Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

alibaba/qwen3.8-2.4t-a95b

Organization: Alibaba
Family: qwen
Providers: 21
Context: 262,144
Output limit: 131,072
Knowledge: —
Release: 2026-08-12
Updated: 2026-08-12
Weights: Open
Input: text
Output: text
Capabilities: Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

30 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
AIHubMix	qwen3.8-2.4t-a95b	262,000	262,000	$2.00 / $6.00	Yes	Yes	Yes	View
Charm Hyper	qwen3.8-2.4t-a95b	1,000,000	128,000	$2.00 / $6.00	Yes	Yes	Yes	View
Cortecs	qwen3.8-2.4t-a95b	262,144	262,144	$2.50 / $6.00	Yes	Yes	Yes	View
Deep Infra	Qwen/Qwen3.8-2.4T-A95B	262,144	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
DevPass (LLM Gateway)	qwen3.8-2.4t-a95b	1,010,000	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
Eden AI	qwen/qwen3.8-2.4t-a95b	1,000,000	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
Fireworks AI	accounts/fireworks/models/qwen3p8-2p4t-a95b	262,144	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
Hugging Face	Qwen/Qwen3.8-2.4T-A95B	262,144	131,072	$2.50 / $6.25	Yes	Yes	Yes	View
IteraCompute	qwen/qwen3.8-2.4t-a95b	970,000	131,072	$1.95 / $5.95	Yes	Yes	Yes	View
Kilo Gateway	qwen/qwen3.8-2.4t-a95b	1,000,000	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
LLM Gateway	deepinfra/qwen3.8-2.4t-a95b	262,144	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
LLM Gateway	together-ai/qwen3.8-2.4t-a95b	1,010,000	909,000	$2.00 / $6.00	Yes	Yes	Yes	View
LLM Gateway	novita/qwen3.8-2.4t-a95b	1,000,000	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
Merge Gateway	qwen/qwen3.8-2.4t-a95b	262,144	1,010,000	$2.50 / $6.25	Yes	No	No	View
Modal	Qwen/Qwen3.8-2.4T-A95B	1,010,000	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
Alibabavia OpenRouter	qwen/qwen3.8-2.4t-a95b unknown	1,000,000	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
DeepInfravia OpenRouter	qwen/qwen3.8-2.4t-a95b fp4	262,144	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
Modalvia OpenRouter	qwen/qwen3.8-2.4t-a95b unknown	1,000,000	262,144	$2.00 / $6.00	Yes	Yes	Yes	View
Novitavia OpenRouter	qwen/qwen3.8-2.4t-a95b unknown	1,000,000	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
SiliconFlowvia OpenRouter	qwen/qwen3.8-2.4t-a95b fp8	1,048,576	131,072	$2.00 / $6.00	Yes	Yes	Yes	View
Togethervia OpenRouter	qwen/qwen3.8-2.4t-a95b unknown	1,010,000	909,000	$2.00 / $6.00	Yes	Yes	Yes	View
Venicevia OpenRouter	qwen/qwen3.8-2.4t-a95b unknown	262,144	65,536	$2.00 / $6.00	Yes	Yes	No	View
Opper	qwen3.8-2.4t-a95b	262,144	131,072	$2.50 / $6.00	Yes	Yes	Yes	View
Requesty	qwen3.8-2.4T-A95B@eu	1,000,000	262,144	$2.50 / $6.00	Yes	Yes	Yes	View
Requesty	qwen3.8-2.4T-A95B	262,144	262,144	$2.00 / $6.00	Yes	Yes	Yes	View
RunInfra	Inferact/Qwen3.8-2.4T-A95B-NVFP4	262,144	32,768	$2.00 / $6.00	Yes	Yes	Yes	View
SiliconFlow	Qwen/Qwen3.8-2.4T-A95B	1,049,000	131,000	$2.00 / $6.00	Yes	Yes	Yes	View
TensorX	qwen/qwen3.8-2.4t-a95b	262,144	64,000	$2.50 / $6.00	Yes	Yes	Yes	View
Venice AI	qwen-3-8-2-4t-a95b	262,144	65,536	$2.50 / $7.50	Yes	Yes	Yes	View
Vercel AI Gateway	alibaba/qwen3.8-2.4t-a95b	262,144	128,000	$2.00 / $6.00	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$1.95Per 1M input tokens

Output from$5.95Per 1M output tokens

Available offers30Across 21 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 7 lowest-priced configurations

InputOutput

Alibabaalibaba

$2.00$6.00

DeepInfradeepinfra/fp4

$2.00$6.00

Modalmodal

$2.00$6.00

Novitanovita

$2.00$6.00

SiliconFlowsiliconflow/fp8

$2.00$6.00

Togethertogether

$2.00$6.00

Venicevenice

$2.00$6.00

qwen/qwen3.8-2.4t-a95bObserved Oct 4, 2026, 11:31 AM UTC

Input: $2.00
Output: $6.00
Cache read: $0.25

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Alibabaalibaba	$2.00	$6.00	$0.25	$2.50
DeepInfradeepinfra/fp4	$2.00	$6.00	$0.20	—
Modalmodal	$2.00	$6.00	$0.25	—
Novitanovita	$2.00	$6.00	$0.25	—
SiliconFlowsiliconflow/fp8	$2.00	$6.00	$0.25	—
Togethertogether	$2.00	$6.00	$0.25	—
Venicevenice	$2.00	$6.00	$0.25	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Alibabaalibaba

