Jahanzaib
Vispark: Vision SmallOfficial docs

Vispark: Vision Small

byVispark
Official docs

Vision Small is a reasoning model from Vispark released on May 15, 2024. It reads text, images, files, audio and video and writes text, with a 1M token context window and up to 66K tokens per reply.

Show more

It costs $1.05 per million input tokens and $3.16 per million output tokens.

It supports tool calling and structured JSON output.

Modalities
In / out price
$1.05 / $3.16 per 1M
Context
1M
Max output
66K
Released
May 15, 2024
Knowledge cutoff
n/a
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Vision Small pricing

USD, as listed on Oct 24, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$1.05 / 1M tokens
Output$3.16 / 1M tokens

What Vision Small costs per month

Pick a workload close to yours or type your own volumes.

Vision Small per month
$112
Without caching
$112
Per request
$0.0037

Supported request parameters

What you can set when you call Vision Small through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning
  • Temperaturetemperature

Alternatives to Vision Small

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Google: Gemini 3.8 Flash

    Index 40.9

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 30 providers.

    by googleSep 2, 20261.05M context$0.75/M input tokens$3.75/M output tokens30 providers

  • Google: Gemini 3.6 Flash

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 27 providers.

    by googleJul 21, 2026$0.75/M input tokens$3.75/M output tokens27 providers

  • Google: Gemini 3.7 Flash

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 25 providers.

    by googleAug 13, 2026$0.75/M input tokens$3.75/M output tokens25 providers

  • Google: Gemini Flash Latest

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 7 providers.

    by googleAug 13, 2026$0.75/M input tokens$3.75/M output tokens7 providers

  • Google: Gemini 3.5 Flash Lite

    Index 22.2

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 27 providers.

    by googleJul 21, 20261.05M context$0.30/M input tokens$2.50/M output tokens27 providers

  • Google: Gemini 2.5 Flash

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 25 providers.

    by googleJun 17, 2025$0.30/M input tokens$2.50/M output tokens25 providers

More from Vispark

  • Vision Large

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning.

    by visparkMay 15, 2024$7.37/M input tokens$22.11/M output tokens

  • Vision Medium

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning.

    by visparkMay 15, 2024$4.21/M input tokens$12.63/M output tokens

All Vispark models

Vision Small questions

How much does the Vision Small API cost?

$1.05 per million input tokens and $3.16 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Vision Small?

1,000,000 tokens of input, and it can write up to 65,536 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Does Vision Small support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is Vision Small open source?

No. Vispark serves it through an API only, so you cannot download the weights or host it yourself.

When was Vision Small released?

May 15, 2024.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 24, 2026. The summary is written from these facts.