Qwen3.8 2.4t A95B

qwen3.8-2.4t-a95b by Qwen Released August 13, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to 35% off
Input from
$1.3 / 1M
Output from
$3.9 / 1M
Cached input from
$0.1625 / 1M
Context window
1.01M
Endpoints
4
from 4 providers
Regions
Global, Europe, United States

About Qwen3.8 2.4t A95B

Qwen3.8-2.4T-A95B is the open-source release of Qwen's latest flagship, launched August 2026. Its sparse MoE architecture holds 2.4T total parameters with ~95B activated per step, paired with hybrid attention and a 1M token context window. Key benchmarks: GPQA Diamond 92.6, PaperBench 93.0, OSWorld 86.1, BabyVision 82.0. Ranked 4th on CodeArena.

Qwen3.8 2.4t A95B is a chat model by Qwen, available on Eden AI through 4 endpoints from 4 providers, from $1.3 per million input tokens and $3.9 per million output tokens, with a context window of up to 1.01M tokens.

Providers and prices

4 endpoints from 4 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
QwenOfficial−35%qwen/qwen3.8-2.4t-a95b
Global
1M
$2$1.3
$3.9
$0.1625
ReasoningToolsJSONCacheVisionWeb
DeepInfra (United States)Official−%deepinfra/Qwen/Qwen3.8-2.4T-A95B
United States
262K
$2$2
$6
$0.2
ReasoningToolsJSONCacheVisionWeb
Together AIOfficial−%together_ai/Qwen/Qwen3.8-2.4T-A95B
Global
1.01M
$2$2
$6
$0.25
ReasoningToolsJSONCacheVisionWeb
TensorX (Europe)Official−%tensorx/qwen/qwen3.8-2.4t-a95b
Europe
262K
$2.5$2.5
$6
$0.625
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
1.09 s
TensorX (Europe)
Lowest latency
3.99 s
TensorX (Europe)
Highest throughput
139.01 tok/s
TensorX (Europe)
Best availability
100%
Together AI
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Qwen
5.38 s
27.97 s
233.2 s
33.99 tok/s
99.9%
87.01%
0.11%
8%
DeepInfra (United States)
s
s
s
tok/s
%
%
%
%
Together AI
s
4.89 s
7.01 s
82.96 tok/s
100%
36.68%
0%
0%
TensorX (Europe)
1.09 s
3.99 s
136.63 s
139.01 tok/s
99.61%
92.11%
0.13%
3.13%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Qwen3.8 2.4t A95B with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about Qwen3.8 2.4t A95B

On Eden AI, prices for this model start at $1.3 per million input tokens and $3.9 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 1.01M tokens, depending on the endpoint.

4 endpoints from 4 providers, available in: Global, Europe, United States. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 1.09 s (TensorX (Europe)) and the highest throughput was 139.01 tokens per second (TensorX (Europe)).