Skip to content
Agnes 2.5 Flash (Free) - ZenMux Multimodal Reasoning Model, 512K Context

Agnes 2.5 Flash (Free) - ZenMux Multimodal Reasoning Model, 512K Context

Model ID sapiens-ai/agnes-2.5-flash
This is a free multimodal model on the ZenMux platform, available at no cost. It supports text and image input.

Model Information

AttributeValue
Context length524,288 tokens
Max output65,536 tokens
Input price$0 / 1M tokens
Output price$0 / 1M tokens
ProviderSapiens AI / ZenMux
StatusFree
Reasoning✅
Input modalitiesText + image

Description

Agnes 2.5 Flash is a multimodal reasoning model from Sapiens AI. It supports text and image input, features a 524K ultra-long context and reasoning capabilities, and is well suited to visual question answering, document understanding, and long-context reasoning tasks. It launched on ZenMux on 2026-08-10.

Usage Example

curl https://zenmux.ai/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sapiens-ai/agnes-2.5-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Related Links

📚 Related Free Models

These models are also available for $0 on ZenMux. Choose by context length and modality.

ModelContextDescription
Ming Image 0.1 Design8KinclusionAI’s text-to-image design model emphasizes text
Ming Image 0.1 Design Layer8KinclusionAI’s image layering model splits flat designs
Dots3 Note393KDots Studio’s omni-modal preview model on ZenMux accepts
GLM 4.6V Flash200KGLM 4.6V Flash is Zhipu’s multimodal vision model. The
GLM 4.7 Flash200KGLM 4.7 Flash is Zhipu’s lightweight Flash-series model.

📋 View all ZenMux free models →

🔗 Site Navigation

Last updated on · Source: ZenMux official documentation and pricing pages. Quotas and prices may change at any time.