ModelPickr

Models / Vispark / Vision Small

Vispark

Vision Small

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

$1.05 in · $3.16 out

per 1M tokens · first-party price. Reference price from Vispark, the lab's own listing.

Context
1,000,000
Max output
65,536
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
May 15, 2024
Updated in source
Sep 1, 2026
Knowledge
—
Providers
1

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Vision Small

$11.04

Cache hit is ignored because this model has no cache-read price.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Visparkreference$1.05$3.16———