Qwen

Qwen3.8 2.4T A95B

Launched 2026-08-12 · Listed on OpenRouter 2026-08-12

Prices updated . Benchmarks updated .

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, with 95 billion active parameters out of 2.4 trillion total. It is...

You send / 1M

$2.00

tokens in

It replies / 1M

$6.00

tokens out

Context

262K

tokens it can read at once

Typical request

$0.0056

1,000 words in, 400 out

Benchmarks

No independent score in the current Epoch or LMArena files, and no lab-reported score on file.

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
Novita$2.00$6.00100%Read
SiliconFlow · fp8$2.00$6.0099%Read
Venice$2.00$6.00100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text
  • Writes: text
  • Weights: Open weights
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 66K tokens
  • Repeated text is billed at $0.250 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with Qwen3.8 2.4T A95B

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.