Back to models
Chat Models

Cohere

Command A Vision

Best for Research

Text and image understanding for documents, tables and charts, with up to 20 images per request and no tool use.

VisionDocuments
Open AppBrowse All Models

At a glance

Know the model before you prompt.

Cohere API specifications
Context window
128,000 tokens
Maximum output
8,000 tokens
Inputs → output
Text + Images → Text
Knowledge cutoff
June 1, 2024

API model ID: command-a-vision-07-2025

Capabilities & boundaries

What it supports. Where the limits are.

Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.

Supported API features and tools

  • Text and image input with text output
  • Up to 20 images in a documented request
  • Document OCR, table extraction and chart interpretation
  • A 128,000-token context and 8,000-token maximum output

Before you choose

  • Tool use is not supported by this model; do not build a direct tool-calling loop around its ID.
  • It accepts images but does not generate them. Blurred labels and cropped tables require review, not inferred values.
  • Free use is bounded by rate limits; Cohere directs production arrangements to sales.
  • Context capacity is not a guarantee of complete recall. Keep source IDs, evaluate omissions and verify citations against the underlying documents.
  • A generated plan or tool call does not authorize or execute an external action. Use a configured integration, validate results and keep consequential changes behind human approval.

Reasoning behavior

The reviewed model-specific sources do not establish hybrid thinking controls or an effort-level list for this ID. Do not copy Command A Reasoning's thinking settings into other Command models. State the goal, evidence and answer format, then verify the result.

  • Use command-a-vision-07-2025 for the model covered here. The website slug is a navigation label, not necessarily the API model ID.
  • Use the image-input request format and check image-count and token limits before sending large batches.
  • Do not confuse labels in a generic capability legend with support for this model. The model-specific limitation explicitly excludes tool use.
  • If a workflow needs external retrieval or actions, keep those steps in a separately authorized application layer and validate the extracted evidence before use.

Put it to work

Start with a more useful prompt.

Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.

Workflow 01

Extract a table from a scan

Preserve units and identify unreadable cells.

Read the table in this supplied image and return its headers, rows and units. Preserve visible formatting where it changes meaning. Mark unreadable or cropped cells explicitly instead of estimating them. Add a verification list for totals, decimal separators and footnotes before anyone imports the data into another system.

Workflow 02

Explain a chart without overclaiming

Separate plotted evidence from interpretation.

Describe this chart using only what is visible. Identify axes, units, legend entries and the main pattern, citing the relevant label or region. Flag unclear scales, missing baselines and any conclusion the chart does not support. Do not invent exact values from an imprecise image or infer causes from correlation.

Workflow 03

Compare document versions visually

Make changes auditable across page images.

Compare these two document images and list visible changes in headings, values, clauses and footnotes. Identify each change by page or image label. Separate confirmed differences from OCR uncertainty and note any content cut off by the screenshots. Do not treat the comparison as a legal judgment or silently normalize different wording.

Developer reference

Cohere API pricing

These are Cohere API reference terms, not EZ Ai Assist subscription prices.

View EZ Ai Assist plans

The current model card offers trial and production keys free usage until rate limits are reached. This is not unlimited free production. Cohere directs production deployments to its sales team. No public per-token production rate is established here.

  • Confirm limits for your exact model and key type; a production key alone is not evidence of unrestricted capacity.
  • Obtain deployment-specific commercial terms before budgeting. Do not substitute another Command model's token rates or show unverified prices as $0.

Common questions

A few things worth knowing.

How many images can a request include?

The model page documents up to 20 images. That does not remove token or request constraints; check the image-input guide and the readability of each image before batching.

Does A Vision support tool calls?

No. The model-specific page explicitly says tool use is unsupported. An application can orchestrate separate steps, but that is not native tool support for this model ID.

Can it generate new images?

No. Its image capability is input understanding with text output. Use a dedicated image-generation model when the desired result is a new image.

What are the production pricing terms?

The card describes free API usage within rate limits and asks production users to contact sales. No public per-token production rate is asserted here, and the standard Command A rate is not substituted.

Can it see current information automatically?

No. Model knowledge and a long context are not a live search service. Provide current evidence or connect an authorized retrieval workflow where supported, and verify the sources before acting on an answer.

How should I test it on my own work?

Use representative examples, explicit pass criteria and difficult counterexamples. Score factual support, omitted requirements and invalid outputs as well as latency and cost. Keep a human escalation path for uncertain or consequential results.

Are these API capabilities included in my EZ Ai Assist plan?

This guide describes the provider API, not subscription entitlements or a promise that every setting is exposed in the app. Check your workspace for model access and supported inputs, and use the EZ Ai Assist pricing page for plan details.

Check the source

Official documentation

Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.

Same provider

More from Cohere

Cohere

Command A+

Multimodal Cohere MoE with hybrid reasoning, 48-language support and a 128K context window.

Cohere

Command A

Text-focused Cohere model for grounded answers and tool workflows, with 256K context and 8K output.

Cohere

Command A Reasoning

Hybrid text reasoning with optional thinking budgets, 256K context and 32K output for evidence-heavy workflows.

Cohere

Command A Translate

Specialized text translation across 23 languages, with separate 8K input and 8K output limits.