← All models
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](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
At a glance
- Context window
- 1Mtokens
- Max output
- 131Ktokens
- Knowledge to
- —
- Released
- 2026
Capabilities
CapabilitiesReasoningToolsStructured output
InputText
OutputText
ReasoningSupportedxhighmediumlow
Benchmarks
- Intelligence index
- 40
- Coding index
- 72
- Agentic index
- 50
Standard evaluations
| Benchmark | Score | Tasks |
|---|---|---|
| gpqa_diamond | 0.86 | 594 |
| tau_bench_verified_airline | 0.77 | 100 |
Source: Artificial Analysis · as of Sep 16, 2026
Performance
Uptime on IranRouter
98.5%
Aug 18Sep 16
Reference uptime
100%
Aug 18Sep 16
Median latency
1,719 ms
Aug 18Sep 16
Throughput
44.8 tok/s
Aug 18Sep 16
IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Parameters this model accepts; anything else is ignored.
Quick start
from openai import OpenAI
client = OpenAI(
api_key="ir-...",
base_url="https://iranrouter.com/v1",
)
resp = client.chat.completions.create(
model="qwen/qwen3.8-2.4t-a95b",
messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)Only base_url and the key change; the rest of your code stays as it is.