Qwen

Qwen3.8 2.4T A95B (batch)

qwen/qwen3.8-2.4t-a95b:batch

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Qwen3.8 2.4T A95B (batch)

reasoning open weights tools

Qwen qwen/qwen3.8-2.4t-a95b:batch

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...

Input $/1M: $2.00
Output $/1M: $6.00
Context: 1.0M
Max output: 909K
Released: Aug 12, 2026
Modalities: text

Intelligence index47

Coding index72

Agentic index51

Cached input reads $0.25 per 1M · weights on Hugging Face as Qwen/Qwen3.8-2.4T-A95B

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Qwen3.8 2.4T A95B (batch)
targets:
  - id: qwen3-8-2-4t-a95b-batch
    kind: llm
    name: Qwen3.8 2.4T A95B (batch)
    metadata:
      model: qwen/qwen3.8-2.4t-a95b:batch          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 1010000
    cost:
      usd_per_1k_tokens: 0.004000

Price among Qwen models

Input list price per million tokens; Qwen3.8 2.4T A95B (batch) is the 11th cheapest of 13 listed.

1
Qwen3.7 Flash
$0.03
2
Qwen3.6 35B A3B
$0.10
3
Qwen3.8 Flash
$0.15
4
Qwen3.6 Flash
$0.19
5
Qwen3.5 Plus 2026-04-20
$0.30
6
Qwen3.6 27B
$0.30
7
Qwen3.7 Plus
$0.32
8
Qwen3.8 27B
$0.42
9
Qwen3.6 Max Preview
$1.03
10
Qwen3.7 Max
$1.48
11
Qwen3.8 2.4T A95B (batch)
$2.00
12
Qwen3.8 Max (0902)
$2.00

More from Qwen

Other models by the same vendor in the catalogue.