Qwen3.8 Max

qwen3.8-max by Qwen Released August 3, 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

Endpoints

from 2 providers

Regions

Monde, États-Unis

About Qwen3.8 Max

Modèle phare MoE de 2,4 billions de paramètres offrant une avancée majeure en matière de codage et de travail professionnel. Il code de manière autonome et livre des projets complets s’étalant sur plus de 10 jours. Il prend en charge des centaines de tâches spécialisées dans les domaines juridique, financier, du design et d’autres secteurs professionnels, produisant des résultats de qualité professionnelle de bout en bout au cours d’une seule conversation. Sa compréhension visuelle native couvre l’ensemble du cycle de planification, d’exécution et de vérification, permettant une analyse sémantique approfondie de documents très longs et de contenus vidéo étendus. Dans le cadre de tâches à long terme, il planifie de manière autonome, itère grâce à des boucles de rétroaction fermées et évolue en permanence.

Qwen3.8 Max est un modèle conversationnel développé par Qwen, disponible sur Eden AI via 2 endpoints chez 2 fournisseurs, à partir de 1,3 $ par million de tokens en entrée et 3,9 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1M tokens.

Providers and prices

2 endpoints from 2 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-max

Monde

$2$1.3

$3.9

$0.1625

ReasoningToolsJSONCacheVisionWeb

DeepInfra (États-Unis)Official−%deepinfra/Qwen/Qwen3.8-Max

États-Unis

256K

$1.65$1.65

$4.951

$0.206

ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token

2.98 s

Qwen

Lowest latency

11.09 s

Qwen

Highest throughput

32.55 tok/s

Qwen

Best availability

100%

DeepInfra (États-Unis)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

Qwen

2.98 s

11.09 s

125.01 s

32.55 tok/s

99.7%

80.63%

11.27%

4.08%

DeepInfra (États-Unis)

3.89 s

14.18 s

134.88 s

30.33 tok/s

100%

85.61%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Qwen3.8 Max 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())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about Qwen3.8 Max

How much does Qwen3.8 Max cost?

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. .

What is the context window of Qwen3.8 Max?

Up to 1M tokens, depending on the endpoint.

Which providers serve Qwen3.8 Max?

2 endpoints from 2 providers, available in: Monde, États-Unis. All of them are called with the same Eden AI API key.

Can I run Qwen3.8 Max in the EU?

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.

How fast is Qwen3.8 Max?

Over the last 30 days, the fastest first token was 2.98 s (Qwen) and the highest throughput was 32.55 tokens per second (Qwen).

About Qwen3.8 Max

Providers and prices

Performance

Estimate your monthly cost

Call Qwen3.8 Max with Eden AI

Questions about Qwen3.8 Max

More from Qwen