فا

Qwen: Qwen3.8 2.4T A95B

by Qwen

qwen/qwen3.8-2.4t-a95b
UnavailableOpen weights

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...

Context

1Mtokens

About 1,498 pages of text at once

Max output

131Ktokens

About 187 pages in one answer

Intelligence

—

No score published for this model.

Output speed

38tokens/s

A 500-word answer in about 18.3 s

From public market statistics for this model

First token

1.9s

Reasoning models start later

From public market statistics for this model

Health, 30 days

50.00%

0 of 30 days without a fault

IranRouter’s measurements

Price & cost

Every rate in Rial. A request pays only for the tokens it actually uses.

Input5,471,931IRR / 1M tokens
Output16,415,793IRR / 1M tokens
Reasoning tokensThe output rate16,415,793IRR / 1M tokens
Cache read683,991IRR / 1M tokens

With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.

What would this model cost you a month?

Monthly cost

787.96MIRR

26.27M IRR a day, 13K IRR each request

30 days at today’s rate.

Rial price over 90 days

It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.

InputOutput

Performance, 30 days

Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.

Daily health50.00%

Time to first token2.13 s

Output speed51 tokens/s

Place in the market

By usage across the global model market.

This model isn’t ranked yet.

Capabilities

Image inputNo
Audio inputNo
Tool callingYes
JSON outputYes
ReasoningReasoning levels: xhigh, medium, low
Web searchNo
Prompt cacheYes
Makes imagesNo
Open weightsYes
On the free planNo
Input
Text
Output
Text

Parameters it accepts

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Other benchmarks

Coding index72
Agentic index50

Standard tests

  • GPQA DiamondScore: 87%Tasks: 1,782
  • τ-bench Verified AirlineScore: 75%Tasks: 400

Start in a minute

The official OpenAI and Anthropic SDKs; only the address and the key change.

Base URLhttps://iranrouter.com/v1
Model IDqwen/qwen3.8-2.4t-a95b
API keyCreate one in the dashboard
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://iranrouter.com/v1",
    api_key="ir-...",
)

r = client.chat.completions.create(
    model="qwen/qwen3.8-2.4t-a95b",
    messages=[{"role": "user", "content": "Hello, introduce yourself"}],
)
print(r.choices[0].message.content)
The full guide in the docs: keys, streaming and errors

Peer models

Its family and models with a close score; the last column compares one message’s cost with this model.

No peer models found.

Technical specs

ID
qwen/qwen3.8-2.4t-a95b
Maker
Qwen
Tokenizer
Qwen
Released
Aug 12, 2026
Added to IranRouter
Aug 19, 2026
Context
1,048,576 tokens
Max output
131,072 tokens
Weights
Qwen/Qwen3.8-2.4T-A95B

Default parameters

top_k=20top_p=0.95temperature=1

Scores by Artificial Analysis, as of Oct 31, 2026

Qwen: Qwen3.8 2.4T A95BOne message about 19,150 IRRStart with this model