Jahanzaib
Cohere: Command A VisionWork with me

Cohere: Command A Vision

byCohere

Command A Vision is a language model from Cohere released on Jul 31, 2025. It reads text and images and writes text, with a 128K token context window and up to 8K tokens per reply.

Show more

It costs $2.50 per million input tokens and $10 per million output tokens.

Its weights are open, so you can host it yourself.

Modalities
In / out price
$2.50 / $10 per 1M
Context
128K
Max output
8K
Released
Jul 31, 2025
Knowledge cutoff
Jun 2024
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Command A Vision pricing

USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$2.50 / 1M tokens
Output$10 / 1M tokens

What Command A Vision costs per month

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

Command A Vision per month
$293
Without caching
$293
Per request
$0.0097

Supported request parameters

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

  • Temperaturetemperature

Alternatives to Command A Vision

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

  • OpenAI: GPT-6.1 Sol

    Index 51.8

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

    by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens27 providers

  • Anthropic: Claude Sonnet 5.5

    Index 56

    Reads text, images and files. Tool calling, structured output, reasoning. Served by 26 providers.

    by anthropicSep 26, 20261M context$2/M input tokens$10/M output tokens26 providers

  • OpenAI: GPT-6 Sol

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

    by openaiSep 22, 2026$2/M input tokens$10/M output tokens27 providers

  • Anthropic: Claude Sonnet 5

    Reads text, images and files. Tool calling, structured output, reasoning. Served by 38 providers.

    by anthropicJun 29, 2026$2/M input tokens$10/M output tokens38 providers

  • Amazon Nova 2 Pro (Preview)

    Index 14.2

    Reads text, images, audio and video. Reasoning.

    by amazonDec 2, 20251M context$1.25/M input tokens$10/M output tokens

  • Google: Gemini 2.5 Pro

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

    by googleFeb 5, 2025$1.25/M input tokens$10/M output tokens30 providers

More from Cohere

  • Embed 5 Fast

    Embeddings

    Turns text into vectors for search and retrieval.

    by cohereSep 30, 2026

  • Embed 5 Pro

    Embeddings

    Turns text into vectors for search and retrieval.

    by cohereSep 30, 2026

  • North Small Translate

    Reads text.

    by cohereSep 9, 2026$0/M input tokens$0/M output tokens

  • North Mini Code (free)

    Reads text. Tool calling, reasoning.

    by cohereJun 17, 2026$0/M input tokens$0/M output tokens

  • North Mini Code

    Index 9.9

    Reads text. Tool calling, structured output, reasoning.

    by cohereJun 9, 2026256K context$0/M input tokens$0/M output tokens

  • Command A+

    Index 13.1

    Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.

    by cohereMay 20, 2026192K context$0.30/M input tokens$1.50/M output tokens2 providers

All Cohere models

Command A Vision questions

How much does the Command A Vision API cost?

$2.50 per million input tokens and $10 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 Command A Vision?

128,000 tokens of input, and it can write up to 8,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Does Command A Vision support tool calling?

Not through the standard tools parameter. For an agent that calls your APIs, pick a model from the alternatives below that does.

Is Command A Vision open source?

Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.

When was Command A Vision released?

Jul 31, 2025, with training data up to Jun 2024.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.

Building on Command A Vision?

I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.

Book Meeting