Qwen3.8 2.4T A95B (NVFP4) by RunInfra

$10 off the fastest Kimi K3 and GLM 5.2$10 off the fastest Kimi K3 and GLM 5.2

Discuss

Model details

Qwen3.8 2.4T A95B (NVFP4)

RunInfraInferact/Qwen3.8-2.4T-A95B-NVFP4qwen

Open provider page Provider docs

Quick Info

Provider: RunInfra
Model key: Inferact/Qwen3.8-2.4T-A95B-NVFP4
Release date: Aug 12, 2026

Cost

Input token cost: $2.00
Output token cost: $6.00

Limits

Output tokens: 32,768 tokens
Context window

Latest news about Qwen3.8 2.4T A95B (NVFP4)

Videos about Qwen3.8 2.4T A95B (NVFP4)

More models around Qwen3.8 2.4T A95B (NVFP4)

Browse family

Also served by

This exact model name is also listed by 9 other providers.

Cortecs Deep Infra Eden AI Hugging Face Kilo Gateway Merge Gateway OpenRouter Requesty Vercel AI Gateway

25 providers

Qwen3.7 Plus

Currently listed through these providers:

AIHubMix Alibaba Alibaba (China)Alibaba Coding Plan Alibaba Coding Plan (China)+20 more

21 providers

Qwen3.8 Max

Currently listed through these providers:

Abacus AIHubMix Alibaba Alibaba (China)Alibaba Token Plan +16 more

15 providers

Qwen3.8 27B

Currently listed through these providers:

RunInfra Cloudflare Workers AI Cortecs CrofAI Deep Infra +10 more

8 providers

Qwen3.7 Flash

Currently listed through these providers:

Alibaba (China)Charm Hyper CrossModel EmpirioLabs AI Kilo Gateway +3 more

5 providers

Qwen3.8 Max Preview

Currently listed through these providers:

Alibaba Token Plan Alibaba Token Plan (China)Charm Hyper DevPass (LLM Gateway)Impossibl

3 providers

Qwen 3.7 Plus

Currently listed through these providers:

Fireworks AI Venice AI Vercel AI Gateway

2 providers

Qwen 3.8 Max

Currently listed through these providers:

Venice AI Vercel AI Gateway

1 provider

Qwen 3.8 27B Uncensored

Currently listed through:

NanoGPT

1 provider

Qwen 3.8 27B

Currently listed through:

Venice AI

1 provider

Qwen3.8 27B TEE

Currently listed through:

Chutes

1 provider

Qwen3.8 27B Thinking

Currently listed through:

NanoGPT

1 provider

Qwen 3.8 2.4T

Currently listed through:

Venice AI

Discuss this model

Powered byHyvor Talk

Add corrections, implementation notes, pricing changes, or usage caveats for other readers.