V

Vispark

3 Canonical Models

Vispark foundation models, inference API endpoints, and pricing.

Official Provider Docs
Endpoint: https://api.lab.vispark.in/v1•Package: @ai-sdk/openai-compatible•Env Key: VISPARK_LAB_API_KEY

Models by Vispark

Specifications, context windows, and pricing for Vispark models

3 models
Vision Small
vispark/vision-small•Vispark
1M ctx

Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.

65.5K out maxVisionPDF
In: $1.05 • Out: $3.16
Vispark
Vision Medium
vispark/vision-medium•Vispark
1M ctx

Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.

65.5K out maxVisionPDF
In: $4.21 • Out: $12.63
Vispark
Vision Large
vispark/vision-large•Vispark
1M ctx

Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.

65.5K out maxVisionPDF
In: $7.37 • Out: $22.11
Vispark