Cohere
Command R7B
Command R7B from Cohere: Cohere retrieval model for long-context chat and enterprise RAG workflows.
- Context
- 128K
- Max output
- 4K
- Input / 1M tokens
- $0.0375
- Output / 1M tokens
- $0.15
Accepts
- Text input
Produces
- Text output
AI model comparison
Compare pricing, context limits, supported inputs and deployment options to choose a model for your workflow.
Command R7B from Cohere lists 128K context, 4K maximum output, $0.0375 input per 1M tokens, $0.15 output per 1M tokens. Command R7B Arabic from Cohere lists 128K context, 4K maximum output, $0.0375 input per 1M tokens, $0.15 output per 1M tokens. Compare the inputs, outputs and deployment options below to see which fits your workflow.
Cohere
Command R7B from Cohere: Cohere retrieval model for long-context chat and enterprise RAG workflows.
Accepts
Produces
Cohere
Command R7B Arabic from Cohere: Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge.
Accepts
Produces
At a glance
Compare the available figures below, then try both models on the work you need to do.
Context capacity
Higher listed limit
Command R7B:128K
Command R7B Arabic:128K
Same value
Maximum output
Higher listed limit
Command R7B:4K
Command R7B Arabic:4K
Same value
Input price
Lower listed token rate
Command R7B:$0.0375
Command R7B Arabic:$0.0375
Same value
Output price
Lower listed token rate
Command R7B:$0.15
Command R7B Arabic:$0.15
Same value
Specifications
| Specification | Command R7B | Command R7B Arabic |
|---|---|---|
| Provider | Cohere | Cohere |
| Listed pricing route | Cohere | Cohere |
| Model family | command-r | command-r |
| Accepted inputs | text | text |
| Produced outputs | text | text |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input price / 1M | $0.0375 | $0.0375 |
| Output price / 1M | $0.15 | $0.15 |
| Reasoning mode | Not documented | Not documented |
| Tool calling | Documented | Documented |
| Image input | Not documented | Not documented |
| Audio input | Not documented | Not documented |
| Structured output | Not documented | Not documented |
| License | Open weights | Open weights |
Workload guidance
The recorded figures alone do not establish a clear choice. Test both on the same representative examples and judge the output against your acceptance criteria. Include tool failures, retries and the time to a completed task.
Explore each model’s features, API requirements and licence terms in the sources below.
Command R7B
Cohere
Profile updated Oct 13, 2026
Model card and weights ↗Command R7B Arabic
Cohere
Profile updated Oct 13, 2026
Model card and weights ↗Documentation and references ↗Search by model or provider to explore another comparison.