2,321–42,448.03 ms

DeepInfradeepinfra/fp4

1,174–5,980.09 ms

Modalmodal

978.5–28,200.59 ms

Novitanovita

2,089–53,727.96 ms

SiliconFlowsiliconflow/fp8

2,089–5,485.16 ms

Togethertogether

1,143–14,492.78 ms

All latency percentiles 7 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	2,321 ms	3,798.25 ms	4,980.7 ms	42,448.03 ms
DeepInfradeepinfra/fp4	1,174 ms	1,430.25 ms	4,437.1 ms	5,980.09 ms
Modalmodal	978.5 ms	4,006.75 ms	7,461 ms	28,200.59 ms
Novitanovita	2,089 ms	5,304 ms	12,338.6 ms	53,727.96 ms
SiliconFlowsiliconflow/fp8	2,089 ms	2,625.5 ms	3,177 ms	5,485.16 ms
Togethertogether	1,143 ms	1,930.5 ms	5,990.2 ms	14,492.78 ms
Venicevenice	1,009 ms	1,610.25 ms	3,032.9 ms	7,023.48 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Alibabaalibaba

40–64.54 t/s

DeepInfradeepinfra/fp4

97–150.3 t/s

Modalmodal

93–142.2 t/s

Novitanovita

31–56.05 t/s

SiliconFlowsiliconflow/fp8

39.5–52.57 t/s

Togethertogether

74–132.32 t/s

All throughput percentiles 7 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	40 t/s	44.25 t/s	48.1 t/s	64.54 t/s
DeepInfradeepinfra/fp4	97 t/s	106.5 t/s	130.8 t/s	150.3 t/s
Modalmodal	93 t/s	109 t/s	122 t/s	142.2 t/s
Novitanovita	31 t/s	36 t/s	40 t/s	56.05 t/s
SiliconFlowsiliconflow/fp8	39.5 t/s	41 t/s	47.7 t/s	52.57 t/s
Togethertogether	74 t/s	90 t/s	103.6 t/s	132.32 t/s
Venicevenice	77.5 t/s	83.5 t/s	96.8 t/s	135.68 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 7 endpoints

Endpoint5 minutes30 minutes24 hours

AlibabaalibabaObserved Oct 4, 2026, 11:31 AM UTC

—

98.65%

DeepInfradeepinfra/fp4Observed Oct 4, 2026, 11:31 AM UTC

—

99.56%

ModalmodalObserved Oct 4, 2026, 11:31 AM UTC

—

100%

95.41%

NovitanovitaObserved Oct 4, 2026, 11:31 AM UTC

—

100%

99.84%

SiliconFlowsiliconflow/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

99.64%

TogethertogetherObserved Oct 4, 2026, 11:31 AM UTC

100%

99.57%

99.93%

VeniceveniceObserved Oct 4, 2026, 11:31 AM UTC

—

92.98%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

qwen/qwen3.8-2.4t-a95bObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 80

Coding

71.9

Agentic

50.1

Intelligence

39.9

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineQwen: Qwen3.8 2.4T A95B

75.467%

gpqa diamondQwen: Qwen3.8 2.4T A95B

86.925%

Evaluation	Configuration	Source	Results	Details
Composite indices	Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b-20260812	Artificial Analysis	Intelligence 39.9 · Coding 71.9 · Agentic 50.1	Details
tau bench verified airline	Qwen: Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b-20260812	OpenRouter	75.467%	Details
gpqa diamond	Qwen: Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b-20260812	OpenRouter	86.925%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

qwen/qwen3.8-2.4t-a95bObserved Oct 4, 2026, 11:31 AM UTC

Context: 1,048,576
Maximum output: 131,072
Tokenizer: Qwen
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2026-08-12

Base URLhttps://openrouter.ai/api/v1

Model IDqwen/qwen3.8-2.4t-a95b

Version IDqwen/qwen3.8-2.4t-a95b-20260812

Weights IDQwen/Qwen3.8-2.4T-A95B

Reasoning

Required: Yes
Enabled by default: Yes
Default effort: xhigh
Supported efforts: xhigh, medium, low

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

Default parameters

top k: 20
top p: 0.95
temperature: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Qwen3.8 2.4T A95B cost?

Listed rates start at $1.95 per million input tokens and $5.95 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Qwen3.8 2.4T A95B?

There are 30 cataloged offers across 21 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Resources

qwen3.8-max

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · df74b59d0f47
Sep 12, 2026 · 45457691124c