Qwen3.8 2.4T A95B (NVFP4) API
About
Build advanced reasoning agents with Qwen3.8 2.4T A95B (NVFP4), a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $2.00/1M input and $6.00/1M output tokens, native tool calling support, open weights architecture. Access Qwen3.8 2.4T A95B (NVFP4) via the RunInfra API with up to 33K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsOpen
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
33K
Tokens
Pricing
Standard (per 1M tokens)
Input
$2.00
Output
$6.00
Caching (per 1M tokens)
Read
$0.20
Frequently Asked Questions
Qwen3.8 2.4T A95B (NVFP4) by RunInfra costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. Cached reads cost $0.20 per 1M tokens.
Model Details
ID
Inferact/Qwen3.8-2.4T-A95B-NVFP4
Provider
RunInfraFamily
qwen
Release Date
Aug 12, 2026
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
RUNINFRA_GATEWAY_KEY
API Base URL
https://api.runinfra.ai/v1