2 / 1M	$0.05 / 1M	262,144 tokens	1.27 s	55 tok/s	99.59%
AkashML	fp8	$0.25 / 1M	$2.2 / 1M	$0.05 / 1M	262,144 tokens	0.68 s	55 tok/s	99.51%
Phala	unknown	$0.3 / 1M	$3 / 1M	$0.05 / 1M	262,144 tokens	0.90 s	64.5 tok/s	99.09%
Chutes	fp8	$0.32 / 1M	$2.5 / 1M	$0.032 / 1M	262,144 tokens	1.98 s	33 tok/s	99.08%
CoreWeave	fp8	$0.4 / 1M	$3 / 1M	$0.15 / 1M	262,144 tokens	0.85 s	45 tok/s	99.90%
NovitaAI	unknown	$0.42 / 1M	$3 / 1M	$0.085 / 1M	1,000,000 tokens	2.23 s	33 tok/s	99.79%
Alibaba Cloud Int.	unknown	$0.425 / 1M	$2.55 / 1M	$0.085 / 1M	1,000,000 tokens	1.04 s	47 tok/s	99.85%
io.net	fp8	$0.432 / 1M	$3.06 / 1M	$0.225 / 1M	65,536 tokens	1.06 s	76 tok/s	99.85%
Cloudflare	unknown	$0.45 / 1M	$3.2 / 1M	$0.05 / 1M	262,144 tokens	0.88 s	39 tok/s	88.33%
Venice	fp8	$0.45 / 1M	$3.2 / 1M	No verified rate	262,144 tokens	0.86 s	102.5 tok/s	99.30%
Reka AI	fp8	$0.214 / 1M	$2.55 / 1M	$0.15 / 1M	262,144 tokens	0.58 s	50 tok/s	98.84%
Ionstream	fp8	$0.35 / 1M	$2.55 / 1M	$0.05 / 1M	262,144 tokens	0.80 s	68 tok/s	98.86%

Benchmark evidence and limitations

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Intelligence Index: 41.4
Coding Index: 68.1
Agentic Index: 46.8
AutoExacto coverage: 15 provider observations over 32 days

AutoExacto provider benchmarks

Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.

Provider	GPQA Diamond	TAU-Bench Airline	Runs
AkashML	81.61%	76.53%	4
Alibaba Cloud Int.	83.24%	76.06%	4
auto-routing	82.14%	78.43%	3
Chutes	82.54%	78.92%	4
Cloudflare	81.83%	78.1%	3
CoreWeave	81.13%	76.27%	4
Darkbloom	80.66%	—	2
io.net	80.15%	78.67%	4
Ionstream	81.14%	70.29%	2
Morph	87.19%	—	1
NovitaAI	82.82%	77.26%	3
Parasail	83.12%	78.2%	4
Phala	67.33%	70.82%	3
Reka AI	77.44%	75.84%	4
Venice	79.49%	72.85%	4

Popularity and market context

Third-party catalog rank: #50
Global market share: Not inferred
Observation date: 2026-09-06

Frequently asked questions

When should I use Qwen3.8 27B?

Qwen3.8 27B is a reference profile: Alibaba Qwen publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Reach for it when you want to trade depth against cost per call: Reasoning effort is selectable across xhigh, medium, low, so one route can serve both cheap and deep work. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. Look elsewhere when the task is hard reasoning: Its 41.4 Artificial Analysis intelligence index is below the median of the 32 models carrying that field. Scores from different suites are not interchangeable, so treat this as one signal rather than a ranking.

What is Qwen3.8 27B?

What context window does Qwen3.8 27B have?

The dated profile lists 1,000,000 tokens of context and up to 131,072 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.

What benchmark evidence is available for Qwen3.8 27B?

The 2026-09-06 snapshot includes 3 Artificial Analysis indexes and AutoExacto results for 15 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Is Qwen3.8 27B available through Kendr?

This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.

Does the popularity rank represent Qwen3.8 27B's global market share?

Sources and evidence dates

Qwen3.8 27B third-party catalog record (catalog, checked 2026-09-06)
Third-party model catalog methodology (methodology, checked 2026-09-06)
Alibaba Qwen official model documentation (primary, checked 2026-09-06)
Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
Qwen3.8 27B third-party catalog record (benchmark, checked 2026-09-06)