Cohere logo

Command A Vision


Command A Vision is Cohere logoCohere's language model with a 128K context window and up to 8K output tokens, starting at $1.56 / 1M input and $1.56 / 1M output. Cohere's first multimodal Command model capable of processing images, excelling at chart analysis, OCR, document Q&A, and object detection.
Spec
Canonical IDcohere-command-a-vision
TypeLanguage
StatusActive
CreatorCohereCohere
Providers
Context Window128K tokens
Max Output8K tokens
Input ModalitiesImageText
Output ModalitiesText

Capabilities

Input2/5
Text
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Oracle Cloud (OCI) logo
Oracle Cloud (OCI)
oci/cohere.command-a-vision-07-2025
$1.56$1.56

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Command Light Text4K$0.300$0.600Available
Command Text4K$1.50$2.00Available
Command A256K$1.56$1.56Available
Command R7B128K$0.037$0.150Available
Command R128K$0.150$0.150Deprecated
Command R+128K$1.56$1.56Deprecated
Command A Vision128K$1.56$1.56Current
Command128K$1.00$1.56Deprecated
Command A Reasoning256K$1.56$1.56Available
Command A Translate256K$0.090$0.090Available
Command Light4K$0.300$0.600Deprecated

Model IDs