Skip to content
LLMs
Qwen logo

Qwen: Qwen3.8 2.4T A95B

by Qwen

Qwen: Qwen3.8 2.4T A95B is a large language model from Qwen. It costs $2.00 per million input tokens and $6.00 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weights
Input / 1M tokens
$2.00
Output / 1M tokens
$6.00
Cached input / 1M
$0.250

On repeated prefixes

Context window
1.0M

tokens

Who serves it cheapest

7 hosts serve Qwen3.8 2.4T A95B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Qwen: Qwen3.8 2.4T A95B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
NovitaCheapest$2.00$6.001M-99.8%
Alibaba$2.00$6.001M-99.7%
SiliconFlowfp8$2.00$6.001.0M-95.7%
Venice$2.00$6.00262K-97.4%
Modal$2.00$6.001M-99.9%
DeepInfrafp4$2.00$6.00262K-98.7%
Together$2.00$6.001.0M-100.0%

The spread between Novita and Together is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
40.0
Coding index
71.9
Agentic index
50.4

About Qwen3.8 2.4T A95B

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...

Specifications

Qwen: Qwen3.8 2.4T A95B specifications
Model IDqwen/qwen3.8-2.4t-a95b
ProviderQwen
Context window1.0M tokens
Max output131K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - Qwen/Qwen3.8-2.4T-A95B
ReleasedAugust 12, 2026

Cheaper alternatives

Models that cost less than Qwen3.8 2.4T A95B while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Qwen: Qwen3.8 2.4T A95B cost?

$2.00 per million input tokens and $6.00 per million output tokens. Cached input reads cost $0.250 per million tokens.

What is the context window of Qwen: Qwen3.8 2.4T A95B?

1.0M tokens, with up to 131K tokens of output per request.

Which provider serves Qwen: Qwen3.8 2.4T A95B cheapest?

Novita at $2.00 per million input tokens - about the same cheaper than Together, the most expensive of the 7 hosts serving it.

Confirm against the source: Qwen official pricing.